CN118551838A

CN118551838A - Relay protection operation safety check decision knowledge base construction method and device

Info

Publication number: CN118551838A
Application number: CN202410818445.4A
Authority: CN
Inventors: 田得良; 陈朝晖; 丁晓兵; 余江; 郑茂然
Original assignee: China Southern Power Grid Co Ltd
Current assignee: China Southern Power Grid Co Ltd
Priority date: 2024-06-24
Filing date: 2024-06-24
Publication date: 2024-08-27

Abstract

The application relates to a method and a device for constructing a relay protection operation safety check decision knowledge base. The method comprises the following steps: acquiring actual operation data of a power grid system, knowledge base construction core data and knowledge base construction auxiliary data; constructing core data according to actual operation data and a knowledge base, and constructing a check decision data analysis layer of a power grid system; constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and constructing a checking decision knowledge analysis layer of the power grid system; according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer, a check decision data application layer of the power grid system is constructed; and fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain a safety check decision knowledge base of the power grid system. The method can eliminate the defect of data processing capacity in the aspect of checking decision on relay protection operation safety.

Description

Relay protection operation safety check decision knowledge base construction method and device

Technical Field

The application relates to the technical field of smart grids, in particular to a method and a device for constructing a relay protection operation safety check decision knowledge base, computer equipment, a storage medium and a computer program product.

Background

With the development of computer technology, a relay protection operation safety check decision technology appears, and the technology evaluates and optimizes the operation condition of a relay protection device in a power system so as to ensure the safety and reliability of a power grid. The process comprises data acquisition and preprocessing, fixed value and action time checking, performance evaluation and fault risk analysis, and is used for optimizing protection configuration and maintenance strategies, making an emergency plan and ensuring that the power grid can still run safely when the relay protection device fails.

In the traditional technology, the implementation of the relay protection operation safety check decision is mainly realized by manually collecting operation data and fault records, relying on engineers to manually compare and calculate to perform constant value check and action time check, evaluating the performance of the protection device through standardized tests, manually analyzing the fault cause and the effectiveness of the protection device after the fault occurs, and finally checking and checking according to a regular maintenance plan, wherein all decisions are analyzed and optimized by engineers with abundant experience. The data processing capability in the aspect of checking the operation safety of relay protection has serious defects.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for constructing a relay protection operation safety check decision knowledge base that can eliminate the drawbacks of data processing capabilities in terms of relay protection operation safety check decisions.

In a first aspect, the application provides a method for constructing a relay protection operation safety check decision knowledge base, which comprises the following steps:

acquiring actual operation data of a power grid system, knowledge base construction core data and knowledge base construction auxiliary data;

Constructing core data according to actual operation data and the knowledge base, and constructing a check decision data analysis layer of the power grid system;

constructing auxiliary data and the check decision data analysis layer according to the knowledge base, and constructing a check decision knowledge analysis layer of the power grid system;

Constructing a check decision data application layer of the power grid system according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer;

And fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain a safety check decision knowledge base of the power grid system.

In a second aspect, the present application further provides a device for constructing a relay protection operation safety check decision knowledge base, including:

The data acquisition module is used for acquiring actual operation data of the power grid system, knowledge base construction core data and knowledge base construction auxiliary data;

The analysis layer construction module is used for constructing core data according to actual operation data and the knowledge base and constructing a check decision data analysis layer of the power grid system;

The analysis layer construction module is used for constructing auxiliary data and the check decision data analysis layer according to the knowledge base and constructing a check decision knowledge analysis layer of the power grid system;

the application layer construction module is used for constructing a check decision data application layer of the power grid system according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer;

the knowledge base obtaining module is used for fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain the safety check decision knowledge base of the power grid system.

In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:

The method, the device, the computer equipment, the storage medium and the computer program product for constructing the relay protection operation safety check decision knowledge base are characterized in that actual operation data of a power grid system, knowledge base construction core data and knowledge base construction auxiliary data are obtained; constructing core data according to actual operation data and a knowledge base, and constructing a check decision data analysis layer of a power grid system; constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and constructing a checking decision knowledge analysis layer of the power grid system; according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer, a check decision data application layer of the power grid system is constructed; and fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain a safety check decision knowledge base of the power grid system.

