[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN117931865A - Deep learning-based municipal engineering BIM intelligent drawing examination method - Google Patents

Deep learning-based municipal engineering BIM intelligent drawing examination method Download PDF

Info

Publication number
CN117931865A
CN117931865A CN202311755227.2A CN202311755227A CN117931865A CN 117931865 A CN117931865 A CN 117931865A CN 202311755227 A CN202311755227 A CN 202311755227A CN 117931865 A CN117931865 A CN 117931865A
Authority
CN
China
Prior art keywords
entity
auditing
parameter information
municipal
bim
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311755227.2A
Other languages
Chinese (zh)
Inventor
戴龙
张辛平
齐维丽
高宏民
程雷鸣
白快
邱峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Central and Southern China Municipal Engineering Design and Research Institute Co Ltd
Original Assignee
Central and Southern China Municipal Engineering Design and Research Institute Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Central and Southern China Municipal Engineering Design and Research Institute Co Ltd filed Critical Central and Southern China Municipal Engineering Design and Research Institute Co Ltd
Priority to CN202311755227.2A priority Critical patent/CN117931865A/en
Publication of CN117931865A publication Critical patent/CN117931865A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24564—Applying rules; Deductive queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/248—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Databases & Information Systems (AREA)
  • Geometry (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Primary Health Care (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Graphics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a municipal engineering BIM intelligent drawing examination method based on deep learning, which comprises the following steps: extracting a municipal design specification set based on word segmentation technology of a deep learning network, wherein the municipal design specification set comprises a plurality of specification strips, and each specification strip comprises an auditing main body and a rule condition corresponding to the auditing main body; acquiring parameter information of each entity class from BIM model space; according to the entity category to which each entity belongs, an auditing body of a specification treaty matched with the entity category is found in the municipal design specification set; and comparing the parameter information of each entity with the standard conditions of the auditing body in the standard treaty, and determining whether the parameter information of each entity is compliant according to the comparison result to generate an aesthetic report. Compared with the existing manual drawing inspection method, the intelligent drawing inspection method provided by the invention has the advantages of higher drawing inspection speed, higher efficiency and higher drawing inspection accuracy.

