CN117974073B

CN117974073B - Electric power engineering digital model calculation amount statistical method and system based on Revit software

Info

Publication number: CN117974073B
Application number: CN202410375469.7A
Authority: CN
Inventors: 欧阳凯斌; 卢文伟; 唐睿; 卜小宝; 杨观村
Original assignee: Shenzhen Huajian Power Engineering Technology Co ltd
Current assignee: Shenzhen Huajian Power Engineering Technology Co ltd
Priority date: 2024-03-29
Filing date: 2024-03-29
Publication date: 2024-06-25
Anticipated expiration: 2044-03-29
Also published as: CN117974073A

Abstract

The application relates to the technical field of data processing, and provides a calculation amount statistical method and a calculation amount statistical system of a digital model of an electric power engineering based on Revit software.

Description

Electric power engineering digital model calculation amount statistical method and system based on Revit software

Technical Field

The application relates to the technical field of data processing, in particular to a power engineering digital model calculation amount statistical method and system based on Revit software.

Background

With the rapid development and continuous improvement of complexity of power engineering, the traditional calculation and statistics method cannot meet the requirements of modern power engineering projects on precision and efficiency. To solve this problem, a Revit software technology has been developed. Revit software is widely applied to power engineering as a powerful Building Information Modeling (BIM) tool, and powerful modeling and data management capability provides powerful support for digital model calculation statistics of the power engineering.

However, the mere reliance on the accounting function of the Revit software itself is not yet sufficient to meet the needs of complex power engineering projects. In practical application, the power engineering component model data often have a large number of attributes and association relations, and the attributes and the relations are critical to the accuracy of calculation statistics. Meanwhile, model data of the power engineering system can also change under different running states, and dynamic adjustment and optimization of the model data are needed.

Disclosure of Invention

In order to solve the problems, the application provides a power engineering digital model calculation amount statistical method and system based on Revit software.

In a first aspect, an embodiment of the present application provides a method for calculating a digital model of electric power engineering based on Revit software, which is applied to a big data processing system, and the method includes:

Performing model attribute knowledge mining on first power engineering component model data and second power engineering component model data corresponding to the first power engineering component model data to obtain a first basic model attribute knowledge vector corresponding to the first power engineering component model data and a second basic model attribute knowledge vector corresponding to the second power engineering component model data, wherein the first power engineering component model data and the second power engineering component model data are power engineering component model data obtained by acquiring modeling data of the same power engineering system under different running states;

Performing model collision detection on the first power engineering component model data and the second power engineering component model data respectively to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, wherein the model collision description vectors comprise unit distribution characteristics of at least two collision model data units associated with a current model data unit in a key component cluster interval and contribution coefficients, the contribution coefficients represent modeling attribute disturbance weights of the collision model data units on the current model data unit, and the key component cluster interval is larger than an upstream and downstream data unit interval of the current model data unit;

performing calculation statistics adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector, and performing calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector to obtain first model attribute calculation adjustment knowledge and second model attribute calculation adjustment knowledge;

and generating a model calculation amount statistical result corresponding to the first power engineering component model data according to the first model attribute calculation amount adjustment knowledge and the second model attribute calculation amount adjustment knowledge.

Preferably, the performing model collision detection on the first power engineering component model data and the second power engineering component model data to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data, and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, where the performing step includes:

Respectively carrying out structural attention characteristic interaction on the first power engineering component model data and the second power engineering component model data to obtain first component structure interaction model data and second component structure interaction model data, wherein the first component structure interaction model data and the second component structure interaction model data are transformer substation component model data;

Based on a preset period, extracting the first component structure interaction model data and the second component structure interaction model data to obtain first power engineering component model compression data and second power engineering component model compression data;

Determining a first key component cluster interval according to a model attention index corresponding to the compressed data of the first power engineering component model; performing model collision detection on the first power engineering component model compressed data according to the first key component cluster interval to obtain the first model collision description vector;

Determining a second key component cluster interval according to a model attention index corresponding to the second power engineering component model compression data; and carrying out model collision detection on the second power engineering component model compressed data according to the second key component cluster interval to obtain the second model collision description vector.

Preferably, in the first critical component cluster section, performing model collision detection on the first power engineering component model compressed data to obtain the first model collision description vector, including: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first distribution relation network identification algorithm according to the first key component cluster interval; obtaining contribution coefficients of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first contribution recognition algorithm;

And in the second key component cluster section, performing model collision detection on the second power engineering component model compressed data to obtain the second model collision description vector, including: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the second power engineering component model data through a first distribution relation network identification algorithm according to the second key component cluster interval; and obtaining the contribution coefficient of the conflict model data unit corresponding to each model data unit in the second power engineering component model data through a first contribution identification algorithm.

Preferably, the performing an algorithm adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector, and performing an algorithm adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector, to obtain a first model attribute algorithm adjustment knowledge and a second model attribute algorithm adjustment knowledge, including:

According to the model attention index of the first basic model attribute knowledge vector, carrying out model attention index association on the first model conflict description vector to obtain a first model conflict description vector with the associated completed attention index, wherein the model attention index of the first model conflict description vector with the associated completed attention index is the same as the model attention index of the first basic model attribute knowledge vector;

Performing model attention index association on the second model conflict description vector according to the model attention index of the second basic model attribute knowledge vector to obtain a second model conflict description vector with associated completed attention index, wherein the model attention index of the second model conflict description vector with associated completed attention index is the same as the model attention index of the second basic model attribute knowledge vector;

performing calculation statistics adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector associated with the completed attention index to obtain first model attribute calculation adjustment knowledge;

and carrying out calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector which completes attention index association to obtain second model attribute calculation adjustment knowledge.

Preferably, the generating the model calculation statistic result corresponding to the first power engineering component model data according to the first model attribute calculation adjustment knowledge and the second model attribute calculation adjustment knowledge includes:

Acquiring a first modeling task indicating variable and a first modeling task category label corresponding to the first power engineering component model data and a second modeling task indicating variable corresponding to the second power engineering component model data;

According to the first modeling task indicating variable and the second modeling task indicating variable, performing knowledge feature mapping on the first model attribute calculation adjustment knowledge and the second model attribute calculation adjustment knowledge by using the first modeling task type label to obtain a first BIM model vector corresponding to the first power engineering component model data and a second BIM model vector corresponding to the second power engineering component model data, wherein the BIM model vector is a linear knowledge vector generated by using the first modeling task type label, and represents the power engineering component model features of each model data unit in different expected running states;

Performing resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data, wherein the resource correction vector is an calculated statistical characteristic formed by combining resource correction data in an engineering budget dimension, and each model data unit on the resource correction data represents correction errors of corresponding model data units on the first power engineering component model data and corresponding model data units on the second power engineering component model data in a model resource dimension;

updating the resource correction vector, and outputting contradictory features based on the engineering budget dimension, wherein the contradictory features represent the matching contradictory possibility of components of each model data unit in each expected running state;

And determining the dimension of the model resource corresponding to each model data unit according to the contradictory characteristics, and obtaining the model calculation statistics result corresponding to the model data of the first power engineering component.

Preferably, the performing resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data includes:

Performing model collision detection on the first BIM model vector to obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector, wherein the third model collision description vector comprises BIM model member distribution and contribution coefficients of at least two collision BIM model members associated with the current BIM model member;

Performing calculation statistics adjustment on the first BIM model vector based on the third model conflict description vector to obtain a first BIM calculation adjustment vector;

and carrying out resource correction on the first BIM calculation amount adjustment vector and the second BIM model vector to obtain the resource correction vector corresponding to the first power engineering component model data.

Preferably, the performing model collision detection on the first BIM model vector to obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector includes:

Determining a third key component cluster interval corresponding to the first BIM model vector;

In the third key component cluster interval, BIM model member distribution of conflict BIM model members corresponding to each BIM model member in the first BIM model vector is obtained through a second distribution relation network identification algorithm;

and obtaining the contribution coefficients of the conflict BIM model members corresponding to each BIM model member in the first BIM model vector through a second contribution recognition algorithm.

Preferably, determining the dimension of the model resource corresponding to each model data unit according to the contradictory characteristics to obtain a model calculation statistic result corresponding to the model data of the first power engineering component, where the method includes:

According to the contradiction characteristics, determining the expected operation state with the highest matching contradiction possibility of the components in the expected operation states corresponding to the model data units as a target expected operation state; determining a model resource dimension corresponding to the target expected running state as a target model resource dimension, and obtaining a model calculation statistic result corresponding to the first power engineering component model data; or strengthening the matching contradiction possibility of the components of each expected running state corresponding to each model data unit and the dimension of the model resources according to the contradiction characteristics, and determining the dimension of the target model resources to obtain the model calculation quantity statistical result corresponding to the model data of the first power engineering components.

Preferably, the method further comprises:

Performing model attribute knowledge mining on a first power engineering component model data sample and a second power engineering component model data sample corresponding to the first power engineering component model data sample through multistage knowledge embedding branches in a depth residual model to obtain a first basic model attribute knowledge vector sample corresponding to the first power engineering component model data sample and a second basic model attribute knowledge vector sample corresponding to the second power engineering component model data sample, wherein the first power engineering component model data sample and the second power engineering component model data sample are power engineering component model data obtained by performing modeling data acquisition on the same power engineering system sample under different running states;

respectively performing model collision detection on the first power engineering component model data sample and the second power engineering component model data sample through collision detection branches in the depth residual error model to obtain a first model collision description vector sample corresponding to each model data unit sample in the first power engineering component model data sample and a second model collision description vector sample corresponding to each model data unit sample in the second power engineering component model data sample;

Performing calculation statistics adjustment on the first basic model attribute knowledge vector sample based on the first model conflict description vector sample and performing calculation statistics adjustment on the second basic model attribute knowledge vector sample based on the second model conflict description vector sample through calculation statistics adjustment branches in the depth residual model to obtain a first model attribute calculation adjustment knowledge sample and a second model attribute calculation adjustment knowledge sample;

through a model calculation amount statistical result output branch in the depth residual error model, a knowledge sample is adjusted according to the first model attribute calculation amount and the second model attribute calculation amount, and a model calculation amount statistical result sample corresponding to the first power engineering component model data sample is generated;

Determining a target training error based on a priori model calculation statistics result corresponding to a first power engineering component model data sample and the model calculation statistics result sample;

And debugging the depth residual error model by using the target training error.