By acquiring actual operation data of the power grid system and constructing a knowledge base of core data and auxiliary data, the operation state and rule of the power grid can be recorded and analyzed in detail. Based on the data, a check decision data analysis layer is constructed, and an accurate decision basis is provided from the data layer. And the analysis layer and the auxiliary data are further combined to construct a check decision knowledge analysis layer, so that a deeper and intelligent analysis result is provided. The layers construct a check decision data application layer under a unified data format, so that effective integration and utilization of data are realized. And finally, forming a safety check decision knowledge base of the power grid system by integrating the analysis layer, the knowledge analysis layer and the application layer. The method not only can eliminate the defect of data processing capability in the aspect of safety check decision of relay protection operation, but also can improve the accuracy and timeliness of the check decision of the power grid, enhance the risk resistance and fault recovery capability of the system, ensure the stable and safe operation of the power grid, and simultaneously provide powerful support and guarantee for the intelligent and digital management of the power grid system.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.

FIG. 1 is an application environment diagram of a method for constructing a relay protection operation safety check decision knowledge base in one embodiment;

FIG. 2 is a schematic flow chart of a method for constructing a knowledge base for checking safety of relay protection operation in one embodiment;

FIG. 3 is a flow diagram of a method for constructing a verification decision knowledge analysis layer in one embodiment;

FIG. 4 is a flow diagram of a method for determining relay electrical security reasoning information in accordance with one embodiment;

FIG. 5 is a flow chart of a method for constructing a verification decision knowledge analysis layer in another embodiment;

FIG. 6 is a flow chart of a method for constructing a check decision data parsing layer in one embodiment;

FIG. 7 is a flowchart of a method for constructing a check decision data parsing layer according to another embodiment;

FIG. 8 is a block diagram of a construction device for a relay protection operation safety check decision knowledge base in one embodiment;

fig. 9 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The method for constructing the relay protection operation safety check decision knowledge base provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 obtains actual operation data of the power grid system, knowledge base construction core data and knowledge base construction auxiliary data from the terminal 102; constructing core data according to actual operation data and a knowledge base, and constructing a check decision data analysis layer of a power grid system; constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and constructing a checking decision knowledge analysis layer of the power grid system; according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer, a check decision data application layer of the power grid system is constructed; and fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain a safety check decision knowledge base of the power grid system. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In an exemplary embodiment, as shown in fig. 2, a method for constructing a relay protection operation safety check decision knowledge base is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps 202 to 210. Wherein:

Step 202, obtaining actual operation data of a power grid system, knowledge base construction core data and knowledge base construction auxiliary data.

The actual operating data may be data generated by each device (including the relay) of the power grid system during operation.

The knowledge base construction core data can be core data of a relay protection operation safety check decision knowledge base for constructing a power grid system.

The knowledge base construction auxiliary data can be auxiliary data of a relay protection operation safety check decision knowledge base for constructing a power grid system.

Specifically, collecting and arranging real-time operation data and historical operation records of each part of a power grid system, and generating a knowledge base to construct core data by utilizing the real-time operation data and the historical operation records, wherein the core data comprises a topological structure, equipment parameters, an operation state, a historical fault record and the like of the power grid; meanwhile, based on related documents, expert experience and standard specifications, a knowledge base is constructed to construct auxiliary data such as operation rules, maintenance manuals, emergency plans and the like.

And 204, constructing core data according to the actual operation data and the knowledge base, and constructing a check decision data analysis layer of the power grid system.

The check decision data analysis layer can be a calculation layer for checking, cleaning, converting and integrating data so as to ensure the accuracy and consistency of the data, and can be constructed by a neural network model. This hierarchy is responsible for converting raw data into usable, structured information, providing a reliable data basis for the decision support system.

Specifically, the actual operation data of the power grid system is cleaned, filtered and preprocessed, so that the accuracy and consistency of the data are ensured; then, constructing core data and actual operation data by utilizing a knowledge base in the knowledge base for carrying out association analysis, namely inputting the actual operation data, a power grid topological structure, equipment parameters, a historical fault record and the like into a comprehensive data integration model, and synthesizing the data of the actual operation data and the power grid topological structure, the equipment parameters, the historical fault record and the like to generate the core data; extracting key operation indexes and abnormal detection results in core data by utilizing a comprehensive data analysis model and through technologies such as statistical analysis, pattern recognition, machine learning and the like; and readjusting the comprehensive data integration model and the comprehensive data analysis model according to the key operation indexes and the abnormal detection results until the adjusted comprehensive data integration model and the adjusted comprehensive data analysis model meet preset targets, and inputting the adjusted comprehensive data integration model and the adjusted comprehensive data analysis model, actual operation data and the actual knowledge base into the analysis layer to obtain the check decision data analysis layer.