Description

Deep learning-based municipal engineering BIM intelligent drawing examination method
Technical Field
The invention relates to the field of municipal engineering drawing, in particular to a municipal engineering BIM intelligent drawing method based on deep learning.
Background
The current municipal industry is mostly cooperatively inspected by a third-party drawing-examining mechanism and a design institute, is dominated by the third-party drawing-examining mechanism, mainly comprises two-dimensional drawings, and has low efficiency.
The municipal industry has low digitization degree, lacks knowledge inheritance, and the design drawing auditing workflow is an information island, lacks effective information transmission and circulation, and is unfavorable for inheritance and reservation of implicit knowledge such as drawing examination points, drawing examination experiences and the like.
Municipal industry needs many professions to cooperate and accomplish, and the specialty includes: the construction, structure, water supply and drainage, heating and ventilation, electric appliances, planning and other professions, and the construction diagram inspection is specific, the inspection standards are multiple, the regulations are complex, and the inspection is needed.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention provides a municipal BIM intelligent drawing examination method based on deep learning, which comprises the following steps:
Extracting a municipal design specification set based on word segmentation technology of a deep learning network, wherein the municipal design specification set comprises a plurality of specification strips, and each specification strip comprises an auditing main body and a rule condition corresponding to the auditing main body;
acquiring parameter information of each entity class from BIM model space;
According to the entity category to which each entity belongs, an auditing body of a specification treaty matched with the entity category is found in the municipal design specification set;
and comparing the parameter information of each entity with the standard conditions of the auditing body in the standard treaty, and determining whether the parameter information of each entity is compliant according to the comparison result to generate an aesthetic report.
On the basis of the technical scheme, the invention can also make the following improvements.
Optionally, the word segmentation technique based on the deep learning network extracts a municipal design specification set, including:
Extracting standard texts containing 'must', 'forbidden', 'should not', 'should meet the specification of the..A deep learning network', 'should execute' and compare the standard texts of the relation according to the..A auditing body and the logic judgment relation in each standard text are extracted;
All the extracted specification treatises are structured to be used as municipal design specification sets and stored in a basic library, and the basic library provides a maintenance interface through which the input of the manual structured specification treatises is supported.
Optionally, the obtaining the parameter information of each entity class from the BIM model includes:
and reading parameter information of each hung entity from the parameter attribute of the BIM model, wherein the parameter information comprises parameters of materials, fire grades and earthquake resistance grades, and identifying the length, width, height, diameter, radius, area and volume of the entity according to the geometric information of each entity.
Optionally, according to the entity category to which each entity belongs, an audit subject of the specification treaty matched with the entity category is found in the municipal design specification set, and the method further includes:
And establishing a matching relationship between the auditing main body in each rule strip and the entity category in the BIM model space by taking the Autodesk Revit as a three-dimensional graphic engine.
Optionally, according to the entity category to which each entity belongs, an audit subject of the specification treaty matched with the entity category is found in the municipal design specification set, including:
According to the entity category of each entity in the BIM model, filtering the entity category of each entity by using an API interface in a three-dimensional graphic engine and adopting a filter, finding an auditing main body matched with the entity category, and acquiring the rule condition of the auditing main body.
Optionally, the comparing the parameter information of each entity with the standard condition of the auditing body in the standard treaty, determining whether the parameter information of each entity is compliant according to the comparison result, and generating the aesthetic report includes:
If the parameter information is not in the specification range of the restraint of the auditing main body, the system carries out parameter information missing prompt or requires to complement the parameter information, and the system records the parameter information;
If the parameter information is complete and the logic constraint relation is not matched, the design of the entity is not compliant, and corresponding non-compliant information is recorded.
Optionally, the non-compliance information includes an audit result of the non-compliance entity, an original specification rule definition, an actual attribute and a design parameter of the entity in a BIM model space, and a spatial position of the non-compliance entity in the BIM model is recorded so as to locate the non-compliance entity;
And displaying the non-compliance information in the form of a problem list based on a UI mode.
Optionally, the entity categories include walls, building floors, structural floors, building columns, structural columns, stairways, doors, windows, and rebar.
The invention provides a deep learning-based municipal engineering BIM intelligent drawing method, which is based on word segmentation technology of a deep learning network and extracts a municipal design specification set, wherein the municipal design specification set comprises a plurality of specification strips, and each specification strip comprises an auditing main body and a rule condition corresponding to the auditing main body; acquiring parameter information of each entity class from BIM model space; according to the entity category to which each entity belongs, an auditing body of a specification treaty matched with the entity category is found in the municipal design specification set; and comparing the parameter information of each entity with the standard conditions of the auditing body in the standard treaty, and determining whether the parameter information of each entity is compliant according to the comparison result to generate an aesthetic report. Compared with the existing manual drawing inspection method, the intelligent drawing inspection method provided by the invention has the advantages of higher drawing inspection speed, higher efficiency and higher drawing inspection accuracy.
Drawings
FIG. 1 is a flow chart of a method for intelligent drawing examination of municipal engineering BIM based on deep learning;
fig. 2 is an overall flow diagram of a deep learning-based intelligent BIM aesthetic method for municipal works.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of each embodiment or the single embodiment provided by the invention can be combined with each other at will to form a feasible technical scheme, and the combination is not limited by the sequence of steps and/or the structural composition mode, but is necessarily based on the fact that a person of ordinary skill in the art can realize the combination, and when the technical scheme is contradictory or can not realize, the combination of the technical scheme is not considered to exist and is not within the protection scope of the invention claimed.
Fig. 1 is a flowchart of a smart map method for municipal engineering BIM based on deep learning, provided by the invention, as shown in fig. 1, and the method includes:
step 1, extracting a municipal design specification set based on word segmentation technology of a deep learning network, wherein the municipal design specification set comprises a plurality of specification strips, and each specification strip comprises an auditing main body and a rule condition corresponding to the auditing main body.
It can be understood that the invention utilizes deep learning to extract and word the strong drawing and key drawing points in the municipal engineering design specification, converts the specification into a structured natural language, and establishes a rule base for BIM model auditing from the structured specification treaty.
As an embodiment, the word segmentation technique based on the deep learning network extracts a municipal design specification set, including: extracting specification texts containing 'must', 'forbidden', 'should not', 'should meet the specification of the..the deep learning network', 'should execute' and compare the specification texts of the relation according to the..the, and extracting an audit subject in each specification text; all the extracted specification treatises are structured to be used as municipal design specification sets and stored in a basic library, and the basic library provides a maintenance interface through which the input of the manual structured specification treatises is supported.