Preferably, the determining the target training error based on the prior model operand statistics result corresponding to the first power engineering component model data sample and the model operand statistics result sample includes: determining a first training error through a preset loss function according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the calculation amount statistical result sample of the model; determining a second training error according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the model calculation amount statistical result sample for completing feature migration;

The debugging the depth residual model with the target training error comprises the following steps: and debugging the depth residual error model according to the first training error and the second training error.

Preferably, the performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data corresponding to the first power engineering component model data to obtain a first basic model attribute knowledge vector corresponding to the first power engineering component model data and a second basic model attribute knowledge vector corresponding to the second power engineering component model data includes: performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data through multistage knowledge embedding branches to obtain an x-order first basic model attribute knowledge vector corresponding to the first power engineering component model data and an x-order second basic model attribute knowledge vector corresponding to the second power engineering component model data;

The detecting the model collision of the first power engineering component model data and the second power engineering component model data to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, includes: performing model collision detection on the first power engineering component model data and the second power engineering component model data respectively to obtain an x-order first model collision description vector corresponding to each model data unit in the first power engineering component model data and an x-order second model collision description vector corresponding to each model data unit in the second power engineering component model data;

The performing calculation statistics adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector, and performing calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector, to obtain first model attribute calculation adjustment knowledge and second model attribute calculation adjustment knowledge, including: performing calculation statistics adjustment on a first basic model attribute knowledge vector of the nth order by using a first model conflict description vector of the nth order, and performing calculation statistics adjustment on a second basic model attribute knowledge vector of the nth order by using a second model conflict description vector of the nth order to obtain a first model attribute calculation adjustment knowledge of the nth order and a second model attribute calculation adjustment knowledge of the nth order, wherein u is more than or equal to 1 and less than or equal to x;

the generating a model calculation statistic result corresponding to the first power engineering component model data according to the first model attribute calculation adjustment knowledge and the second model attribute calculation adjustment knowledge comprises the following steps: and generating an x-th model calculation amount statistical result corresponding to the first power engineering component model data based on the x-th order first model attribute calculation amount adjustment knowledge and the x-th order second model attribute calculation amount adjustment knowledge.

Preferably, the method further comprises:

In the process of carrying out knowledge feature mapping on the (u+1) -th order first model attribute calculation amount adjustment knowledge and the (u+1) -th order second model attribute calculation amount adjustment knowledge based on the first modeling task indication variable and the second modeling task indication variable by referring to the first modeling task category label, carrying out calculation amount statistical monitoring by utilizing a (u) -th model calculation amount statistical result to obtain a (u+1) -th order first BIM model vector corresponding to the first power engineering component model data and a (u+1) -th order second BIM model vector corresponding to the second power engineering component model data;

And generating a u+1 model calculation quantity statistical result corresponding to the first power engineering component model data according to the u+1-order first BIM model vector and the u+1-order second BIM model vector.

Preferably, the calculating amount statistical monitoring is performed by using a calculating amount statistical result of the u-th model to obtain a first BIM model vector of the (u+1) -th order corresponding to the first power engineering component model data and a second BIM model vector of the (u+1) -th order corresponding to the second power engineering component model data, including:

Performing calculation improvement on the calculation statistics result of the u-th model based on the model data of the first power engineering component to obtain an improved calculation statistics result of the u-th model;

And carrying out calculation statistics monitoring based on the improved calculation statistics result of the u-th model to obtain the first BIM model vector of the u+1 order and the second BIM model vector of the u+1 order.

Preferably, the calculating amount improvement is performed on the calculation amount statistical result of the u-th model based on the model data of the first power engineering component, so as to obtain an improved calculation amount statistical result of the u-th model, which includes:

performing derivative treatment on the calculation statistics result of the u model, and performing model attribute knowledge mining on the calculation statistics result of the u model after the derivative treatment to obtain the model characteristics of the first power engineering component of the calculation statistics result of the u model;

performing model attribute knowledge mining on the first power engineering component model data to obtain second power engineering component model characteristics and component model redundancy information of the first power engineering component model data;

And carrying out calculation improvement on the calculation result of the u-th model according to the first power engineering component model characteristics, the second power engineering component model characteristics and the component model redundancy information to obtain the improved calculation result of the u-th model.

In a second aspect, embodiments of the present application provide a big data processing system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes computer-executable instructions stored in the memory such that the at least one processor performs the method of the first aspect.

In a third aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when run, implements the method of the first aspect.

The application provides a calculation amount statistical method of a power engineering digital model combining a big data processing system and Revit software. And carrying out deep mining and conflict detection on the model data of the power engineering component by a big data processing system, so as to obtain a model attribute knowledge vector and a model conflict description vector. The vectors not only contain the attribute and the association relation information of the model data, but also reflect the change condition of the model data under different running states.

On the basis, the application further utilizes the big data processing system to carry out calculation statistics adjustment on the model attribute knowledge vector, and obtains the adjusted model attribute calculation knowledge. And finally, generating a calculation statistic result of the power engineering component model data according to the adjusted calculation knowledge. The method not only improves the accuracy and efficiency of calculation statistics, but also provides powerful support for cost control, material purchase and construction plan formulation of power engineering projects.

In summary, the application solves the problem that the traditional calculation method cannot meet the requirements of modern power engineering projects by combining the calculation and statistics technology of the power engineering digital model of the big data processing system and the Revit software. This innovative approach will provide new power and support for the development of power engineering construction.

Drawings

Fig. 1 is a flowchart of a calculation amount statistical method of a digital model of electric power engineering based on Revit software according to an embodiment of the present application.

FIG. 2 is a block diagram of a big data processing system 200 according to an embodiment of the present application.

Detailed Description

In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present application is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and the technical features of the embodiments and the embodiments of the present application may be combined with each other without conflict.

FIG. 1 shows a power engineering digital model calculation statistics method based on Revit software, which is applied to a big data processing system, and comprises the following steps 110-140.

And 110, the big data processing system performs model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data corresponding to the first power engineering component model data to obtain a first basic model attribute knowledge vector corresponding to the first power engineering component model data and a second basic model attribute knowledge vector corresponding to the second power engineering component model data.

The first power engineering component model data and the second power engineering component model data are power engineering component model data obtained by acquiring modeling data of the same power engineering system under different running states.

And 120, respectively performing model collision detection on the first power engineering component model data and the second power engineering component model data by the big data processing system to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data.

The model conflict description vector of the big data processing system comprises unit distribution characteristics of at least two conflict model data units associated with a current model data unit in a key component cluster interval and contribution coefficients, wherein the contribution coefficients represent modeling attribute disturbance weights of the conflict model data unit to the current model data unit, and the key component cluster interval is larger than upstream and downstream data unit intervals of the current model data unit.

And 130, the big data processing system performs calculation statistics adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector, and performs calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector, so as to obtain first model attribute calculation adjustment knowledge and second model attribute calculation adjustment knowledge.

And 140, the big data processing system generates a model calculation amount statistical result corresponding to the first power engineering component model data according to the first model attribute calculation amount adjustment knowledge and the second model attribute calculation amount adjustment knowledge.

In a first aspect, the technical solutions described in steps 110-140 are introduced by a specific application scenario example for implementing calculation statistics in power engineering for big data processing systems.

Modeling and data acquisition of the power engineering system are required in different stages of a power engineering project, such as a design stage, a construction stage and an operation and maintenance stage. These model data reflect the properties and characteristics of the power engineering components under different operating conditions. In this example, two phases are of interest: a design stage and a construction stage.

In the design phase, a designer uses a professional modeling tool to design the power engineering system in detail and generates first power engineering component model data. The data contains detailed information about the geometry, material properties, connection relationships, etc. of the components. Meanwhile, in the construction stage, the actual state of the power engineering component may be different from the design stage due to the variation of the actual construction environment and conditions. Therefore, the constructor carries out modeling and data acquisition again on the actual power engineering system, and second power engineering component model data are obtained.

A big data processing system is introduced into this process to perform the steps of the above-described solution. First, the system performs model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data. By deep learning, natural language processing and other technologies, the system can extract key attribute information in the model data and generate a first basic model attribute knowledge vector and a second basic model attribute knowledge vector respectively. These vectors represent various attribute features of the component model in a digitized form.

Next, the big data processing system performs model collision detection on the two sets of model data. In this process, the system simulates the position and relationship of the components in real space and detects if there is a conflict or overlap. For each model data unit, the system generates a model conflict description vector comprising unit distribution characteristics and contribution coefficients of at least two conflicting model data units associated with the current unit. This information helps to quantify the extent to which conflicts have an impact on the modeled properties.

And then, the big data processing system performs calculation statistics adjustment on the basic model attribute knowledge vector according to the model conflict description vector. By taking into account the disturbance weights of the conflict on the modeled properties, the system is able to more accurately evaluate the actual properties of the electrical engineering components under different operating conditions. The adjusted knowledge vector is referred to as model attribute vector adjustment knowledge.

Finally, the big data processing system combines the first model attribute calculation amount adjustment knowledge and the second model attribute calculation amount adjustment knowledge to generate a model calculation amount statistical result corresponding to the first power engineering component model data. This result is presented in the form of a report or graphic, providing project manager with detailed information about the number, type, attributes, etc. of the power engineering components. The information has important reference value in the aspects of project budget planning, progress control, resource optimization and the like.

Through this application scenario example, the complete flow and actual effect of the big data processing system implementing the calculation statistics in the power engineering can be seen. The system can fully utilize model data and algorithm technology, improves accuracy and efficiency of calculation statistics, and provides powerful support for smooth implementation of electric power engineering projects.

In a second aspect, the terms of the techniques involved in steps 110-140 are explained separately.

First power engineering component model data: this refers to a data set obtained by modeling power engineering components at a certain stage of the power engineering (e.g., a design stage). These data detail the geometry, physical properties, material type, relationships between other components, etc. of the power engineering components. For example, in designing a substation, a designer may use specialized modeling software to create a three-dimensional model of power engineering components such as transformers, switchgear, cables, and the like. The data of these models, including size, location, connection, etc., constitute the first power engineering component model data.

Second power engineering component model data: this generally refers to data obtained by re-modeling the same batch of power engineering components at another stage of the power engineering (e.g., a construction stage or an operation and maintenance stage). These data may differ from the first model data due to actual construction conditions, material changes, or system upgrades, etc. For example, previously designed power engineering components may require adjustment during the construction phase due to changes in field conditions or replacement of materials. The constructor can be modeled again according to the actual situation, and the data of the new models form the data of the second power engineering component model.