And 206, constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and constructing a checking decision knowledge analysis layer of the power grid system.

The checking decision knowledge analysis layer is mainly responsible for carrying out deep analysis and mining on checked and parsed data so as to extract valuable knowledge and finding holes. The level combines the technologies of statistical analysis, machine learning, artificial intelligence and the like to carry out complex analysis and pattern recognition on the data, thereby providing deep support for decision making, and the data is converted into knowledge which can be directly applied by a decision maker through a knowledge analysis layer.

Specifically, an operation rule, a maintenance manual and an emergency plan in auxiliary data are constructed by utilizing a knowledge base, and operation indexes and abnormal detection results extracted from a check decision data analysis layer are deeply analyzed and interpreted; classifying and analyzing reasons of abnormal conditions by combining expert experience data and standard specification data, and providing targeted solutions and operation suggestions; then, the analysis result is structured and graphically displayed by adopting a knowledge graph and an artificial intelligence technology, so that the analysis result is convenient to understand and apply; integrating the analysis results, the operation suggestions, the structuring and the graphics into a preset analysis layer to obtain a check decision knowledge analysis layer.

And step 208, constructing a check decision data application layer of the power grid system according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer.

The check decision data application layer may be mainly responsible for applying the checked, parsed and analyzed data to the actual service scenario. This hierarchy converts the extracted knowledge and insight into specific decision support tools and applications, such as reports, dashboards, predictive models, etc., to help the decision-maker make efficient decisions in the actual operation.

Specifically, based on a unified data model and a standardized data interface, the development data fusion and conversion module is utilized to integrate and optimize the operation indexes and the abnormal detection results in the check decision data analysis layer, the analysis results and suggestions in the check decision knowledge analysis layer according to the same data format; then, constructing a visual and interactive interface to meet the requirements of displaying the running state, risk early warning and optimization suggestions of the power grid system in the modes of an instrument panel, a chart, a report and the like; and finally, deploying the integrated and optimized data to an initial data application layer by combining a visual and interactive interface, so that the integrated and optimized data can receive and process power grid operation data in real time, and providing dynamic monitoring, decision support and intelligent management functions to obtain a check decision data application layer.

Step 210, a check decision data analysis layer, a check decision knowledge analysis layer and a check decision data application layer are fused to obtain a safety check decision knowledge base of the power grid system.

The security check-decision knowledge base may be a system for storing and managing security-related check-decision knowledge. It aggregates the validated and analyzed security data, rules, standards, and best practices to form a systematic knowledge base. This knowledge base supports automated and manual security decision processes, providing a reliable source of information to help identify and address potential security threats and risks. By means of continuous updating and maintenance, the security check decision knowledge base can provide the latest and most effective security policy and solution for the organization, and ensure the security operation of the business.

Specifically, integrating data and analysis results of all layers, and establishing a unified data storage and management platform for storing and managing the integrated data; by utilizing a development data synchronization and update mechanism and combining a big data analysis and artificial intelligence technology, the integrated data is subjected to deep mining and intelligent processing, and high-value safety check decision knowledge is extracted; and constructing an access and query interface of the knowledge base, integrating the checking decision data analysis layer, the checking decision knowledge analysis layer and the checking decision data application layer into an initial checking decision knowledge base, and carrying out parameter optimization on the initial checking decision knowledge base according to the safety checking decision knowledge to obtain a safety checking decision knowledge base.

In the method for constructing the relay protection operation safety check decision knowledge base, actual operation data of a power grid system, knowledge base construction core data and knowledge base construction auxiliary data are obtained; constructing core data according to actual operation data and a knowledge base, and constructing a check decision data analysis layer of a power grid system; constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and constructing a checking decision knowledge analysis layer of the power grid system; according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer, a check decision data application layer of the power grid system is constructed; and fusing the check decision data analysis layer, the check decision knowledge analysis layer and the check decision data application layer to obtain a safety check decision knowledge base of the power grid system.