The method comprises the steps of extracting a standard rule based on a word segmentation technology of a deep neural network, such as a cyclic neural network (RNN), a long-short-term memory network (LSTM), a two-way long-short-term memory network (BiLSTM), a transducer and other models, and obtaining an auditing body and rule conditions in the standard rule.
According to the extracted and segmented treatises, the selected and segmented treatises are used as an examination and drawing standard base library, and in order to facilitate the expansion of the examination and drawing standard base, a maintenance interface is provided by a program, so that the manual structured treatise input is supported.
And 2, acquiring parameter information of each entity class from the BIM model space.
It will be appreciated that in auditing the various components (referred to herein as entities) in the BIM model space, parameter information for each entity of each entity class needs to be obtained from the BIM model space. The entity categories include walls, building floors, structural floors, building columns, structural columns, stairs, doors, windows, steel bars and the like, for example, the walls in the BIM model are inspected, and parameter information of each wall is required to be extracted from the BIM model space, namely, the parameter information of each entity in each entity category is extracted. The method comprises the steps of reading parameter information of each hung entity from parameter attributes of a BIM model, wherein the parameter information comprises materials, fire resistance level, earthquake resistance level and the like, and identifying parameter information such as length, width, height, diameter, radius, area, volume and the like of the entity according to geometric information of each entity.
And step 3, according to the entity category to which each entity belongs, finding an auditing body of the specification treaty matched with the entity category in the municipal design specification set.
It can be appreciated that the auditors in the specification strips of the design specification set are different from the representations of the entity categories in the BIM model space, and therefore, a corresponding matching relationship between the auditors in the specification strips and the entity categories in the BIM model space needs to be established.
In the invention, an Autodesk Revit is taken as a three-dimensional graphic engine, and a matching relation between an auditing main body in a standard strip and an entity in a model space is established, for example, the type of a BIM entity corresponding to a Wall in the standard strip is Wall, and the type of a BIM entity corresponding to a Column in the standard strip is a family example (FAMILYINSTANCE and the type is Column).
And after extracting the parameter information of each entity category from the BIM model space, finding an audit subject of the specification treaty matched with the entity category in the municipal design specification set according to the entity category to which each entity belongs. Specifically, according to the entity category to which each entity belongs in the BIM model, filtering the entity category to which each entity belongs by adopting a filter in a three-dimensional graphic engine by utilizing an API interface, finding an auditing main body matched with the entity category, and acquiring rule conditions of the auditing main body.
And step 4, comparing the parameter information of each entity with the standard conditions of the auditing main body in the standard treaty, and determining whether the parameter information of each entity is compliant according to the comparison result to generate an aesthetic report.
It can be understood that if the parameter information is not in the specification range of the restraint of the auditing main body, the system carries out parameter information missing prompt or requires to complement the parameter information, and the system records the parameter information; if the parameter information is complete and the logic constraint relation is not matched, the design of the entity is not compliant, and corresponding non-compliant information is recorded.
Specifically, according to the limiting conditions, the definition main body, the numerical value rules or the attribute rules, the model conventional attributes and the geometric attributes in the specification strip, an auditing comparison rule is established according to the relation of attribute definition or comparison, if the limiting conditions are that when the beam height is more than or equal to 300, the main body is determined to be a steel bar, the diameter of the steel bar is more than or equal to 10, and the unit is a millimeter, namely, a beam (FAMILYINSTANCE) is filtered out, then a steel bar entity (Rebar) in a beam bounding box is extracted, then the diameter parameters and the numerical values of the steel bar entity are extracted, and compared and determined with the specification condition range of the steel bar entity in the specification strip, and then whether the parameter information of the steel bar entity in the BIM model meets the specification conditions is judged, if the parameter information of the steel bar entity meets the specification conditions, and if the parameter information of the steel bar entity does not meet the specification conditions, the parameter information of the steel bar entity is not compliant. When auditing the entities in the BIM model space, traversing each entity in the BIM model space, auditing each entity according to the standard conditions, recording the auditing result of each entity, and recording the non-compliance information in the most important.
The non-compliance information comprises an auditing result of a non-compliance entity, an original specification rule definition, actual attributes and design parameters of the entity in a BIM model space, and a spatial position of the non-compliance entity in the BIM model is recorded so as to position the non-compliance entity; and displaying the non-compliance information in the form of a problem list based on a UI mode, and viewing the problem list item information and the space position in an interactive mode.
Referring to fig. 2, an overall flowchart of a deep learning-based smart BIM (building information modeling) aesthetic method for municipal works is shown, firstly, municipal works specifications are carded, semantic recognition and semantic analysis are performed on the municipal works specifications based on deep learning semantic recognition, important specification treatises are extracted, the specification treatises are structured, project parameters and various entity component parameters are carded out, and the parameters are arranged into parameter rules and stored in an audit rule base. The audit rule base may provide a maintenance interface that supports manual entry of structured specification treatises.
When the BIM is input, extracting parameter information of each entity in BIM space, finding out corresponding auditing main body and standard conditions in a standard library according to the entity category of each entity, comparing the parameter information of the entity with the standard conditions, judging whether the parameter information of the entity is compliant, recording auditing results and non-compliant information of the entity, recording auditing results, original standard treaty definition of the non-compliant entity, actual attributes and design parameters of the entity in BIM space, recording the space position of the non-compliant entity in the BIM space, and displaying the space position in a list running mode, thereby facilitating personnel to check. Through BIM intelligence aesthetic drawing, can examine error, omission and conflict in the design drawing fast, accurately to improve aesthetic drawing quality and efficiency, through visual model, the design intent can be understood better by the aesthetic drawing personnel, improves the communication effect.
The municipal engineering BIM intelligent drawing examination method based on deep learning provided by the invention has the following advantages:
(1) Through BIM technology, can carry out intelligent examination to each professional model, directly output examination result, this function has improved the work efficiency of aesthetic drawing personnel to a great extent, has reduced the error rate. The traditional drawing process requires a large amount of manual investment, is time-consuming and labor-consuming and is easy to cause errors due to negligence, and by means of the BIM intelligent inspection management platform, inspection staff can rapidly and accurately complete coordination work among professions, so that the working efficiency is improved.
(2) BIM examination technology can gradually form an enterprise engineering design problem library, and municipal design quality common diseases or conditions of serious professional violations and the like can be summarized and analyzed regularly through full utilization of data resources. BIM design problem library analysis can help the BIM design problem library to know the design quality conditions of all projects of a unit, and intuitively find problems, so that 'symptomatic drug delivery'. Meanwhile, the design or the project to be designed is provided with references of the previous design results, so that the repeated occurrence of individual problems is effectively avoided, and the design quality is improved.
In general, BIM intelligent examination and drawing brings various benefits to all parties of engineering construction through high-efficiency and accurate examination capability and data analysis capability.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (8)