Model attribute knowledge mining is conducted: this is a process that utilizes data mining and machine learning techniques to extract and analyze hidden information or patterns in the pattern data. Through model attribute knowledge mining, deeper knowledge and rules about the power engineering components can be obtained. For example, after having a large amount of power engineering component model data, a data mining algorithm may be used to analyze hidden patterns in the data, such as the performance change rules of a certain type of component under a specific environment, or the interaction relationship between different components.

First base model attribute knowledge vector: this is a feature vector representation of the first electrical engineering component model data obtained by model attribute knowledge mining. This vector contains key attribute information of the model data and is the basis for subsequent analysis and processing. For example, after knowledge mining of the first power engineering component model data, a vector may be obtained that includes a plurality of values representing key attribute features extracted from the model data, such as component size, weight, material, etc.

Second base model attribute knowledge vector: similar to the first basic model attribute knowledge vector, this is a feature vector representation obtained after model attribute knowledge mining for the second power engineering component model data. For example, similarly, the second underlying model attribute knowledge vector may also contain a series of values that reflect key attribute features mined in the second model data.

Operating state: in electric power engineering, an operating state refers to a working state of an electric power system or equipment at a certain moment, and includes a normal state, an abnormal state, a shutdown state, and the like. Different operating conditions can have an impact on modeling and analysis of the electrical engineering components. For example, a transformer may be in different operating states, such as a light load state, a full load state, and an overload state, due to load changes during operation. The change of these states affects parameters such as temperature, voltage and current of the transformer, and further affects accuracy and reliability of model data thereof.

An electric power engineering system: the power engineering system refers to an overall system which is composed of a plurality of power engineering components and is used for generating, transmitting, distributing and using electricity. The system comprises a power station, a transformer substation, a power transmission line, a power distribution network, various electric equipment and the like. For example, a complete power engineering system may include a thermal power plant, multiple substations, hundreds of kilometers of transmission line, and a distribution network covering a city. The system needs to ensure stable supply of electric energy and meet the requirements of safety, economy, environmental protection and the like.

And (3) carrying out modeling data acquisition: this is a process of actually measuring and recording data on the power engineering components by various means and methods. The purpose of the modeling data acquisition is to obtain accurate model data for subsequent modeling and analysis work. For example, in modeling data acquisition, a worker may use a laser scanner to three-dimensionally scan an actual component, or use sensors to monitor parameters such as temperature, pressure, etc. of the component in real time. The collected data is consolidated into a standard format and used for subsequent modeling work.

Performing model collision detection: model collision detection is the checking of whether there is spatial overlap or conflict between different models by specific algorithms and tools in a three-dimensional modeling environment. In power engineering, this helps to find potential problems in design or construction in time, avoiding collisions and delays in actual engineering. For example, in designing a complex substation layout, a designer may use a model collision detection tool to check whether models of components such as transformers, switchgear, cable trays, etc. interfere with each other. If collision is found, a designer can adjust the model in time, so that collision in actual construction is avoided.

Model data unit: the model data unit is a basic data element constituting the power engineering component model. Each model data unit contains detailed information about a certain part of the component, such as geometry, position coordinates, material properties, etc. For example, in a transformer model, each bolt, each coil, each insulating sheet, etc. can be regarded as a model data unit. The data of these units are assembled to form a complete transformer model.

First model conflict description vector: the first model collision description vector is a vector representation obtained after model collision detection of the first electric power engineering component model data. It details the conflict relationship and the degree of conflict between the individual data units in the model. For example, after collision detection of a design model of a substation, a vector describing the collision relationship between the transformer and the switchgear may be obtained. This vector may contain information about the location, direction, severity, etc. of the conflict.

Second model conflict description vector: similar to the first model conflict description vector, the second model conflict description vector is a conflict relation description obtained after the collision detection is performed on the second power engineering component model data. For example, in a model at the construction stage, collisions not previously found in the design may occur due to changes in the field environment. The second model conflict description vector captures these newly occurring conflicts and provides detailed information.

Key component cluster interval: a critical component cluster interval refers to the spatial extent occupied by a group of components in power engineering that are closely related to and may have a significant impact on a particular model data unit. For example, in a substation, the installation location of a transformer may affect the layout of the surrounding switchgear, cable trays, etc. The space taken up by these affected components constitutes the critical component cluster section of the transformer.

Current model data unit: the current model data unit refers to a particular model data unit being processed or of interest when performing model collision detection or attribute analysis. For example, in performing crash detection on a model of a switchgear cabinet, a designer may check the model data unit for each cabinet door, each partition, etc. one by one. At this point, the cabinet door or partition being inspected is the current model data unit.

Conflict model data unit: the collision model data unit refers to other model data units that are in spatial collision or overlap with the current model data unit in the model collision detection process. For example, if the current model data unit is part of a cable bridge, it may be found in collision detection that it is in conflict with the pipe above or the equipment below. These pipes or devices that collide with the cable bridge are the collision model data units.

Cell distribution characteristics: the cell distribution characteristics describe the distribution rules of the position, the direction, the density and the like of the model data cells in space. These features are of great significance for analyzing the spatial relationship of the model and the conflict situation. For example, in analyzing the layout of a substation, it may be found that certain areas have a higher distribution density of equipment, while certain areas are relatively open. This non-uniformity of the distribution of the device is an manifestation of the cell distribution characteristics.

Contribution coefficient: the contribution coefficient refers to a numerical index used to quantify the extent to which a conflicting model data unit affects a current model data unit when analyzing model conflicts or attribute disturbances. It reflects the importance or weight of different conflicts to the current model data unit. For example, if a cable tray collides with multiple pipes and equipment, but the position adjustment of a certain pipe has the greatest effect on the current tray, the contribution coefficient of that pipe will be relatively high.

Modeling attribute perturbation weights: modeling attribute perturbation weight refers to a weight value used to measure the extent to which conflicts or other factors affect the attributes (e.g., geometry, physical properties, etc.) of a current model data unit during model collision detection or attribute analysis. It helps to more accurately evaluate the performance and behavior of the model in actual engineering. For example, when analyzing a model of a transformer, it may be found that its spatial conflict with surrounding equipment has some effect on its heat dissipation performance. The magnitude of this effect can be quantified by modeling the attribute perturbation weights.

Upstream and downstream data unit intervals: upstream and downstream data unit intervals refer to the spatial extent occupied by the preceding and following data units in the model that are directly functionally or flowably linked to the current model data unit. These data units function as inputs or outputs in the workflow of the current data unit. For example, in a model of an electrical power system, electrical energy generated by a power plant is transmitted to a substation via a transmission line for transformation, and then transmitted to a customer via a distribution network. In this process, the power station, the transmission line, the substation and the user side form an upstream-downstream relationship with each other. The space they occupy is the upstream and downstream data unit interval.

And (3) carrying out calculation statistics adjustment: in power engineering, big data processing systems are responsible for integrating, analyzing and managing huge amounts of engineering data. When the actual demand, design change or construction condition changes, the system can automatically or semi-automatically carry out calculation statistics adjustment according to the latest data. This includes recalculating, counting, and making necessary adjustments to the number, size, material usage, etc. of engineering projects to ensure engineering accuracy and economy. For example, in an electrical engineering project, big data processing systems receive information from various data sources such as site surveys, design drawings, construction feedback, and the like. When the designer finds that the cable length in the original design is insufficient, they can enter new parameters or adjust the design data in the system. The big data processing system will then automatically recalculate the exact length of cable required and update the material procurement plan and construction schedule accordingly. Such an adjustment process ensures smooth progress of the project and efficient use of resources.

First model attribute calculation adjustment knowledge: in a big data processing system, the first model attribute operand adjustment knowledge refers to rules, algorithms and expertise of the system for calculating and adjusting initial model attribute data. These knowledge are embedded into the algorithms and logic of the system based on the performance parameters of the different materials, the impact of the construction process on the calculation amount, the requirements of the standard specification, etc., to ensure accurate adjustment of the model properties. For example, when a modeling team models a transformer in a big data processing system, the system calculates and adjusts the transformer according to the capacity, weight, heat dissipation performance, and other attribute parameters of the transformer. These parameters and associated knowledge are stored in a database of the system and applied to the construction process of the model by algorithms and logic to ensure the accuracy and reliability of the transformer model.

Second model attribute calculation adjustment knowledge: the second model attribute operand adjustment knowledge in the big data processing system refers to rules, algorithms and expertise that the system relies on when calculating and adjusting attribute data for an existing model at another stage of power engineering or based on updated information. The system can process the change of the actual condition of the site, the newly-appearing problems, the communication coordination with the design or construction units and the like, and ensures the timely adjustment of the model attribute calculation amount and the continuity of the engineering. For example, during construction of a power engineering project, if the model of the cable originally planned for use changes, the big data processing system can automatically or semi-automatically adjust the corresponding attribute calculation in the second model according to the specification parameters of the new cable. The system ensures that the accuracy of the model is not affected by applying an algorithm and a logic, and provides support for smooth progress of the project.

Model calculation statistics result: in a big data processing system, the model calculation statistics result is a data result obtained by calculating and counting the number, size, weight and other attributes of various components and materials. The system can integrate various data sources, perform automatic data analysis and processing, generate accurate and comprehensive statistical results, and provide important basis for engineering cost budget, material purchase, construction scheduling and the like. For example, in an electrical engineering project, big data processing systems can automatically model all electrical equipment and materials and make a quantitative statistic of the detailed properties of each component. The statistical result generated by the system comprises key data such as the total length of various cables, the total weight of the transformer, the number of switch cabinets and the like. These data are used to build bill of materials, schedule construction progress, and base cost estimates. Through deep analysis of the calculation statistics, the system can also find potential problems and defects, and provides basis for further optimization of projects.

In the third aspect, the first power engineering component model data and the second power engineering component model data are subjected to deep analysis and processing by utilizing the big data processing system, so that effective mining of the power engineering component model attribute knowledge and accurate adjustment of calculation statistics are realized, and the accuracy and efficiency of power engineering modeling are remarkably improved.

Firstly, through the model attribute knowledge mining in step 110, the application can extract a first basic model attribute knowledge vector and a second basic model attribute knowledge vector from the power engineering component model data obtained by collecting modeling data of the same power engineering system under different running states. The vectors contain rich model attribute information and provide a solid foundation for subsequent calculation amount statistics adjustment.

Next, the model collision detection in step 120 can accurately identify a collision between each model data unit in the first power engineering component model data and the second power engineering component model data, and generate a corresponding first model collision description vector and second model collision description vector. These vectors not only contain the distribution characteristics of the conflict model data units, but also quantify the modeling attribute disturbance weights of the conflict model data units to the current model data units through the contribution coefficients. This comprehensive conflict description provides an important reference for subsequent statistical adjustments of the metrics.

Then, in step 130, the present application performs a calculation statistic adjustment on the first basic model attribute knowledge vector and the second basic model attribute knowledge vector by using the first model conflict description vector and the second model conflict description vector, respectively. The adjustment mode can fully consider conflict and disturbance among model data units, and ensures that the calculated quantity of the adjusted model attribute is more accurate and reliable. Through the step, the first model attribute operand adjustment knowledge and the second model attribute operand adjustment knowledge are obtained, and key support is provided for subsequent model operand statistical result generation.

Finally, in step 140, the present application generates a model calculation statistic corresponding to the model data of the first power engineering component according to the first model attribute calculation adjustment knowledge and the second model attribute calculation adjustment knowledge. The result not only accurately reflects the actual condition of the power engineering component, but also provides important basis for subsequent cost budget, material purchase, construction scheduling and the like. Meanwhile, through deep analysis of the calculation statistics result, the application can also find potential problems and defects, and provides basis for further optimization of projects.

In summary, the application realizes the deep mining of the power engineering component model attribute knowledge and the accurate adjustment of the calculation statistics through the strong analysis capability of the big data processing system, and remarkably improves the accuracy and efficiency of the power engineering modeling. This has important significance in promoting the development of power engineering construction.

In some possible embodiments, the performing model collision detection on the first power engineering component model data and the second power engineering component model data to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data, and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, where the performing step includes: respectively carrying out structural attention characteristic interaction on the first power engineering component model data and the second power engineering component model data to obtain first component structure interaction model data and second component structure interaction model data, wherein the first component structure interaction model data and the second component structure interaction model data are transformer substation component model data; based on a preset period, extracting the first component structure interaction model data and the second component structure interaction model data to obtain first power engineering component model compression data and second power engineering component model compression data; determining a first key component cluster interval according to a model attention index corresponding to the compressed data of the first power engineering component model; performing model collision detection on the first power engineering component model compressed data according to the first key component cluster interval to obtain the first model collision description vector; determining a second key component cluster interval according to a model attention index corresponding to the second power engineering component model compression data; and carrying out model collision detection on the second power engineering component model compressed data according to the second key component cluster interval to obtain the second model collision description vector.

In some possible embodiments, the process of the system for model collision detection of the first and second electrical engineering component model data may be performed in accordance with the following detailed steps.

First, the system performs structural attention feature interaction on the first and second power engineering component model data, respectively. The purpose of this step is to extract the structural information in the model data and to identify the interaction relationship between the individual components. Through the structural attention feature interaction, the system is able to obtain first component structural interaction model data and second component structural interaction model data. The data are specially aimed at a component model of the transformer substation, and contain rich structural information and interaction relations.

Next, the system performs data extraction on the first component structure interaction model data and the second component structure interaction model data based on a preset period. The preset period may be set according to actual needs, such as daily, weekly, monthly, etc. The purpose of data extraction is to reduce the dimensionality and complexity of the data while retaining critical information. By data extraction, the system can obtain first and second power engineering component model compression data. These compressed data both reduce the overhead of storage and processing, and retain sufficient information for subsequent model collision detection.

Then, the system determines a first critical component cluster interval according to a model attention index corresponding to the compressed data of the first power engineering component model. Model attention indicators are metrics used to measure the importance and impact of various components in a model. By calculating and analyzing model attention indicators, the system is able to identify key component cluster intervals in the first power engineering component model, i.e. those component sets that have an important impact on the model performance and stability.

And then, the system performs model collision detection on the first power engineering component model compressed data according to the first key component cluster interval. In this step, the system checks whether there is a conflict or overlap between components within the critical component cluster interval. If a conflict exists, the system records information such as the position, type, severity, etc. of the conflict and generates a first model conflict description vector. This vector contains important information such as the cell distribution characteristics and contribution coefficients of the conflicting members for subsequent statistical adjustment of the calculation amount.

Similarly, the system determines a second key component cluster interval according to the model attention index corresponding to the second power engineering component model compressed data, and performs model collision detection on the second power engineering component model compressed data. Through this process, the system can obtain a second model conflict description vector, which also contains important information such as the unit distribution characteristics and contribution coefficients of the conflict components.

Finally, the system performs calculation statistics adjustment according to the first model conflict description vector and the second model conflict description vector, and generates accurate model calculation statistics results. These results can provide powerful data support for cost control, material procurement and construction planning for electrical engineering projects. Meanwhile, through deep analysis of calculation statistics results, the system can also find potential design problems and optimization space, and powerful guarantee is provided for continuous improvement of power engineering projects.

In the next step, in the first critical component cluster section, performing model collision detection on the first power engineering component model compressed data to obtain the first model collision description vector, where the method includes: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first distribution relation network identification algorithm according to the first key component cluster interval; obtaining contribution coefficients of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first contribution recognition algorithm; and in the second key component cluster section, performing model collision detection on the second power engineering component model compressed data to obtain the second model collision description vector, including: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the second power engineering component model data through a first distribution relation network identification algorithm according to the second key component cluster interval; and obtaining the contribution coefficient of the conflict model data unit corresponding to each model data unit in the second power engineering component model data through a first contribution identification algorithm.

In the next step, the process of the system performing model collision detection on the first and second power engineering component model compressed data to obtain model collision description vectors may be performed according to the following detailed steps.

First, the system processes the first power engineering component model compressed data according to the first key component cluster section through a first distribution relation network identification algorithm. The purpose of this algorithm is to identify conflicting relationships between individual data units in the model, particularly those at least two model data units that have a conflict with the current model data unit. Through the operation of the algorithm, the system can obtain the unit distribution characteristics of the conflict model data units in the key component cluster interval. These features describe important information such as the location, number, and interrelationship of the conflict model data units.

The system then utilizes a first contribution recognition algorithm to further analyze the first power engineering component model compression data. The purpose of this algorithm is to calculate the disturbance weights, i.e. the contribution coefficients, of the modeling properties of the conflicting model data units to the current model data unit. The contribution coefficient is a quantization index that reflects the extent to which the conflicting model data units affect the current model data unit. Through the operation of the algorithm, the system can obtain the contribution coefficient of the conflict model data unit corresponding to each model data unit.

The system then integrates the cell distribution characteristics and the contribution coefficients to form a first model conflict description vector. This vector is a multi-dimensional data structure that contains conflicting information for all model data units in the first power engineering component model compression data.

Likewise, the system processes the second power engineering component model compressed data according to the second key component cluster interval through the first distribution relation network identification algorithm and the second contribution identification algorithm. By running the two algorithms, the system can obtain a second model conflict description vector which contains conflict information of all model data units in the second power engineering component model compressed data.

Finally, the system performs subsequent statistical adjustments to the calculation based on the first model conflict description vector and the second model conflict description vector. These vectors provide rich conflict information that helps the system more accurately identify and handle conflict problems in the model, thereby improving the accuracy and efficiency of the calculation statistics.

Under other possible design ideas, the performing an algorithm adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector, and performing an algorithm adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector to obtain a first model attribute algorithm adjustment knowledge and a second model attribute algorithm adjustment knowledge, including: according to the model attention index of the first basic model attribute knowledge vector, carrying out model attention index association on the first model conflict description vector to obtain a first model conflict description vector with the associated completed attention index, wherein the model attention index of the first model conflict description vector with the associated completed attention index is the same as the model attention index of the first basic model attribute knowledge vector; performing model attention index association on the second model conflict description vector according to the model attention index of the second basic model attribute knowledge vector to obtain a second model conflict description vector with associated completed attention index, wherein the model attention index of the second model conflict description vector with associated completed attention index is the same as the model attention index of the second basic model attribute knowledge vector; performing calculation statistics adjustment on the first basic model attribute knowledge vector based on the first model conflict description vector associated with the completed attention index to obtain first model attribute calculation adjustment knowledge; and carrying out calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector which completes attention index association to obtain second model attribute calculation adjustment knowledge.

In other possible design considerations, the process of performing the statistical computation adjustment on the first basic model attribute knowledge vector and the second basic model attribute knowledge vector by the system may be performed according to the following detailed steps.

Firstly, the system performs model attention index association on the first model conflict description vector according to the model attention index of the first basic model attribute knowledge vector. Model attention index is referred to herein as a metric that measures the importance and impact of various parts of the model. By correlating the model attention index of the first model conflict description vector with the model attention index of the first underlying model attribute knowledge vector, the system is able to ensure consistency of both in the attention index. In this way, the first model conflict description vector can accurately reflect the key information and importance in the first basic model attribute knowledge vector in the process of calculation amount statistics adjustment. After this step, the system obtains a first model conflict description vector that completes the attention index association.

Then, the system uses the same method to correlate the model attention index of the second model conflict description vector according to the model attention index of the second basic model attribute knowledge vector. In this way, the system can obtain a second model conflict description vector that completes the attention index association. Likewise, the model attention index of the vector is the same as the model attention index of the second basic model attribute knowledge vector, and the consistency of the key information and the importance of the key information is ensured.

The system then performs a statistical computation adjustment on the first base model attribute knowledge vector based on the first model conflict description vector completing the attention index association. In this process, the system adjusts the respective attribute values in the first base model attribute knowledge vector based on the conflict information and contribution coefficients in the first model conflict description vector. These adjustments reflect the impact of conflicts in the model on the attribute knowledge, making the calculation statistics more accurate and reliable. Through this step, the system can obtain the first model attribute calculation adjustment knowledge.

Finally, the system uses the same method to perform calculation statistics adjustment on the second basic model attribute knowledge vector based on the second model conflict description vector for completing the attention index association. Thus, the system can obtain knowledge of the second model attribute scalar adjustment. These adjusted knowledge of the attributes provides a more accurate and reliable data basis for subsequent model calculation statistics.

In summary, through the series of steps, the system can fully utilize the model conflict description vector and the model attention index to adjust the basic model attribute knowledge vector, thereby obtaining more accurate and reliable model attribute calculation adjustment knowledge. The knowledge provides powerful data support for cost control, material purchase and construction planning of power engineering projects.

In some preferred design ideas, the generating the model operand statistics corresponding to the first power engineering component model data according to the first model attribute operand adjustment knowledge and the second model attribute operand adjustment knowledge includes: acquiring a first modeling task indicating variable and a first modeling task category label corresponding to the first power engineering component model data and a second modeling task indicating variable corresponding to the second power engineering component model data; according to the first modeling task indicating variable and the second modeling task indicating variable, performing knowledge feature mapping on the first model attribute calculation adjustment knowledge and the second model attribute calculation adjustment knowledge by using the first modeling task type label to obtain a first BIM model vector corresponding to the first power engineering component model data and a second BIM model vector corresponding to the second power engineering component model data, wherein the BIM model vector is a linear knowledge vector generated by using the first modeling task type label, and represents the power engineering component model features of each model data unit in different expected running states; performing resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data, wherein the resource correction vector is an calculated statistical characteristic formed by combining resource correction data in an engineering budget dimension, and each model data unit on the resource correction data represents correction errors of corresponding model data units on the first power engineering component model data and corresponding model data units on the second power engineering component model data in a model resource dimension; updating the resource correction vector, and outputting contradictory features based on the engineering budget dimension, wherein the contradictory features represent the matching contradictory possibility of components of each model data unit in each expected running state; and determining the dimension of the model resource corresponding to each model data unit according to the contradictory characteristics, and obtaining the model calculation statistics result corresponding to the model data of the first power engineering component.

In some preferred design considerations, the process of generating the model calculation statistics corresponding to the model data of the first power engineering component by the system may be performed according to the following detailed steps.

First, the system obtains a first modeling task indication variable and a first modeling task category label corresponding to the first power engineering component model data, and a second modeling task indication variable corresponding to the second power engineering component model data. Modeling task indication variables are parameters that identify modeling task types and requirements, and modeling task category labels are information that categorize and label modeling tasks. These variables and tags provide important context information for the subsequent processing of model attribute computation scaling knowledge.

Then, the system performs knowledge feature mapping on the first model attribute operand adjustment knowledge and the second model attribute operand adjustment knowledge by using the first modeling task class labels according to the first modeling task indication variable and the second modeling task indication variable. Knowledge feature mapping is a process of converting attribute vector adjustment knowledge into a specific form vector, here specifically a BIM (Building Information Modeling, building information model) model vector. Through mapping, the system can obtain a first BIM model vector corresponding to the first power engineering component model data and a second BIM model vector corresponding to the second power engineering component model data. These BIM model vectors are linear knowledge vectors that characterize the model features of the power engineering components of each model data unit at different desired operating states.

The system then performs a resource correction on the first BIM model vector and the second BIM model vector. Resource correction is a process of adjusting and optimizing vectors in order to eliminate errors in the dimension of the resource for model data. And the system can obtain the resource correction vector corresponding to the first power engineering component model data through the resource correction. The vector is an algorithm statistical feature formed by combining the resource correction data in the engineering budget dimension, wherein each model data unit represents a correction error of a corresponding model data unit on the first power engineering component model data and a corresponding model data unit on the second power engineering component model data in the model resource dimension.

The system then updates the resource correction vector and outputs contradictory features based on the engineering budget dimension. The contradictory characteristics are an indicator of the likelihood of a component match contradiction for each model data unit at each desired operating state. By updating the resource correction vector and outputting the contradictory features, the system can more accurately identify and address contradictory problems in the model.

And finally, the system determines the dimension of the model resource corresponding to each model data unit according to the contradictory characteristics, and obtains the model calculation statistics result corresponding to the model data of the first power engineering component. The process is a comprehensive analysis and decision-making process, and the system determines the optimal model resource dimension allocation scheme according to contradictory features and other relevant information and generates corresponding calculation statistics. These results can provide powerful data support for cost control, material procurement and construction planning for electrical engineering projects.

In summary, through these steps, the system can fully utilize technical means such as model attribute calculation amount adjustment knowledge, modeling task indicating variables, modeling task category labels, resource correction and the like to generate accurate and reliable model calculation amount statistical results. The results not only reflect the actual requirements and performance characteristics of each part in the model, but also provide important reference for the implementation of the subsequent power engineering project.

In the next step, the performing resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data includes: performing model collision detection on the first BIM model vector to obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector, wherein the third model collision description vector comprises BIM model member distribution and contribution coefficients of at least two collision BIM model members associated with the current BIM model member; performing calculation statistics adjustment on the first BIM model vector based on the third model conflict description vector to obtain a first BIM calculation adjustment vector; and carrying out resource correction on the first BIM calculation amount adjustment vector and the second BIM model vector to obtain the resource correction vector corresponding to the first power engineering component model data.

In the next step, the system performs resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data, which may be performed according to the following detailed steps.

First, the system performs model collision detection on the first BIM model vector. The purpose of this step is to identify conflicting relationships between the individual BIM model members in the first BIM model vector. Model collision detection is a technique that algorithmically compares the spatial position and properties of various components in a model to determine if a collision exists. In this process, the system may be particularly concerned with a minimum of two conflicting BIM model members associated with the current BIM model member. These conflicting model members refer to other BIM model members that are in conflict with the current BIM model member in terms of spatial location, size, shape, or attribute.

Through model collision detection, the system can obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector. The third model conflict description vector is a data structure containing a BIM model member distribution of at least two conflicting BIM model members associated with the current BIM model member and contribution coefficients. BIM model member distribution describes the positions, numbers and interrelationships of conflicting BIM model members in the vector, while contribution coefficients quantify the extent to which conflicting BIM model members affect the current BIM model member.

Next, the system performs a statistical adjustment on the first BIM model vector based on the third model conflict description vector. This adjustment process aims at adjusting the attribute values of the individual members in the BIM model vector based on the conflict information and the contribution coefficients to reflect the impact of conflicts in the model on the attribute knowledge. Through the calculation amount statistics adjustment, the system can obtain a new BIM vector, which is called a first BIM calculation amount adjustment vector. This vector contains the attribute values of the conflict-adjusted and optimized BIM model members.

The system then performs a resource correction on the first BIM vector adjustment and the second BIM model vector. The resource correction is a comprehensive adjustment process, which aims to eliminate errors of two BIM model vectors in the dimension of the resource and obtain a uniform resource correction vector. In this process, the system compares the attribute values of the corresponding BIM model members in the first BIM vector and the second BIM vector, and calculates their correction errors in the resource dimension. The correction error reflects the difference in resource usage, allocation, or demand of the corresponding BIM model member in the two vectors.

And finally, the system corrects the first BIM calculation amount adjustment vector according to the calculated correction error to obtain a resource correction vector corresponding to the first power engineering component model data. The resource correction vector is a calculated statistical feature combined in the engineering budget dimension, wherein each model data unit represents the correction result of the corresponding BIM model member in the first power engineering component model data and the corresponding BIM model member in the second power engineering component model data in the resource dimension. The result not only reflects the actual resource requirements and performance characteristics of each part in the model, but also provides important data support for the subsequent implementation of the electric power engineering project.

In summary, by these detailed steps and explanations, it can be understood more clearly how the system performs resource correction on the first BIM model vector and the second BIM model vector, and obtains the resource correction vector corresponding to the first power engineering component model data. The process fully utilizes technical means such as model collision detection, calculation statistics adjustment, resource correction and the like to ensure the accuracy and consistency of the model.

In a further step, the performing model collision detection on the first BIM model vector to obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector, including: determining a third key component cluster interval corresponding to the first BIM model vector; in the third key component cluster interval, BIM model member distribution of conflict BIM model members corresponding to each BIM model member in the first BIM model vector is obtained through a second distribution relation network identification algorithm; and obtaining the contribution coefficients of the conflict BIM model members corresponding to each BIM model member in the first BIM model vector through a second contribution recognition algorithm.

In a further step, the process of performing model collision detection on the first BIM model vector by the system to obtain a third model collision description vector corresponding to each BIM model member may be performed according to the following detailed steps.

First, the system determines a third key component cluster interval corresponding to the first BIM model vector. The critical component cluster interval refers to a spatial region containing important components or critical nodes in the BIM model. These critical components or nodes are often parts of the model that are subject to conflict or require special attention. The purpose of determining the third critical component cluster section is to reduce the range of collision detection and improve the detection efficiency. The system can determine which spatial regions belong to the third key component cluster section according to the structural characteristics of the BIM model, design requirements or historical experience and other information.

Next, in a third key component cluster interval, the system obtains BIM model member distribution of conflict BIM model members corresponding to each BIM model member in the first BIM model vector through a second distribution relation network identification algorithm. The second distribution network recognition algorithm is an algorithm for recognizing the spatial distribution relationship between the individual components in the model. By the algorithm, the system can analyze which BIM model members have conflict or overlap conditions on the space positions and determine the distribution relation between the BIM model members. These distribution relationships may include information about relative position, distance, angle, etc.

And then, the system obtains the contribution coefficients of the conflict BIM model members corresponding to each BIM model member in the first BIM model vector through a second contribution recognition algorithm. The second contribution recognition algorithm is an algorithm for quantifying the degree of contribution of each component in the model to the collision. By means of the algorithm, the system can evaluate the contribution of each BIM model member in the conflict, namely the influence degree of the BIM model member on the conflict. The contribution coefficient is a value or scale that is used to represent the relative importance or impact of each BIM model member in a conflict.

Finally, the system integrates the BIM model membership distribution and contribution coefficients into a third model conflict description vector. This vector is a data structure for storing and representing the distribution relationship and contribution coefficient information of at least two conflicting BIM model members associated with the current BIM model member. By integrating the information, the system can obtain a comprehensive and detailed conflict description, and provides accurate data support for subsequent resource correction and calculation statistics.

From the above, it can be more clearly understood how the system performs model collision detection on the first BIM model vector, and obtains the third model collision description vector corresponding to each BIM model member. The process fully utilizes the technical means of key component cluster interval determination, a second distribution relation network recognition algorithm, a second contribution recognition algorithm and the like to improve the accuracy and the efficiency of collision detection.

In the next step, determining the dimension of the model resource corresponding to each model data unit according to the contradictory characteristics, and obtaining the model calculation statistics corresponding to the model data of the first power engineering component, where the step includes: according to the contradiction characteristics, determining the expected operation state with the highest matching contradiction possibility of the components in the expected operation states corresponding to the model data units as a target expected operation state; determining a model resource dimension corresponding to the target expected running state as a target model resource dimension, and obtaining a model calculation statistic result corresponding to the first power engineering component model data; or strengthening the matching contradiction possibility of the components of each expected running state corresponding to each model data unit and the dimension of the model resources according to the contradiction characteristics, and determining the dimension of the target model resources to obtain the model calculation quantity statistical result corresponding to the model data of the first power engineering components.

In the next step, the system determines the model resource dimension corresponding to each model data unit according to the contradictory characteristics, and obtains the model calculation statistics corresponding to the model data of the first power engineering component according to the model resource dimension. This process can be performed in two ways.

First mode

The system firstly evaluates each expected running state corresponding to each model data unit according to the contradictory characteristics. Contradictory features herein may include dimensional mismatch between components, positional conflicts, functional overlap, and the like. The objective of the evaluation is to find the expected operating state with the highest probability of contradiction between component matches.

In the evaluation process, the system may consider various factors such as geometric properties, physical properties, functional requirements, etc. of the components, as well as their behavior in different desired operating conditions. By means of comprehensive analysis and comparison, the system can determine which expected operating states of each model data unit face a large component matching contradiction.

Once the desired operating state is found for which the likelihood of component matching conflicts is greatest, the system determines it as the target desired operating state. This means that in these states there is a more pronounced conflict or inconsistency between the components in the model data unit.

Next, the system determines a model resource dimension corresponding to the target expected operating state as a target model resource dimension. Model resource dimensions may include material usage, equipment quantity, human demand, etc., which form the basis of model calculation statistics.

And finally, carrying out calculation statistics according to the dimension of the target model resource by the system to obtain a model calculation statistics result corresponding to the model data of the first power engineering component. This result reflects the number and distribution of resources required by the model data unit under different desired operating conditions.

Second mode

The system also carries out strengthening treatment on the matching contradiction possibility of the components of each expected running state corresponding to each model data unit and the dimension of the model resource according to the contradiction characteristics. The purpose of the reinforcement is to highlight those factors that have a significant impact on component matching conflicts and resource requirements.

During the reinforcement process, the system may employ methods such as weight adjustment, sensitivity analysis, etc., to increase the impact of desired operating conditions that may manifest themselves in component matching conflicts and resource requirements. Thus, the subsequent calculation amount statistics can be more accurate and targeted.

After the reinforcement treatment, the system can determine the dimension of the target model resource. Unlike the first approach, the target model resource dimension is derived here taking into account the component matching contradictory probabilities and resource requirements for each desired operating state.

And finally, carrying out calculation statistics according to the dimension of the target model resource by the system, and obtaining a model calculation statistics result corresponding to the model data of the first power engineering component. This result reflects the resource requirements of the model data unit in different desired operating states more comprehensively and finely.

In other exemplary embodiments, the method further comprises steps 210-260.

Step 210, performing model attribute knowledge mining on a first power engineering component model data sample and a second power engineering component model data sample corresponding to the first power engineering component model data sample through multistage knowledge embedding branches in a depth residual model to obtain a first basic model attribute knowledge vector sample corresponding to the first power engineering component model data sample and a second basic model attribute knowledge vector sample corresponding to the second power engineering component model data sample, wherein the first power engineering component model data sample and the second power engineering component model data sample are power engineering component model data obtained by performing modeling data acquisition on the same power engineering system sample under different running states.

And 220, respectively performing model collision detection on the first power engineering component model data sample and the second power engineering component model data sample through collision detection branches in the depth residual error model to obtain a first model collision description vector sample corresponding to each model data unit sample in the first power engineering component model data sample and a second model collision description vector sample corresponding to each model data unit sample in the second power engineering component model data sample.

And 230, performing calculation statistics adjustment on the first basic model attribute knowledge vector sample based on the first model conflict description vector sample and the second basic model attribute knowledge vector sample based on the second model conflict description vector sample through a calculation statistics adjustment branch in the depth residual model to obtain a first model attribute calculation adjustment knowledge sample and a second model attribute calculation adjustment knowledge sample.

And 240, generating a model calculation amount statistical result sample corresponding to the first power engineering component model data sample according to the first model attribute calculation amount adjustment knowledge sample and the second model attribute calculation amount adjustment knowledge sample through a model calculation amount statistical result output branch in the depth residual error model.

And 250, determining a target training error based on the prior model calculation statistics corresponding to the first power engineering component model data sample and the model calculation statistics sample.

Step 260, debugging the depth residual model with the target training error.

In other exemplary embodiments, the method includes steps 210 through 260, which are illustrated in detail below.

In this step, the system uses multi-level knowledge embedding branches in the depth residual model to process power engineering component model data samples in two different states. Specifically, the system performs model attribute knowledge mining on a first power engineering component model data sample and a second power engineering component model data sample corresponding to the first power engineering component model data sample, wherein the two data samples are obtained by modeling and data acquisition of the same power engineering system under different running states. Through the process, the system can obtain a first basic model attribute knowledge vector sample corresponding to the first power engineering component model data sample and a second basic model attribute knowledge vector sample corresponding to the second power engineering component model data sample. The basic model attribute knowledge vector examples contain basic attribute and characteristic information of the model in each state.

Next, the system performs model collision detection on the first and second power engineering component model data samples, respectively, using collision detection branches in the depth residual model. This process aims to identify possible collision or collision conditions inside the model. Through the step, the system can obtain a first model conflict description vector sample corresponding to each model data unit sample in the first power engineering component model data sample and a second model conflict description vector sample corresponding to each model data unit sample in the second power engineering component model data sample. These conflict description vector samples detail the conflict situations and the conflict levels of the various parts in the model.

After the conflict description vector samples are obtained, the system carries out calculation statistics adjustment on the basic model attribute knowledge vector samples according to the conflict description vector samples through calculation statistics adjustment branches in the depth residual model. Specifically, the system adjusts the first base model attribute knowledge vector sample based on the first model conflict description vector sample and adjusts the second base model attribute knowledge vector sample based on the second model conflict description vector sample. Through the process, the system can obtain the first model attribute operand adjustment knowledge sample and the second model attribute operand adjustment knowledge sample after conflict adjustment. These adjusted knowledge samples more accurately reflect the properties and characteristics of the model in actual conditions.

And then, the system adjusts the knowledge sample according to the adjusted model attribute calculation amount through a model calculation amount statistical result output branch in the depth residual error model to generate a model calculation amount statistical result sample corresponding to the first power engineering component model data sample. This statistical result sample is a comprehensive output that contains detailed statistical information about the model in various aspects, such as material usage, equipment count, human demand, etc. This information has important reference value for subsequent engineering budgets and implementations.

On this basis, the system also determines the target training error based on the a priori model operand statistics (which are previously known statistics) corresponding to the first power engineering component model data samples and the model operand statistics samples just generated. The target training error reflects the degree of difference between the model predicted result and the actual result, and is one of the important indexes for evaluating the model performance.

Finally, the system will debug the depth residual model with the determined target training error. The purpose of the debugging is to optimize the parameters and structure of the model so that it can more accurately predict and process similar power engineering component model data samples. Through continuous iteration and optimization, the system can gradually improve the performance and accuracy of the depth residual error model.

In the next step, the determining the target training error in step 250 based on the a priori model calculation statistics corresponding to the first power engineering component model data sample and the model calculation statistics sample includes: determining a first training error through a preset loss function according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the calculation amount statistical result sample of the model; determining a second training error according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the model calculation amount statistical result sample for completing feature migration; the debugging the depth residual model with the target training error comprises the following steps: and debugging the depth residual error model according to the first training error and the second training error.

In the next step, the system will perform step 250 of determining a target training error based on the a priori model volume statistics corresponding to the first power engineering component model data samples and the model volume statistics samples. The following is a detailed illustration.

Firstly, the system needs to determine a first training error according to a calculation amount statistics view corresponding to a calculation amount statistics result of the prior model and a calculation amount statistics view corresponding to a calculation amount statistics result sample of the model. In this process, the accounting perspective may be understood as a perspective of accounting for different interpretations or emphasis on model accounting results, such as material usage, equipment count, human demand, and the like. The system calculates a first training error using a predetermined loss function by comparing the difference between these two statistical views. The loss function is a mathematical function that measures the difference between the predicted result and the actual result of the model, with smaller values indicating that the predicted result of the model is closer to the actual result.

Secondly, the system also needs to determine a second training error according to the calculation statistics view corresponding to the calculation statistics result of the prior model and the calculation statistics view corresponding to the model calculation statistics result sample for completing feature migration. Feature migration refers to the process of applying knowledge or features learned from one domain or task to another related domain or task. The model calculation statistics result sample for completing feature migration refers to a model calculation statistics result integrating new features or knowledge on the basis of keeping original features. The system also needs to compare the difference between these two statistical perspectives to calculate the second training error.

Finally, after determining the first training error and the second training error, the system needs to debug the depth residual model according to the two training errors. The debugging aims at optimizing parameters and structures of the model so as to reduce training errors and improve prediction accuracy and generalization capability of the model. Specifically, the system can adjust parameters such as weight, bias and the like of the model according to the magnitude and the direction of the training error, or adjust settings such as network structure, layer number and the like of the model so as to achieve a better prediction effect.

It should be noted that the terms of the calculation statistics perspective, the loss function, the feature migration, and the like in the above steps are all common terms in the machine learning field. The view of calculation statistics can be understood as different interpretation or emphasis points of the model output result; the loss function is a mathematical function for measuring the difference between the model predicted result and the actual result; feature migration is the process of applying knowledge or features learned from one domain or task to another related domain or task. These terms are widely used in many application scenarios of machine learning.

In summary, through the above steps and explanation, it can be more clearly understood how the system determines the target training error based on the a priori model calculation statistics result and the model calculation statistics result sample corresponding to the first power engineering component model data sample, and debugs the depth residual model accordingly. The process fully utilizes related technologies and methods in the machine learning field to improve the prediction accuracy and generalization capability of the model.

In some alternative embodiments, the performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data corresponding to the first power engineering component model data to obtain a first basic model attribute knowledge vector corresponding to the first power engineering component model data and a second basic model attribute knowledge vector corresponding to the second power engineering component model data includes: and performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data through multistage knowledge embedding branches to obtain an x-order first basic model attribute knowledge vector corresponding to the first power engineering component model data and an x-order second basic model attribute knowledge vector corresponding to the second power engineering component model data.

And performing model collision detection on the first power engineering component model data and the second power engineering component model data respectively to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, where the method includes: and respectively carrying out model collision detection on the first power engineering component model data and the second power engineering component model data to obtain an x-order first model collision description vector corresponding to each model data unit in the first power engineering component model data and an x-order second model collision description vector corresponding to each model data unit in the second power engineering component model data.

And the calculating amount statistics adjustment is performed on the first basic model attribute knowledge vector based on the first model conflict description vector, and the calculating amount statistics adjustment is performed on the second basic model attribute knowledge vector based on the second model conflict description vector, so as to obtain first model attribute calculating amount adjustment knowledge and second model attribute calculating amount adjustment knowledge, including: and performing calculation statistics adjustment on the first basic model attribute knowledge vector of the nth order by using the first model conflict description vector of the nth order, and performing calculation statistics adjustment on the second basic model attribute knowledge vector of the nth order by using the second model conflict description vector of the nth order to obtain the first model attribute calculation adjustment knowledge of the nth order and the second model attribute calculation adjustment knowledge of the nth order, wherein u is more than or equal to 1 and less than or equal to x.

And generating a model calculation amount statistical result corresponding to the first power engineering component model data according to the first model attribute calculation amount adjustment knowledge and the second model attribute calculation amount adjustment knowledge, including: and generating an x-th model calculation amount statistical result corresponding to the first power engineering component model data based on the x-th order first model attribute calculation amount adjustment knowledge and the x-th order second model attribute calculation amount adjustment knowledge.

In some alternative embodiments, the system performs a more detailed partitioning and processing of the first electrical engineering component model data and the second electrical engineering component model data corresponding thereto. The following is a detailed illustration.

First, the system performs model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data through the multi-level knowledge embedding branches. In this process, the system may go deep into various levels and attributes of the model, extracting key information about model features, performance, etc. Through the step, the system can obtain an x-order first basic model attribute knowledge vector corresponding to the first power engineering component model data and an x-order second basic model attribute knowledge vector corresponding to the second power engineering component model data. "order x" herein is understood to mean the level or depth of model properties, which reflects the degree of refinement and complexity of knowledge of model properties.

Next, the system performs model collision detection on the first power engineering component model data and the second power engineering component model data, respectively. In this process, the system simulates the collision and collision situations which may occur in the actual operation of the model, and analyzes and records the situations. Through the step, the system can obtain the x-order first model conflict description vector corresponding to each model data unit in the first power engineering component model data and the x-order second model conflict description vector corresponding to each model data unit in the second power engineering component model data. The conflict description vectors record the conflict condition and the conflict degree of each part in the model in detail, and provide important basis for subsequent calculation statistics adjustment.

And then, the system performs calculation statistics adjustment on the first basic model attribute knowledge vector of the u th order by using the first model conflict description vector of the u th order, and performs calculation statistics adjustment on the second basic model attribute knowledge vector of the u th order by using the second model conflict description vector of the u th order. The term "calculation statistics adjustment" refers to correcting and adjusting the basic model attribute knowledge vector according to the information of the conflict description vector, so as to make the basic model attribute knowledge vector more in line with the actual situation and the requirements. Through the step, the system can obtain the first model attribute operand adjustment knowledge of the u th order and the second model attribute operand adjustment knowledge of the u th order, wherein u is more than or equal to 1 and less than or equal to x. This means that the system will make corresponding statistical adjustments to each order of the model, resulting in more accurate and comprehensive knowledge of the model's properties.

And finally, the system generates an x-th model calculation amount statistical result corresponding to the first power engineering component model data based on the x-th order first model attribute calculation amount adjustment knowledge and the x-th order second model attribute calculation amount adjustment knowledge. This statistics is a comprehensive output that contains detailed statistics of the model in various aspects, such as material usage, equipment quantity, human demand, and possible collision and collision conditions. This information has important reference value for subsequent engineering budgets and implementations.

From the foregoing detailed steps and explanations in these alternative embodiments, it will be more clearly understood how the system performs detailed and sophisticated processing and analysis of the first and second power engineering component model data. The process fully utilizes technical means such as multi-level knowledge embedding branches and model collision detection, extracts key attribute knowledge and conflict description information of the model, and obtains more accurate and comprehensive model attribute calculation adjustment knowledge and model calculation statistical results through calculation statistical adjustment.

In a next step, the method further comprises: in the process of carrying out knowledge feature mapping on the (u+1) -th order first model attribute calculation amount adjustment knowledge and the (u+1) -th order second model attribute calculation amount adjustment knowledge based on the first modeling task indication variable and the second modeling task indication variable by referring to the first modeling task category label, carrying out calculation amount statistical monitoring by utilizing a (u) -th model calculation amount statistical result to obtain a (u+1) -th order first BIM model vector corresponding to the first power engineering component model data and a (u+1) -th order second BIM model vector corresponding to the second power engineering component model data; and generating a u+1 model calculation quantity statistical result corresponding to the first power engineering component model data according to the u+1-order first BIM model vector and the u+1-order second BIM model vector.

In the next step, the system executes the method covering the knowledge feature mapping of the current stage with the model calculation statistics of the previous stage, and finally generating new BIM model vectors and model calculation statistics. The following is a detailed illustration.

Firstly, the system performs knowledge feature mapping on the (u+1) -th order first model attribute operand adjustment knowledge and the (u+1) -th order second model attribute operand adjustment knowledge by referring to the first modeling task class labels based on the first modeling task indication variable and the second modeling task indication variable. In this process, knowledge feature mapping can be understood as transforming model attribute scalar knowledge into a more specific, more suited form or structure for a particular modeling task. The first modeling task indicating variable and the second modeling task indicating variable may be parameters or settings used to guide the mapping process, which define the target and direction of the mapping. The first modeling task category label provides specific context and background information for mapping, and ensures that a mapping result meets specific modeling task requirements.

Meanwhile, in the process of mapping the knowledge features, the system can utilize the calculation statistics result of the u model to carry out calculation statistics monitoring. The calculation statistics monitoring can be understood as analysis and utilization of the calculation statistics of the previous stage model to evaluate the accuracy and effectiveness of the knowledge feature mapping of the current stage. Through calculation statistics monitoring, the system can ensure that the result of the knowledge feature mapping keeps consistent and consistent with the model calculation statistics result of the previous stage.

After the calculation quantity statistics monitoring, the system obtains a first BIM model vector of the (u+1) th order corresponding to the first power engineering component model data and a second BIM model vector of the (u+1) th order corresponding to the second power engineering component model data. BIM model vectors are key components in BIM (building information model) and contain various attributes and information of the model, such as geometry, material properties, connection modes, etc. Here, the (u+1) -th order first BIM model vector and the second BIM model vector represent updated and optimized model information obtained after knowledge feature mapping and calculation amount statistical monitoring.

And finally, generating a u+1 model calculation quantity statistical result corresponding to the model data of the first power engineering component by the system according to the u+1-order first BIM model vector and the u+1-order second BIM model vector. This statistical result combines the information and results of the first two steps to provide computationally comprehensive and accurate data about the power engineering component model. The data has important reference value and guiding significance for the subsequent engineering design, budget, construction and other links.

From the above description, it is better understood how the system uses the model calculation statistics of the previous stage to assist the knowledge feature mapping of the current stage, and finally generates new BIM model vectors and model calculation statistics. The process ensures the consistency and accuracy of the model information and improves the efficiency and quality of modeling tasks.

In a further step, the calculating and monitoring is performed by using the calculation and statistics result of the u-th model to obtain a first BIM model vector of the (u+1) -th order corresponding to the first power engineering component model data and a second BIM model vector of the (u+1) -th order corresponding to the second power engineering component model data, including: performing calculation improvement on the calculation statistics result of the u-th model based on the model data of the first power engineering component to obtain an improved calculation statistics result of the u-th model; and carrying out calculation statistics monitoring based on the improved calculation statistics result of the u-th model to obtain the first BIM model vector of the u+1 order and the second BIM model vector of the u+1 order.

In a further step, the system performs a method covering statistical monitoring of the calculation using the calculation result of the u-th model, and obtains the BIM model vector of the update stage (i.e., u+1 order) through a series of processes. The following is a detailed illustration.

First, the system will perform a calculation improvement on the calculation statistics of the u-th model based on the first power engineering component model data. The term "improvement" is understood here as the process of optimizing and correcting the statistics of the previous stage. In this process, the system may analyze errors, omissions, or inconsistencies in the calculation statistics of the u-th model, and make corresponding adjustments and improvements based on the characteristics and requirements of the model data of the first electrical engineering component. Such improvements may include data cleansing, outlier handling, missing value padding, etc. to ensure accuracy and reliability of the statistics.

After the calculation amount is improved, the system obtains the improved calculation amount statistical result of the u model. The result is more accurate and comprehensive than the original statistical result, and provides a better basis for subsequent processing and analysis.

Next, the system performs statistical monitoring based on the improved calculation statistics of the u-th model. "statistical monitoring of the calculation" is understood here as a further analysis and verification process of the improved statistics. In this process, the system may utilize various statistical methods and algorithms to perform multidimensional analysis and evaluation of the improved statistics to ensure compliance with expected standards and requirements.

Through calculation and statistics monitoring, the system obtains a first BIM model vector of the (u+1) th order and a second BIM model vector of the (u+1) th order. These two vectors represent updated and optimized BIM model information obtained after the calculation improvement and the statistical monitoring. The BIM model not only contains various attributes and information of the original model, but also integrates optimization and correction in the statistics result of the previous stage, so that the BIM model is more accurate, fine and comprehensive.

It should be noted that "the (u+1) th order" herein refers to an update stage of the BIM model vector, which is similar to the previous "x order" or "u order", and represents the level or depth of the model attribute or information. However, in this context, "the (u+1) th order" refers specifically to the BIM model vector of the update phase obtained after the calculation improvement and the statistical monitoring.

From the above description of these steps, it is more clearly understood how the system uses the calculation statistics of the u-th model to perform calculation statistics monitoring, and obtains the BIM model vector of the update stage through a series of processes. The process ensures the accuracy and reliability of BIM model information, and provides powerful support for subsequent engineering design, construction and management.

In a further step, the calculating improvement is performed on the calculation result of the u-th model based on the first power engineering component model data, so as to obtain an improved calculation result of the u-th model, which includes: performing derivative treatment on the calculation statistics result of the u model, and performing model attribute knowledge mining on the calculation statistics result of the u model after the derivative treatment to obtain the model characteristics of the first power engineering component of the calculation statistics result of the u model; performing model attribute knowledge mining on the first power engineering component model data to obtain second power engineering component model characteristics and component model redundancy information of the first power engineering component model data; and carrying out calculation improvement on the calculation result of the u-th model according to the first power engineering component model characteristics, the second power engineering component model characteristics and the component model redundancy information to obtain the improved calculation result of the u-th model.

In a further step, the system performs a series of refinement processes on the model-calculation statistics to obtain improved statistics. The following is a detailed illustration.

First, the system derives the calculation statistics of the u-th model. "derived processing" is understood herein to mean processing, transforming, or extracting the original statistical data to generate new data or information. In this process, the system may employ various data processing techniques and algorithms, such as data aggregation, feature extraction, dimension reduction, etc., to extract more valuable information from the raw statistics.

After the derivation process, the system obtains a new calculation statistic result of the u model, and the result contains implicit information and modes in the original data. Next, the system performs model attribute knowledge mining on the derived and processed calculation statistics of the u-th model. The term "model attribute knowledge mining" as used herein refers to extracting knowledge and information related to model attributes from model data using techniques such as data mining and machine learning. Through this step, the system can identify the first power engineering component model feature in the u-th model calculation amount statistics.

Meanwhile, the system can also conduct model attribute knowledge mining on the first power engineering component model data. This process is similar to the mining process described above, but the goal is to extract the second electrical engineering component model features and component model redundancy information from the raw model data. The "second electric power engineering component model feature" herein refers to feature information that is different from or complementary to the first electric power engineering component model feature, and the "component model redundant information" refers to information that exists in the model data but does not matter for the current task or analysis.

After the first power engineering component model feature, the second power engineering component model feature and the component model redundant information are obtained, the system performs calculation improvement on the calculation statistics result of the u-th model according to the information. This improvement process may include the steps of data cleansing, outlier handling, missing value padding, and feature-based weight adjustment. Through the processing, the system can ensure that the statistical result is more accurate, comprehensive and meets the actual requirements.

Finally, the system obtains the improved calculation statistic result of the ith model. The result not only fuses the information of the original statistical data and the derived data, but also considers the influence of the model characteristics and the redundant information, thereby having higher accuracy and reliability. This result will provide a solid basis for subsequent BIM model vector generation and model phasor statistics.

From the above, it is clear how the system derives the calculation statistics of the model u, digs the knowledge of the model attribute, and improves the calculation. The process ensures the accuracy and reliability of the statistical result and provides powerful data support for the smooth implementation of the power engineering project.

FIG. 2 is a schematic diagram of a big data processing system 200 according to an embodiment of the present application. Big data processing system 200, as shown in FIG. 2, includes a processor 210, and processor 210 may call and execute a computer program from memory to implement methods in embodiments of the present application.

Optionally, as shown in FIG. 2, big data processing system 200 may also include a memory 230. Wherein the processor 210 may call and run a computer program from the memory 230 to implement the method in an embodiment of the application.

Wherein the memory 230 may be a separate device from the processor 210 or may be integrated into the processor 210.

Optionally, as shown in fig. 2, the big data processing system 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices, and in particular, may send information or data to other devices, or receive information or data sent by other devices.

Optionally, the big data processing system 200 may implement the storage engine or a component (such as a processing module) in the storage engine or a corresponding flow corresponding to a device in which the storage engine is deployed in each method of the embodiments of the present application, which is not described herein for brevity.

It should be appreciated that the processor of an embodiment of the present application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The Processor may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), an Application SPECIFIC INTEGRATED Circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It will be appreciated that the memory in embodiments of the application may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, DDR SDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and Direct memory bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

It should be appreciated that the above memory is exemplary but not limiting, and for example, the memory in the embodiments of the present application may also be static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (doubledata RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCH LINK DRAM, SLDRAM), direct Rambus RAM (DR RAM), and the like. That is, the memory in embodiments of the present application is intended to comprise, without being limited to, these and any other suitable types of memory.

On the basis of the above, a computer readable storage medium is provided, on which a computer program is stored, which computer program, when run, implements the method described above.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art.

Claims

1. A method for calculating and counting an electric power engineering digital model based on Revit software, which is characterized by being applied to a big data processing system, the method comprising:

Performing model collision detection on the first power engineering component model data and the second power engineering component model data respectively to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, wherein the model collision description vectors comprise unit distribution characteristics of at least two collision model data units associated with a current model data unit in a key component cluster interval and contribution coefficients, the contribution coefficients represent modeling attribute disturbance weights of the collision model data units on the current model data unit, and the key component cluster interval is larger than an upstream and downstream data unit interval of the current model data unit; the key component cluster interval refers to a space range occupied by a group of components which are related to the model data unit and influence the model data unit in the power engineering; the upstream and downstream data unit interval refers to the space range occupied by the preceding and subsequent data units which are directly connected with the current model data unit in function or flow in the model; the upstream and downstream data units play a role in inputting or outputting in the workflow of the current data unit;

generating a model calculation amount statistical result corresponding to the first power engineering component model data according to the first model attribute calculation amount adjustment knowledge and the second model attribute calculation amount adjustment knowledge;

The detecting the model collision of the first power engineering component model data and the second power engineering component model data to obtain a first model collision description vector corresponding to each model data unit in the first power engineering component model data and a second model collision description vector corresponding to each model data unit in the second power engineering component model data, includes:

determining a second key component cluster interval according to a model attention index corresponding to the second power engineering component model compression data; performing model collision detection on the second power engineering component model compressed data according to the second key component cluster interval to obtain a second model collision description vector; the model attention index corresponding to the first power engineering component model compression data and the model attention index corresponding to the second power engineering component model compression data are used for measuring the measurement standard of the importance and influence of each component in the model;

In the first key component cluster section, performing model collision detection on the first power engineering component model compressed data to obtain the first model collision description vector, including: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first distribution relation network identification algorithm according to the first key component cluster interval; obtaining contribution coefficients of conflict model data units corresponding to each model data unit in the first power engineering component model data through a first contribution recognition algorithm; and in the second key component cluster section, performing model collision detection on the second power engineering component model compressed data to obtain the second model collision description vector, including: obtaining unit distribution characteristics of conflict model data units corresponding to each model data unit in the second power engineering component model data through a first distribution relation network identification algorithm according to the second key component cluster interval; and obtaining the contribution coefficient of the conflict model data unit corresponding to each model data unit in the second power engineering component model data through a first contribution identification algorithm.

2. The method of claim 1, wherein performing a statistical computation adjustment on the first base model attribute knowledge vector based on the first model conflict description vector and performing a statistical computation adjustment on the second base model attribute knowledge vector based on the second model conflict description vector to obtain a first model attribute computation adjustment knowledge and a second model attribute computation adjustment knowledge, comprising:

Performing model attention index association on the second model conflict description vector according to the model attention index of the second basic model attribute knowledge vector to obtain a second model conflict description vector with associated completed attention index, wherein the model attention index of the second model conflict description vector with associated completed attention index is the same as the model attention index of the second basic model attribute knowledge vector; the model attention index of the first basic model attribute knowledge vector and the model attention index of the second basic model attribute knowledge vector refer to measurement standards for measuring importance and influence of each part in the model;

3. The method of claim 1, wherein generating the model operand statistics corresponding to the first electrical power engineering component model data based on the first model attribute operand adjustment knowledge and the second model attribute operand adjustment knowledge comprises:

4. The method of claim 3, wherein performing resource correction on the first BIM model vector and the second BIM model vector to obtain a resource correction vector corresponding to the first power engineering component model data includes:

Performing resource correction on the first BIM calculation amount adjustment vector and the second BIM model vector to obtain the resource correction vector corresponding to the first power engineering component model data;

The performing model collision detection on the first BIM model vector to obtain a third model collision description vector corresponding to each BIM model member in the first BIM model vector, including:

5. A method according to claim 3, wherein determining the model resource dimension corresponding to each model data unit according to the contradictory characteristics, and obtaining the model calculation statistic result corresponding to the model data of the first power engineering component includes:

6. The method according to claim 1, wherein the method further comprises:

Debugging the depth residual error model by using the target training error;

Wherein, the determining a target training error based on the prior model calculation statistic result corresponding to the first power engineering component model data sample and the model calculation statistic result sample includes: determining a first training error through a preset loss function according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the calculation amount statistical result sample of the model; determining a second training error according to the calculation amount statistical viewpoint corresponding to the calculation amount statistical result of the prior model and the calculation amount statistical viewpoint corresponding to the model calculation amount statistical result sample for completing feature migration; the debugging the depth residual model with the target training error comprises the following steps: and debugging the depth residual error model according to the first training error and the second training error.

7. The method according to claim 1, wherein the performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data corresponding to the first power engineering component model data to obtain a first basic model attribute knowledge vector corresponding to the first power engineering component model data and a second basic model attribute knowledge vector corresponding to the second power engineering component model data includes: performing model attribute knowledge mining on the first power engineering component model data and the second power engineering component model data through multistage knowledge embedding branches to obtain an x-order first basic model attribute knowledge vector corresponding to the first power engineering component model data and an x-order second basic model attribute knowledge vector corresponding to the second power engineering component model data;

8. The method of claim 7, wherein the method further comprises:

generating a u+1 model calculation quantity statistical result corresponding to the first power engineering component model data according to the u+1-order first BIM model vector and the u+1-order second BIM model vector;

the calculating quantity statistical monitoring is performed by using a u-th model calculating quantity statistical result to obtain a u+1-th order first BIM model vector corresponding to the first power engineering component model data and a u+1-th order second BIM model vector corresponding to the second power engineering component model data, including:

performing calculation statistics monitoring based on the improved calculation statistics result of the u-th model to obtain the first BIM model vector of the (u+1) -th order and the second BIM model vector of the (u+1) -th order;

The calculating amount improvement is performed on the calculation amount statistical result of the u-th model based on the model data of the first power engineering component, and the improved calculation amount statistical result of the u-th model is obtained, and the calculating amount improvement method comprises the following steps:

9. A big data processing system comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the method of any one of claims 1-8.