In an exemplary embodiment, as shown in fig. 3, the auxiliary data and the checking decision data analysis layer are constructed according to the knowledge base, and the checking decision knowledge analysis layer of the power grid system is constructed, which includes steps 302 to 306. Wherein:

and step 302, constructing auxiliary data and a checking decision data analysis layer according to the knowledge base, and determining relay safety entity relation information.

The relay safety entity relation information can be detailed information of various entities and interrelations thereof related to the relay protection system. These entities include electrical system equipment such as relays, circuit breakers, transformers, and their roles and connections in the protection system.

Specifically, constructing information such as operation rules, maintenance manuals, historical fault records and the like in auxiliary data by a knowledge base, and performing association analysis on the information and operation indexes and abnormal detection results in a checking decision data analysis layer; extracting and mapping the entities (such as equipment, fault types, maintenance measures and the like) in the two different data sources by using a knowledge graph technology, and constructing a relay safety entity relationship graph; and extracting relay safety entity relation information according to the relay safety entity relation diagram.

And step 304, constructing auxiliary data, a checking decision data analysis layer and relay entity relation information according to the knowledge base, and determining relay safety reasoning information.

The relay safety reasoning information can be safety assessment and decision information obtained through logical reasoning and analysis based on equipment state and operation data in the relay protection system. The method combines real-time monitoring data, historical fault records and system operation rules to carry out comprehensive judgment, predicts possible faults, evaluates the safety of the system and provides corresponding preventive and treatment measures.

Specifically, deep learning training is carried out on operation rules and maintenance manuals in the knowledge base construction auxiliary data, and relevant rules and reasoning logic are extracted; combining the reasoning logic with the operation index and the abnormal detection result in the checking decision data analysis layer, and carrying out causal relationship reasoning and fault mode analysis by utilizing the relay entity relation information to obtain a reasoning result; and matching and verifying the reasoning result and the entity relationship through a knowledge graph technology to generate specific relay safety reasoning information including fault reasons, possible influences and suggested measures.

And 306, constructing a checking decision knowledge analysis layer according to the relay safety entity relation information and the relay safety reasoning information.

Specifically, integrating relay safety entity relation information and relay safety reasoning information to establish a unified data model; carrying out structural storage and association mapping on relay safety entity relation information and relay safety reasoning information by utilizing a knowledge graph technology, and constructing a comprehensive knowledge network; further using machine learning and artificial intelligence technology to carry out deep analysis and mining on the knowledge network, and extracting key decision nodes and association rules; and utilizing a development visual analysis tool to display analysis results and reasoning processes, and deploying a unified data model, a comprehensive knowledge network, a construction key decision node and association rules into an initial analysis layer to obtain a checking decision knowledge analysis layer.

In the embodiment, the auxiliary data and the checking decision data analysis layer are built by combining the knowledge base, the relay safety entity relation information is determined, and on the basis, the relay safety reasoning information is determined by utilizing the relay safety entity relation information and the data of the checking decision data analysis layer, so that the checking decision knowledge analysis layer is built. The method can effectively integrate multi-source data, accurately identify the relationship between equipment and faults, conduct intelligent fault reasoning and risk assessment, and finally form a structured knowledge analysis layer. The process not only improves the accuracy and reliability of the check decision of the power grid system, but also enhances the intelligent management capability of the system, and ensures the stable operation and the rapid fault response of the power grid.

In an exemplary embodiment, as shown in fig. 4, the relay security reasoning information is determined by constructing auxiliary data, a check decision data parsing layer and relay entity relationship information according to a knowledge base, and the steps comprise step 402 to step 404. Wherein:

and step 402, acquiring a relay safety reasoning algorithm corresponding to the power system.

The relay safety reasoning algorithm can be a calculation method for analyzing and evaluating the safety of the relay protection system. The algorithm identifies potential safety risks and fault modes by carrying out logic reasoning and comprehensive analysis on state data, historical fault records and operation rules of various devices in the power system. It can predict possible faults, provide preventive maintenance advice, and make a responsive decision quickly when a fault occurs.

Specifically, forming a training data set by historical operation data, fault records and maintenance manuals of the power system; further after selecting a proper artificial intelligence and machine learning algorithm (such as decision tree, random forest or deep learning), training the selected artificial intelligence and machine learning algorithm by using a training data set to generate a preliminary reasoning model; and (3) optimizing and verifying the reasoning model by combining the relay safety entity relation information to form a relay safety reasoning algorithm, and updating and training the model through continuous data.

And step 404, based on the reasoning rule set and the reasoning logic, using a relay safety reasoning algorithm to perform reasoning on the knowledge base construction auxiliary data, the checking decision data analysis layer and the relay entity relation information, so as to obtain relay safety reasoning information.

The inference rule set may be a rule set for logical inference and decision-making in a power system. These rules define actions or decisions to be taken in each case based on knowledge and experience in a particular field. The inference rule set typically includes matching relationships of conditions and conclusions, and by applying these rules, the system can automatically analyze the input data to arrive at a reasonable conclusion or suggestion.

Specifically, under the guidance of an inference rule set and an inference logic, the knowledge base is used for constructing auxiliary data, a checking decision data analysis layer and relay entity relation information to be input into a relay safety inference algorithm for automatic inference, the relay safety inference algorithm in the inference process is used for analyzing and processing the input data, identifying potential failure modes and risk factors, and deducing possible failure reasons and influence ranges thereof by combining the entity relation information to obtain a preliminary inference result; and carrying out structural storage and visual display on the preliminary reasoning result to obtain relay safety reasoning information.

In the embodiment, by acquiring a relay safety reasoning algorithm corresponding to the power system, the algorithm comprises a reasoning rule set and a reasoning logic, and based on the reasoning rule set and the logic, the relay safety reasoning algorithm is used for reasoning auxiliary data, a checking decision data analysis layer and relay entity relation information constructed by a knowledge base, so as to generate relay safety reasoning information. The process effectively integrates and analyzes the multi-source data, automatically identifies and infers potential fault modes and risk factors, and provides accurate fault diagnosis and coping strategies, so that the safety, stability and intelligent management capacity of the power system are greatly improved, faults are timely found and processed in the running process of the power grid system, and the risks of power failure and equipment damage are reduced.

In an exemplary embodiment, as shown in fig. 5, a check decision knowledge analysis layer is constructed according to the relay safety entity relationship information and the relay safety reasoning information, and the check decision knowledge analysis layer comprises steps 502 to 506. Wherein:

Step 502, determining initial data interface information of a checking decision knowledge analysis layer according to relay safety entity relation information and relay safety reasoning information.

The initial data interface information may be a detailed description of basic data and its related interfaces acquired from an external data source by the checking decision knowledge analysis layer at the beginning of data processing and analysis. Such information includes data source, data format, transport protocol, interface address, authentication mode, etc.

Specifically, key data fields and association relations required by a checking decision knowledge analysis layer are identified and extracted; defining a data interface standard according to the hardware facilities, the key data fields and the association relation of the checking decision knowledge analysis layer, and determining a data transmission format and a protocol; based on relay safety reasoning information, designing input and output parameters of a data interface, covering information such as fault reasons, influence ranges, risk levels, recommended measures and the like, and defining an initial data interface; and forming initial data interface information of the checking decision knowledge analysis layer under the condition that the data interface standard and the standard of the initial data interface are unified.

Step 504, optimizing the initial data interface information according to the data interface information of the check decision data analysis layer to obtain optimized data interface information.

The optimized data interface information may be data interface information after the initial data interface information is optimized.

Specifically, evaluating an initial data interface, and identifying performance bottlenecks and potential problems in data transmission; under the condition that the performance bottleneck and the data transmission can meet the power grid system, the data format and the transmission protocol of the initial data interface information are optimized by combining the data interface information of the check decision data analysis layer; and further adjusting and expanding input and output parameters of the data interface, adding necessary fields to meet the check decision requirement, and finally obtaining the optimized data interface information.

And step 506, constructing a checking decision knowledge analysis layer according to the relay safety entity relation information, the relay safety reasoning information and the optimized data interface information.

Specifically, integrating relay safety entity relation information, relay safety reasoning information and optimized data interface information, and establishing a unified data model; importing relay safety entity relation information and relay safety reasoning information into an initial checking decision knowledge analysis layer by utilizing optimized data interface information; deep analysis and knowledge mining are carried out on the imported data by adopting machine learning and artificial intelligence technology, and key decision nodes and association rules are extracted; and deploying the unified data model, the key decision nodes and the association rules into an initial checking decision knowledge analysis layer to construct a complete checking decision knowledge analysis layer.

In this embodiment, initial data interface information of the checking decision knowledge analysis layer is defined by determining relay safety entity relation information and relay safety reasoning information, then the initial interfaces are optimized according to the data interface information of the checking decision knowledge analysis layer, optimized data interface information is obtained, and finally the checking decision knowledge analysis layer is constructed by utilizing the relay safety entity relation information, the reasoning information and the optimized data interface information. The method ensures the accuracy and the high efficiency of the data interface, enhances the compatibility and the interoperability among the data layers, and enables the knowledge analysis layer to effectively integrate and analyze multi-source data, thereby improving the fault diagnosis, the risk assessment and the intelligent decision making capability of the power grid system and finally improving the safety, the reliability and the management efficiency of the system.

In an exemplary embodiment, as shown in fig. 6, the core data is constructed according to the actual operation data and the knowledge base, and a check decision data analysis layer of the power grid system is constructed, which includes steps 602 to 606. Wherein:

Step 602, segment segmentation is performed on the actual operation data and the knowledge base construction core data, so as to obtain segment operation data and segment core data.

The paragraph operation data may be a segmentation result obtained by segmenting the actual operation data into paragraphs; the paragraph core data can be a segmentation result obtained by segmenting paragraphs of knowledge base construction core data

Specifically, constructing data characteristics and logic relations of core data according to actual operation data and a knowledge base, formulating a paragraph segmentation rule, and determining segmentation points (such as time stamps, event types and the like); dividing the actual operation data by applying a paragraph dividing rule and dividing points, and dividing the continuous data stream into independent paragraphs to obtain paragraph operation data; and simultaneously, carrying out the same segmentation processing on the knowledge base construction core data by applying the paragraph segmentation rules and segmentation points, and dividing the information of different categories and layers into independent paragraphs to obtain paragraph core data.

Step 604 identifies critical paragraph data from the paragraph run data and paragraph core data.

Specifically, identifying criteria and indicators of key paragraphs are defined, such as outliers, critical parameter changes, important event markers, etc.; analyzing paragraph operation data by using data mining and pattern recognition technology, and screening out key paragraphs meeting recognition standards; meanwhile, the core data of the paragraphs are correspondingly analyzed, and core paragraphs with important reference values are identified; the identified key paragraphs and the core paragraphs are cross-validated, and in the event of a validation pass, these key paragraph data are extracted and labeled to form a key paragraph data set.

Step 606, a check decision data analysis layer is constructed according to the key paragraph data.

Specifically, the identified key paragraph data are subjected to sorting and standardization processing, a data analysis model is established under the condition of ensuring the consistency of the data format, and the key paragraph data are subjected to deep analysis by utilizing technologies such as statistical analysis, pattern recognition and machine learning, so that key operation indexes and abnormal characteristics are extracted; and constructing a multidimensional data analysis view according to the key operation indexes and the abnormal characteristics for analysis, and disposing an analysis result and a data analysis model on an out-of-order check decision data analysis layer to form a check decision data analysis layer.

In this embodiment, the segment operation data and the segment core data are obtained by respectively performing segment segmentation on the actual operation data and the core data of the knowledge base, then the key segment data is identified from the segment data, and a check decision data analysis layer is constructed based on the key segment data. This process helps to structure large amounts of operational data and core data, extracting critical information, and thereby improving the accuracy and efficiency of data analysis. The finally constructed check decision data analysis layer can provide real-time operation monitoring, fault diagnosis and optimization decision support, and the management intelligence level and the safety reliability of the power grid system are obviously improved.

In one exemplary embodiment, as shown in FIG. 7, a check decision data parsing layer is built from the critical paragraph data, including steps 702 through 706. Wherein:

step 702, identifying a device-fault relationship, device information, and an operation criterion based on the critical paragraph data.

The device-fault relationship may be a correspondence relationship between each different device in the power grid system and a fault of the device.

Specifically, the first: classifying and sorting the key paragraph data, extracting information such as equipment operation records, fault events, operation logs and the like from the key paragraph data, identifying the relationship between equipment and faults by utilizing association analysis and pattern recognition technology, and establishing an equipment-fault relationship diagram; second,: extracting specific information of equipment from the key paragraphs, including model numbers, parameters, historical operation data and the like, analyzing operation logs and maintenance manuals, and extracting relevant operation standards and regulations; third,: and integrating and verifying the information of the two steps to form a complete equipment-fault relation, equipment information and operation standard data set.

Step 704, selecting a decision data analysis algorithm according to the key paragraph data.

The decision data analysis algorithm may be, among other things, a computational method and logic process for processing and analyzing data to support decision-making. These algorithms help decision makers understand trends and relationships behind data by screening, cleaning, modeling, and analyzing large amounts of data, extracting valuable information and patterns. They may include techniques such as statistical analysis, machine learning, data mining, etc., to improve the accuracy and efficiency of decisions through optimization and automated analysis processes.

Specifically, extracting and preprocessing the characteristics of the key paragraph data, and identifying main characteristics and modes of the data; evaluating the applicability of different analysis algorithms (such as decision trees, random forests, support vector machines, neural networks and the like) according to the characteristics and analysis requirements of the data; and then testing and comparing candidate algorithms by using cross-validation and performance evaluation indexes (such as accuracy, recall, F1 score and the like), and selecting an optimal algorithm as a decision data analysis algorithm.

In step 706, a check decision data analysis layer is constructed in combination with the equipment-fault relationship, the equipment information, the operation criteria and the decision data analysis algorithm.

Specifically, integrating the equipment-fault relationship, the equipment information and the operation standard into unified data; training and optimizing the integrated unified data by using a selected decision data analysis algorithm to generate a prediction model and an analysis rule; inputting the real-time operation data into a model for fault prediction and risk assessment to obtain fault and risk assessment data; under the support of constructing a visual interface, deploying the prediction model, the analysis rules and the evaluation data of faults and risks in an initial checking decision data analysis layer to form a complete checking decision data analysis layer.

In this embodiment, by identifying the equipment-fault relationship, the equipment information and the operation standard according to the key paragraph data, selecting a suitable decision data analysis algorithm, and combining these information and algorithms to construct a check decision data analysis layer. The process ensures that the construction of the data analysis layer is based on accurate equipment and fault associated information and standard operation rules, and simultaneously utilizes an optimal analysis algorithm to process data. Finally, the constructed check decision data analysis layer can provide efficient and accurate fault diagnosis and decision support, greatly improve the fault early warning capacity, the running stability and the management efficiency of the power grid system and ensure the safe and reliable running of the power grid system.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a device for constructing the relay protection operation safety check decision knowledge base, which is used for realizing the method for constructing the relay protection operation safety check decision knowledge base. The implementation scheme of the solution provided by the device is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the one or more relay protection operation safety check decision knowledge base construction devices provided below can be referred to the limitation of the relay protection operation safety check decision knowledge base construction method hereinabove, and the description is omitted herein.

In an exemplary embodiment, as shown in fig. 8, there is provided a relay protection operation safety check decision knowledge base construction apparatus, including: a data acquisition module 802, an parsing layer construction module 804, an analysis layer construction module 806, an application layer construction module 808, and a knowledge base obtaining module 810, wherein:

the data acquisition module 802 is configured to acquire actual operation data of the power grid system, knowledge base construction core data, and knowledge base construction auxiliary data;

the analysis layer construction module 804 is configured to construct core data according to actual operation data and a knowledge base, and construct a check decision data analysis layer of the power grid system;

the analysis layer construction module 806 is configured to construct an auxiliary data and a check decision data analysis layer according to the knowledge base, and construct a check decision knowledge analysis layer of the power grid system;

the application layer construction module 808 is configured to construct a check decision data application layer of the power grid system according to the data of the check decision data analysis layer and the data of the check decision knowledge analysis layer;

the knowledge base obtaining module 810 is configured to fuse the check decision data analysis layer, the check decision knowledge analysis layer, and the check decision data application layer to obtain a security check decision knowledge base of the power grid system.

In one embodiment, the analysis layer construction module 806 is further configured to construct auxiliary data and check decision data analysis layers according to the knowledge base, and determine relay security entity relationship information; constructing auxiliary data, a checking decision data analysis layer and relay entity relation information according to the knowledge base, and determining relay safety reasoning information; and constructing a checking decision knowledge analysis layer according to the relay safety entity relation information and the relay safety reasoning information.

In one embodiment, the analysis layer construction module 806 is further configured to obtain a relay security reasoning algorithm corresponding to the power system; the relay safety reasoning algorithm comprises a reasoning rule set and a reasoning logic; based on the reasoning rule set and the reasoning logic, the relay safety reasoning algorithm is used for reasoning auxiliary data, a checking decision data analysis layer and relay entity relation information constructed by the knowledge base, and relay safety reasoning information is obtained.

In one embodiment, the analysis layer construction module 806 is further configured to determine initial data interface information of the check decision knowledge analysis layer according to the relay security entity relationship information and the relay security reasoning information; optimizing initial data interface information according to the data interface information of the check decision data analysis layer to obtain optimized data interface information; and constructing a checking decision knowledge analysis layer according to the relay safety entity relation information, the relay safety reasoning information and the optimized data interface information.

In one embodiment, the parsing layer construction module 804 is further configured to perform paragraph segmentation on the actual operation data and the knowledge base construction core data, to obtain paragraph operation data and paragraph core data; identifying key paragraph data from paragraph run data and paragraph core data; and constructing a check decision data analysis layer according to the key paragraph data.

In one embodiment, the parsing layer construction module 804 is further configured to identify a device-fault relationship, device information, and operation criteria according to the critical paragraph data; selecting a decision data analysis algorithm according to the key paragraph data; and constructing a checking decision data analysis layer by combining the equipment-fault relation, the equipment information, the operation standard and the decision data analysis algorithm.

All or part of each module in the relay protection operation safety check decision knowledge base construction device can be realized by software, hardware and combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing server data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to realize a method for constructing a relay protection operation safety check decision knowledge base.

It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-described method embodiments.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are both information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A method for constructing a relay protection operation safety check decision knowledge base is characterized by comprising the following steps:

2. The method according to claim 1, wherein the building auxiliary data and the checking decision data analysis layer according to the knowledge base, building a checking decision knowledge analysis layer of the power grid system, comprises:

Constructing auxiliary data and the check decision data analysis layer according to the knowledge base, and determining relay safety entity relation information;

Establishing auxiliary data, the check decision data analysis layer and the relay entity relation information according to the knowledge base, and determining relay safety reasoning information;

And constructing the checking decision knowledge analysis layer according to the relay safety entity relation information and the relay safety reasoning information.

3. The method of claim 2, wherein said constructing auxiliary data, said check decision data parsing layer, and said relay entity relationship information from said knowledge base, determining relay security reasoning information, comprises:

Acquiring a relay safety reasoning algorithm corresponding to the power system; the relay safety reasoning algorithm comprises a reasoning rule set and a reasoning logic;

And based on an inference rule set and the inference logic, using the relay safety inference algorithm to construct auxiliary data, the checking decision data analysis layer and the relay entity relation information to infer the knowledge base, so as to obtain the relay safety inference information.

4. The method according to claim 2, wherein the constructing the check decision knowledge analysis layer according to the relay security entity relation information and the relay security reasoning information comprises:

Determining initial data interface information of the checking decision knowledge analysis layer according to the relay safety entity relation information and the relay safety reasoning information;

Optimizing the initial data interface information according to the data interface information of the check decision data analysis layer to obtain optimized data interface information;

And constructing the checking decision knowledge analysis layer according to the relay safety entity relation information, the relay safety reasoning information and the optimized data interface information.

5. The method according to claim 1, wherein the building core data according to actual operation data and the knowledge base, and building a check decision data analysis layer of the power grid system, comprises:

Respectively carrying out paragraph segmentation on the actual operation data and the knowledge base construction core data to obtain paragraph operation data and paragraph core data;

Identifying critical paragraph data from the paragraph run data and the paragraph core data;

and constructing the check decision data analysis layer according to the key paragraph data.

6. The method of claim 5, wherein constructing the check decision data parsing layer from the key paragraph data comprises:

identifying a device-fault relationship, device information, and an operation standard according to the key paragraph data;

selecting a decision data analysis algorithm according to the key paragraph data;

and constructing the checking decision data analysis layer by combining the equipment-fault relation, the equipment information, the operation standard and the decision data analysis algorithm.

7. The utility model provides a relay protection operation safety check decision knowledge base construction device which characterized in that, the device includes:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.