1. The utility model provides a municipal works BIM intelligence aesthetic drawing method based on degree of depth study which characterized in that includes:
Extracting a municipal design specification set based on word segmentation technology of a deep learning network, wherein the municipal design specification set comprises a plurality of specification strips, and each specification strip comprises an auditing main body and a rule condition corresponding to the auditing main body;
acquiring parameter information of each entity class from BIM model space;
According to the entity category to which each entity belongs, an auditing body of a specification treaty matched with the entity category is found in the municipal design specification set;
and comparing the parameter information of each entity with the standard conditions of the auditing body in the standard treaty, and determining whether the parameter information of each entity is compliant according to the comparison result to generate an aesthetic report.
2. The smart map method of municipal works BIM according to claim 1, wherein the word segmentation technique based on the deep learning network extracts a municipal design specification set, including:
Extracting standard texts containing 'must', 'forbidden', 'should not', 'should meet the specification of the..A deep learning network', 'should execute' and compare the standard texts of the relation according to the..A auditing body and the logic judgment relation in each standard text are extracted;
All the extracted specification treatises are structured to be used as municipal design specification sets and stored in a basic library, and the basic library provides a maintenance interface through which the input of the manual structured specification treatises is supported.
3. The smart map method of municipal engineering BIM according to claim 1, wherein the obtaining parameter information of each entity class from the BIM model includes:
and reading parameter information of each hung entity from the parameter attribute of the BIM model, wherein the parameter information comprises materials, fire resistance level and earthquake resistance level, and identifying the length, width, height, diameter, radius, area and volume of the entity according to the geometric information of each entity.
4. The intelligent drawing method for municipal works BIM according to claim 1, wherein according to the entity category to which each entity belongs, the auditing body of the specification treaty matched with the entity category is found in the municipal design specification set, and the method further comprises the following steps:
And establishing a matching relationship between the auditing main body in each rule strip and the entity category in the BIM model space by taking the Autodesk Revit as a three-dimensional graphic engine.
5. The intelligent drawing method for municipal engineering BIM model according to claim 3, wherein the auditing body of the specification treaty matched with the entity category is found in the municipal design specification set according to the entity category to which each entity belongs, comprising:
According to the entity category of each entity in the BIM model, filtering the entity category of each entity by using an API interface in a three-dimensional graphic engine and adopting a filter, finding an auditing main body matched with the entity category, and acquiring the rule condition of the auditing main body.
6. The intelligent drawing method for municipal engineering BIM model according to claim 1, wherein comparing the parameter information of each entity with the standard conditions of the auditing body in the standard treaty, determining whether the parameter information of each entity is compliant according to the comparison result, and generating the drawing report comprises the following steps:
If the parameter information is not in the specification range of the restraint of the auditing main body, the system carries out parameter information missing prompt or requires to complement the parameter information, and the system records the parameter information;
If the parameter information is complete and the logic constraint relation is not matched, the design of the entity is not compliant, and corresponding non-compliant information is recorded.
7. The intelligent drawing method of municipal engineering BIM according to claim 6, wherein the non-compliance information comprises an auditing result of a non-compliant entity, an original specification rule definition, actual properties and design parameters of the entity in BIM space, and the spatial position of the non-compliant entity in the BIM is recorded to locate the non-compliant entity;
And displaying the non-compliance information in the form of a problem list based on a UI mode.
8. The smart graphic method for municipal engineering BIM models according to any one of claims 1 to 7, wherein the entity categories include walls, building floors, structural floors, building columns, structural columns, stairways, doors, windows and reinforcing bars.
CN202311755227.2A 2023-12-18 2023-12-18 Deep learning-based municipal engineering BIM intelligent drawing examination method Pending CN117931865A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311755227.2A CN117931865A (en) 2023-12-18 2023-12-18 Deep learning-based municipal engineering BIM intelligent drawing examination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311755227.2A CN117931865A (en) 2023-12-18 2023-12-18 Deep learning-based municipal engineering BIM intelligent drawing examination method

Publications (1)

Publication Number Publication Date
CN117931865A true CN117931865A (en) 2024-04-26

Family

ID=90754711

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311755227.2A Pending CN117931865A (en) 2023-12-18 2023-12-18 Deep learning-based municipal engineering BIM intelligent drawing examination method

Country Status (1)

Country Link
CN (1) CN117931865A (en)

Similar Documents

Publication Publication Date Title
Zhu et al. Integration of BIM and GIS: IFC geometry transformation to shapefile using enhanced open-source approach
Peng et al. A hybrid data mining approach on BIM-based building operation and maintenance
US20210165920A1 (en) MBD-Based Three-Dimensional Process Designing Method and Platform for Typical Automobile Machined Part
CN114511202A (en) BIM-based full-period engineering project management method and platform
CA3045217A1 (en) Method for constructing a 3d digital model from a 2d plan
CN112100195B (en) IFC model change detection method based on semantic classification
Akanbi et al. Data-driven reverse engineering algorithm development method for developing interoperable quantity takeoff algorithms using IFC-based BIM
CN112818460A (en) Intelligent building rollover method from two-dimensional drawing to three-dimensional model
Jiang et al. Semantic enrichment for BIM: Enabling technologies and applications
Nepal et al. Supporting knowledge-intensive construction management tasks in BIM
CN116821223B (en) Industrial visual control platform and method based on digital twinning
CN116186831A (en) Semantic structured description and compliance inspection method and system for building engineering design
Yin et al. An automated layer classification method for converting CAD drawings to 3D BIM models
Puri et al. Toward automated dimensional quality control of precast concrete elements using design BIM
CN114626833A (en) Construction standard process supervision method, device, equipment and medium
Al-Roumi et al. Exploring the rate of adoption and implementation depth of building information modeling (BIM): A case of Kuwait
CN114048535A (en) System and method for generating door and window in CAD wall map layer during map construction
CN117931865A (en) Deep learning-based municipal engineering BIM intelligent drawing examination method
CN115577526B (en) Customized building information model construction method for pedestrian traffic modeling
Wang et al. On intelligent fire drawings review based on building information modeling and knowledge graph
CN116663100A (en) Engineering data calling method and system based on intelligent construction technology
Cocco et al. From rubbles to digital material bank. A digital methodology for construction and demolition waste management in post-disaster areas
CN115577424A (en) Method, device, equipment and storage medium for calculating construction engineering quantity
CN114065344A (en) Automatic modeling method based on OSG and CAD building plan
CN114201544A (en) Early warning analysis method and device for economic contract abnormal data of natural gas enterprise

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination