CN109711099B - BIM automatic modeling system based on image recognition machine learning - Google Patents
BIM automatic modeling system based on image recognition machine learning Download PDFInfo
- Publication number
- CN109711099B CN109711099B CN201910061408.2A CN201910061408A CN109711099B CN 109711099 B CN109711099 B CN 109711099B CN 201910061408 A CN201910061408 A CN 201910061408A CN 109711099 B CN109711099 B CN 109711099B
- Authority
- CN
- China
- Prior art keywords
- information
- data
- bim
- component
- engineering
- 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.)
- Active
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 26
- 238000013461 design Methods 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000012795 verification Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 210000001503 joint Anatomy 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000006698 induction Effects 0.000 claims abstract description 5
- 230000008520 organization Effects 0.000 claims abstract description 5
- 238000013075 data extraction Methods 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000000295 complement effect Effects 0.000 claims description 4
- 238000003032 molecular docking Methods 0.000 claims description 4
- 239000010426 asphalt Substances 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims description 2
- 239000004568 cement Substances 0.000 claims description 2
- 238000003066 decision tree Methods 0.000 claims description 2
- 230000005662 electromechanics Effects 0.000 claims description 2
- 230000002068 genetic effect Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 238000007477 logistic regression Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 claims description 2
- 230000004048 modification Effects 0.000 claims description 2
- 238000007637 random forest analysis Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 4
- 239000013589 supplement Substances 0.000 claims 1
- 206010063385 Intellectualisation Diseases 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a BIM automatic modeling system based on image recognition machine learning, which effectively solves the problems of automation and intellectualization of BIM technical modeling of engineering projects, geometric characteristics and attribute characteristics of corresponding components related in the current highway engineering design specification, data acquisition and determination information extraction range and characteristic matching in the data processing image recognition process; data acquisition is carried out according to the extraction range and the organization form, preliminary induction and arrangement are carried out according to the specialties of roadbeds, pavements, bridges, culverts and tunnels, data processing is carried out, and data butt joint is supplemented; fusing corresponding terrain and geological information according to the component characteristic information and the correlation information among the components, and intelligently generating a BIM (building information modeling) model of a corresponding engineering entity; and (4) exporting attribute information of key parts, important parts and complex parts of the BIM, carrying out inverse calculation verification on the attribute information and corresponding information extracted from the original drawing, and quickly positioning the position of a model component. The invention is easy to install and use, and reduces the labor, time and economic cost.
Description
Technical Field
The invention relates to the field of BIM technology modeling automation and intelligence, in particular to a BIM automatic modeling system based on image recognition machine learning.
Background
Years of development practice of the BIM technology proves that: the BIM technology has been and will continue to lead the information revolution in the engineering construction field, and with the gradual deepening of the application of the BIM technology, the traditional architecture in the engineering construction field will be broken, and a new architecture taking the information technology as the leading factor will be replaced. The BIM model as a carrier for bearing information technology endows the engineering entity with digital life, is the core for realizing one-module-multiple-use, one-module-to-one-key management in the engineering construction field, and is the basis for comprehensively knowing the 'foreignness' and 'appearance and inner core' of the engineering entity.
Based on the above consensus, the engineering construction informatization field is also promoted at present according to the principle of BIM model advance, and is only not deeply applied to the whole life cycle of engineering projects and the operation and maintenance management of existing engineering entities at home, and the reason is mainly shown as follows: on one hand, currently, the popular BIM modeling software in China is mainly made by foreign manufacturers, such as Autodesk and Bentley, and the foreign software manufacturers have strong fine modeling capability, but are relatively lack of combination with the actual Chinese engineering, and particularly come from the integration in the aspects of specifications, standards and management modes. On the other hand, due to the fact that design cost is low, change is frequent and management modes are rough in the construction process of domestic engineering projects, design quality and design depth of BIM models of design houses are limited, domestic relevant BIM technology software manufacturers and consulting companies mostly stay in the stage of how to live, research on BIM technology modeling automation and intellectualization is not deeply advanced on the premise that the BIM models are fine, and therefore, on the premise that the BIM models are fine, the BIM technology modeling automation and intellectualization are not reported publicly.
Disclosure of Invention
In view of the above situation, in order to overcome the defects of the prior art, the present invention aims to provide a BIM automatic modeling system based on image recognition machine learning, which can effectively solve the problems of automation and intellectualization of engineering project BIM technology modeling.
The technical scheme of the invention is that the BIM automatic modeling system based on image recognition machine learning integrates image recognition and character recognition by a scanner, and automatically extracts corresponding modeling information required by a platform from a drawing:
(1) Engineering design feature library (module): the feature library comprises geometric features and attribute features of corresponding components related in the current highway engineering design specification and is used for determining the information extraction range by a data acquisition (module) and matching the features in the image recognition process by a data processing (module);
(2) Data acquisition (module): the data acquisition is carried out according to the information extraction range and the organization form determined by the system engineering design feature library and according to the specialties of roadbeds, pavements, bridges, culverts and tunnels, the initial induction and the arrangement are carried out; the data acquisition (module) supports file import, drawing scanning and voice remark data acquisition modes;
(3) Data processing (module): the data processing comprises data extraction, data analysis and machine learning (sub-modules), (1) the data extraction sub-module is used for comparing and extracting effective information of the data information acquired by the data acquisition module according to a characteristic library which is built in the system and embodies engineering design specifications and standards; (2) the data analysis sub-module takes the characteristic information corresponding to each component as a basic sample, matches the target data sample obtained by the data acquisition module, and automatically identifies the corresponding component and the effective characteristic information and attribute information thereof through the matching of the basic characteristic and the exclusive characteristic; (3) the machine learning submodule analyzes the collected data by an algorithm, learns from the engineering design characteristic library and then makes a decision or forecast on the collected various drawing information. The system is used for collecting the characteristic information of the components which cannot be matched with the system engineering design characteristic library, adding the characteristic information into the system engineering design characteristic library and automatically identifying similar pattern information in the follow-up process;
(4) Complementary data interfacing (module): the method comprises the following steps: the method comprises the following steps that (1) topographic and geological environment data related to highway engineering not only have operation, maintenance and transformation data of engineering entities, but also are subjected to data extraction through the butt joint of the environment data and a GIS (geographic information system);
(5) BIM model generation (Module): fusing corresponding terrain and geological information according to the analyzed component characteristic information and the association information among the components, and intelligently generating a BIM (building information modeling) model of a corresponding engineering entity;
(6) Key component validation (module): attribute information of key parts, important parts and complex parts of the generated BIM is exported, and inverse calculation verification is carried out on the attribute information and corresponding information extracted from the original drawing, so that the matching performance and effectiveness of the generated BIM and the original drawing are ensured;
(7) BIM model search (module): the method is used for quickly positioning the position of the model component, and the searching mode supports accurate matching and fuzzy searching according to the component name, the component code, the component characteristic information, the component attribute information, the component material information, the pile number, the elevation and the three-dimensional GIS coordinate.
The system is simple, easy to install and use, can effectively solve the problems of automation and intellectualization of BIM technical modeling of engineering projects, has high working efficiency and low labor intensity, realizes quick intelligent automatic modeling, provides technical guarantee for quick modeling of a large number of existing engineering entities, greatly reduces the labor, time and economic cost of information construction of the existing BIM technical, and has remarkable economic and social benefits.
Drawings
FIG. 1 is a block diagram of the system of the present invention.
FIG. 2 is a diagram illustrating data relationships of the system of the present invention.
Detailed Description
The following detailed description of the embodiments of the invention refers to the accompanying drawings and detailed description.
As shown in fig. 1, the BIM automatic modeling system based on image recognition machine learning of the present invention integrates image recognition and character recognition by a scanner, and automatically extracts corresponding modeling information required by a platform from a drawing:
(1) Engineering design feature library: the feature library comprises geometrical features and attribute features of corresponding components related in the current highway engineering design specifications and is used for acquiring and determining information extraction range and performing feature matching in the data processing image recognition process;
the design specification is highway engineering, includes: the design method comprises the following steps of establishing sub-libraries for classification and penetration in a feature library according to the specialties of roadbed, road surface, bridge, culvert, tunnel and traffic administration in the feature library, wherein the design specifications of highway roadbed (JTG D30-2015), highway cement concrete pavement design specifications (JTG D40-2011), highway asphalt pavement design specifications (JTG D50-2017), highway bridge and culvert design general specifications (JTGD 60-2015), highway tunnel design detailed rules (JTGTD 70-2010) and highway traffic engineering and facility design general specifications along the line (JTGD 80-2006);
(2) And data acquisition: the data acquisition is carried out according to the information extraction range and the organization form determined by the system engineering design feature library and preliminary induction and sorting according to the specialties of roadbeds, pavements, bridges, culverts and tunnels; the data acquisition supports file import, drawing scanning and voice remark data acquisition modes;
the file import does not need to select the design professional type corresponding to the imported file, the system completes automatic matching by identifying the data information and the image information in the file, and supports various file, picture and graphic file forms such as WORD, PDF, JPG, PNG and DWG; the method comprises the following steps that drawing scanning utilizes an external scanner integrated with image recognition and character recognition to automatically extract required data information after a tangible drawing is scanned, and the required data information is added to a system for data processing; the voice remarks are used for inputting supplementary information through manual intervention in a voice recognition mode for individual data information which is not a perfect drawing file and data information which cannot be classified or is wrongly classified by a system;
(3) And data processing: the data processing comprises data extraction, data analysis and machine learning, (1) data extraction is used for comparing and extracting effective information of data information acquired by data acquisition according to a characteristic library which is built in a system and embodies engineering design specifications and standards as a sample; (2) data analysis, namely matching a target data sample obtained by data acquisition according to the characteristic information corresponding to each component as a basic sample, and automatically identifying the corresponding component and effective characteristic information and attribute information thereof through matching of basic characteristics and exclusive characteristics; (3) machine learning, analyzing the acquired data by using an algorithm, combining an engineering design feature library to learn, then making a decision or prediction on the acquired various drawing information, and acquiring feature information of components which cannot be matched with the system engineering design feature library, adding the acquired feature information into the system engineering design feature library, and subsequently automatically identifying similar pattern information;
(4) And complementary data docking: the method comprises the following steps: the method comprises the following steps that (1) topographic and geological environment data related to highway engineering not only have operation, maintenance and transformation data of engineering entities, but also are subjected to data extraction through the butt joint of the environment data and a GIS (geographic information system);
the operation, maintenance and modification data of the engineering entity is subjected to data extraction through the butt joint of a network and a corresponding operation and maintenance system, and if the data can not be butted through the network, the data of the corresponding operation and maintenance system is exported and then manually imported into the system to realize the butt joint of the data;
(5) And generating a BIM model: fusing corresponding terrain and geological information according to the analyzed component characteristic information and the association information among the components, and intelligently generating a BIM (building information modeling) model of a corresponding engineering entity;
the component feature information includes, but is not limited to, geometric information, positional information, material or material information; the associated information includes but is not limited to elevation, origin-destination pile number, offset angle;
(6) Verifying key components: attribute information of key parts, important parts and complex parts of the generated BIM is exported, and inverse calculation verification is carried out on the attribute information and corresponding information extracted from the original drawing, so that the matching performance and effectiveness of the generated BIM and the original drawing are ensured;
(7) And searching a BIM model: the method is used for quickly positioning the position of the model component, and the searching mode supports accurate matching and fuzzy searching according to the component name, the component code, the component characteristic information, the component attribute information, the component material information, the stake number, the elevation and the three-dimensional GIS coordinate.
As shown in fig. 2, in order to ensure the use effect and the convenience of use, the engineering design feature library is used as a basic information database to provide corresponding data interaction directions, criteria and ranges for other modules so as to ensure the validity of data transmission, wherein data acquisition and supplementary data are connected in a butt joint manner to form a data input interface; the data processing and the BIM model generation complement each other, the basic information of the engineering design feature library and the data input interface are combined to obtain effective information, and a corresponding component model is generated through a parameterized automatic modeling tool and is intelligently spliced; and checking a final model generated and output by the BIM through key component verification and BIM model search so as to ensure the matching and effectiveness of the generated BIM and the original drawing.
The design specifications integrated in the engineering design feature library module preferably include professional design specifications of roads, buildings, municipal works, water conservancy projects, railways, electromechanics, civil aviation airports and the like, but are not limited to the above;
the algorithms related in the machine learning submodule preferably include classical machine learning algorithms such as decision trees, random forests, logistic regression, adaboost and neural networks, but are not limited thereto;
the back calculation verification method related in the key component verification module preferably includes, but is not limited to, a graph method and a regression formula method, an iterative method, a database search method, a genetic algorithm, an artificial neural network method and other classical back calculation methods.
It should be noted that the above-mentioned embodiments are only examples, and are not intended to limit the scope of the present invention, and all technical solutions substantially identical to the technical solutions of the present invention, which are made by using equivalent and equivalent alternative technical means, belong to the scope of the present invention.
The system has the advantages of simple structure, novelty, uniqueness, easy installation and use, good effect, capability of effectively solving the problems of automation and intellectualization of engineering project BIM technical modeling, very good effect through field test and application, and the following outstanding advantages compared with the prior art:
1. by repeatedly analyzing and summarizing the existing design standards, specifications and drawings through machine learning, more than 90% of three-dimensional models can be automatically generated by the system;
2. the modeling efficiency is improved by more than 3 times while the modeling accuracy is ensured, and the repeated labor and error opportunities in the modeling process are reduced;
3. the design base library of complex shapes and structure families is realized, and the complex modeling work of variable cross-section continuous beams, special-shaped components and the like is automatically generated by combining spatial structures and geographic information;
4. the rapid collaborative design among all the professions is realized, only the model creation of the professions needs to be considered in all the professions, and the butt joint among the professions is automatically related by the system through information such as position, elevation and the like and can be manually adjusted;
5. the method realizes rapid intelligent automatic modeling, provides technical guarantee for rapid modeling of a large number of existing engineering entities, greatly reduces labor, time and economic cost of information construction of the existing working BIM technology, can save more than 60% of labor, shorten more than 60% of time and save more than 50% of cost, is a great innovation, and has remarkable economic and social benefits.
Claims (6)
1. The BIM automatic modeling system based on image recognition machine learning is characterized in that the system integrates image recognition and character recognition by a scanner, extracts corresponding modeling information required by a platform from a drawing:
(1) Engineering design feature library: the feature library comprises geometric features and attribute features of corresponding components related in the current highway engineering design specification and is used for data acquisition, information extraction range determination and feature matching in the data processing image recognition process;
(2) And data acquisition: the data acquisition is carried out according to the information extraction range and the organization form determined by the system engineering design feature library and according to the specialties of roadbeds, pavements, bridges, culverts and tunnels, the initial induction and the arrangement are carried out; the data acquisition supports file import, drawing scanning and voice remark data acquisition modes;
(3) And data processing: the data processing comprises data extraction, data analysis and machine learning, (1) data extraction is used for comparing and extracting effective information of data information acquired by data acquisition according to a characteristic library which is built in a system and embodies engineering design specifications and standards as a sample; (2) data analysis, namely matching a target data sample obtained by data acquisition according to characteristic information corresponding to each component as a basic sample, and automatically identifying the corresponding component and effective characteristic information and attribute information thereof through matching of basic characteristics and exclusive characteristics; (3) machine learning, namely analyzing the acquired data by using an algorithm, combining an engineering design feature library, learning from the data, then making a decision or prediction on the acquired various drawing information, and carrying out feature information acquisition on components which cannot be matched with the system engineering design feature library, adding the acquired component to the system engineering design feature library, and subsequently automatically identifying similar pattern information;
(4) And complementary data docking: the method comprises the following steps: the environmental data of the landform and geology related to the highway engineering not only has the data of operation, maintenance and reconstruction of engineering entities, but also carries out data extraction by butting the environmental data with a GIS system;
(5) And generating a BIM model: fusing corresponding terrain and geological information according to the analyzed component characteristic information and the association information among the components, and intelligently generating a BIM (building information modeling) model of a corresponding engineering entity;
(6) Verifying key components: attribute information of key parts, important parts and complex parts of the generated BIM is exported, and inverse calculation verification is carried out on the attribute information and corresponding information extracted from the original drawing, so that the matching performance and effectiveness of the generated BIM and the original drawing are ensured;
(7) And searching a BIM model: the method is used for quickly positioning the position of the model component, and the searching mode supports accurate matching and fuzzy searching according to the component name, the component code, the component characteristic information, the component attribute information, the component material information, the pile number, the elevation and the three-dimensional GIS coordinate.
2. The BIM automatic modeling system based on image recognition machine learning of claim 1, characterized in that the system integrates image recognition and character recognition by scanner, extracts the corresponding modeling information needed by platform from drawing:
(1) Engineering design feature library: the feature library comprises geometrical features and attribute features of corresponding components related in the current highway engineering design specifications and is used for acquiring and determining information extraction range and performing feature matching in the data processing image recognition process;
the design specification is highway engineering, includes: the design specifications of a highway subgrade design specification (JTG D30-2015), a highway cement concrete pavement design specification (JTG D40-2011), a highway asphalt pavement design specification (JTG D50-2017), a highway bridge and culvert design general specification (JTGD 60-2015), a highway tunnel design detailed rule (JTGTD 70-2010) and a highway traffic engineering and along-line facility design general specification (JTGD 80-2006) are established, and the specifications are classified and communicated according to subgrades, pavements, bridges, culverts, tunnels and crossing construction major building sub-libraries in a feature library;
(2) And data acquisition: the data acquisition is carried out according to the information extraction range and the organization form determined by the system engineering design feature library and according to the specialties of roadbeds, pavements, bridges, culverts and tunnels, the initial induction and the arrangement are carried out; the data acquisition supports file import, drawing scanning and voice remark data acquisition modes;
the file import does not need to select the design professional type corresponding to the imported file, the system completes automatic matching by identifying the data information and the image information in the file, and supports multiple file, picture and graphic file forms of WORD, PDF, JPG, PNG and DWG; the method comprises the following steps that drawing scanning utilizes an external scanner integrated with image recognition and character recognition to automatically extract required data information after a tangible drawing is scanned, and the required data information is added to a system for data processing; the voice remarks are used for inputting supplementary information through manual intervention in a voice recognition mode for individual data information which is not a perfect drawing file and data information which cannot be classified or is wrongly classified by a system;
(3) And data processing: the data processing comprises data extraction, data analysis and machine learning, (1) the data extraction is used for comparing and extracting effective information of data information acquired by data acquisition according to a characteristic library which is built in a system and embodies engineering design specifications and standards as a sample; (2) data analysis, namely matching a target data sample obtained by data acquisition according to the characteristic information corresponding to each component as a basic sample, and automatically identifying the corresponding component and effective characteristic information and attribute information thereof through matching of basic characteristics and exclusive characteristics; (3) machine learning, analyzing the acquired data by using an algorithm, combining an engineering design feature library to learn, then making a decision or prediction on the acquired various drawing information, and acquiring feature information of components which cannot be matched with the system engineering design feature library, adding the acquired feature information into the system engineering design feature library, and subsequently automatically identifying similar pattern information;
(4) And supplementary data docking: the method comprises the following steps: the environmental data of the landform and geology related to the highway engineering not only has the data of operation, maintenance and reconstruction of engineering entities, but also carries out data extraction by butting the environmental data with a GIS system;
the operation, maintenance and modification data of the engineering entity is subjected to data extraction through the butt joint of a network and a corresponding operation and maintenance system, and if the data can not be butted through the network, the data of the corresponding operation and maintenance system is exported and then manually imported into the system to realize the butt joint of the data;
(5) And generating a BIM model: fusing corresponding terrain and geological information according to the analyzed component characteristic information and the association information among the components, and intelligently generating a BIM model of a corresponding engineering entity;
the component feature information includes, but is not limited to, geometric information, positional information, material or material information; the associated information includes but is not limited to elevation, origin-destination pile number, offset angle;
(6) Verifying key components: attribute information of key parts, important parts and complex parts of the generated BIM is exported, and inverse calculation verification is carried out on the attribute information and corresponding information extracted from the original drawing, so that the matching performance and effectiveness of the generated BIM and the original drawing are ensured;
(7) And searching a BIM model: the method is used for quickly positioning the position of the model component, and the searching mode supports accurate matching and fuzzy searching according to the component name, the component code, the component characteristic information, the component attribute information, the component material information, the pile number, the elevation and the three-dimensional GIS coordinate.
3. The BIM automatic modeling system based on image recognition machine learning of claim 1, wherein the engineering design feature library is used as a basic information database to provide corresponding data interaction direction, criterion and range for other modules to ensure the validity of data transmission, wherein data acquisition and supplementary data docking together form a data input interface; the data processing and the BIM model generation supplement each other, the basic information of the engineering design feature library and the data input interface are combined to obtain effective information, and a corresponding component model is generated through a parameterized automatic modeling tool and is intelligently spliced; and checking a final model generated and output by the BIM through key component verification and BIM model search so as to ensure the matching and effectiveness of the generated BIM and the original drawing.
4. The BIM automatic modeling system based on image recognition machine learning of claim 1, wherein the design specifications integrated into the engineering design feature library are design specifications for highways, buildings, municipalities, water conservancy, railways, electromechanics, civil aviation airports.
5. The BIM automatic modeling system based on image recognition machine learning of claim 1, characterized in that the algorithm involved in machine learning is a machine learning algorithm of decision tree, random forest, logistic regression, adaboost and neural network.
6. The BIM automatic modeling system based on image recognition machine learning as claimed in claim 1, wherein the key component verification involves back calculation verification methods of graph method and regression formula method, iterative method, database search method, genetic algorithm and artificial neural network method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061408.2A CN109711099B (en) | 2019-01-23 | 2019-01-23 | BIM automatic modeling system based on image recognition machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061408.2A CN109711099B (en) | 2019-01-23 | 2019-01-23 | BIM automatic modeling system based on image recognition machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109711099A CN109711099A (en) | 2019-05-03 |
| CN109711099B true CN109711099B (en) | 2022-10-04 |
Family
ID=66262532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910061408.2A Active CN109711099B (en) | 2019-01-23 | 2019-01-23 | BIM automatic modeling system based on image recognition machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711099B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335247B (en) * | 2019-05-30 | 2021-12-10 | 广东省机场管理集团有限公司工程建设指挥部 | BIM (building information modeling) -based defect positioning method, device, equipment and storage medium |
| CN110334924B (en) * | 2019-06-21 | 2023-04-07 | 中交二公局第三工程有限公司 | BIM-based computer aided design and construction integrated management system and method |
| GB201913406D0 (en) * | 2019-09-17 | 2019-10-30 | Peregrine Tech Holdings Limited | Recycling of flat panel displays |
| CN112700529A (en) * | 2019-10-07 | 2021-04-23 | 奥比塞德技术公司 | Method and system for generating three-dimensional model according to standard document |
| CN111079209B (en) * | 2019-12-12 | 2023-04-11 | 上海建工五建集团有限公司 | Building modeling method and system based on intelligent voice recognition |
| CN111523167A (en) * | 2020-04-17 | 2020-08-11 | 平安城市建设科技(深圳)有限公司 | BIM model generation method, device, equipment and storage medium |
| CN112257162A (en) * | 2020-10-29 | 2021-01-22 | 中国十七冶集团有限公司 | Railway underpass frame box culvert jacking construction method based on BIM technology |
| CN114612924B (en) * | 2022-02-18 | 2024-11-22 | 中国建筑第八工程局有限公司 | A rapid modeling method based on BIM technology |
| CN114840900B (en) * | 2022-05-18 | 2023-06-20 | 滁州学院 | A method for automatic generation of generative BIM components based on i-GBDT technology |
| CN114757661B (en) * | 2022-06-13 | 2022-08-16 | 中国建筑西南设计研究院有限公司 | Automatic refining method and system of BIM (building information modeling) model, electronic equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989198A (en) * | 2015-01-29 | 2016-10-05 | 中交宇科（北京）空间信息技术有限公司 | BIM-based (building information modeling based) road parametric auto-modeling method and system |
| CN106777680A (en) * | 2016-12-14 | 2017-05-31 | 华中科技大学 | A kind of existing bridge fast B IM modelings and method |
| CN108665248A (en) * | 2018-08-17 | 2018-10-16 | 住房和城乡建设部科技发展促进中心 | BIM-based building information integrated management system and construction method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8818932B2 (en) * | 2011-02-14 | 2014-08-26 | Decisive Analytics Corporation | Method and apparatus for creating a predictive model |
-
2019
- 2019-01-23 CN CN201910061408.2A patent/CN109711099B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989198A (en) * | 2015-01-29 | 2016-10-05 | 中交宇科（北京）空间信息技术有限公司 | BIM-based (building information modeling based) road parametric auto-modeling method and system |
| CN106777680A (en) * | 2016-12-14 | 2017-05-31 | 华中科技大学 | A kind of existing bridge fast B IM modelings and method |
| CN108665248A (en) * | 2018-08-17 | 2018-10-16 | 住房和城乡建设部科技发展促进中心 | BIM-based building information integrated management system and construction method |
Non-Patent Citations (2)
| Title |
|---|
| BIM模型智能检查工具研究与应用;张荷花等;《土木建筑工程信息技术》;20180415(第02期);全文 * |
| 基于BIM的公路全寿命周期管理平台构建与应用;刘向阳等;《公路》;20160825(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109711099A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711099B (en) | BIM automatic modeling system based on image recognition machine learning | |
| CN112052547B (en) | An automatic generation method of urban road network based on artificial intelligence | |
| CN102521973B (en) | A kind of mobile phone switches the road matching method of location | |
| CN110782154A (en) | Construction plan management system based on BIM + GIS | |
| Qin et al. | Automated reconstruction of parametric bim for bridge based on terrestrial laser scanning data | |
| CN109635748B (en) | Method for extracting road characteristics in high-resolution image | |
| Wang et al. | Quality analysis of open street map data | |
| CN111899343A (en) | Traffic dispersion method in municipal engineering based on BIM technology | |
| Ariyachandra et al. | Detection of railway masts in airborne LiDAR data | |
| CN110298768B (en) | Road and bridge maintenance auxiliary decision-making system and maintenance method based on BIM and GIS | |
| CN109993064B (en) | Method for extracting connection path between road network nodes in picture | |
| CN111062958B (en) | Urban road element extraction method | |
| CN117036939B (en) | A method for identifying urban functional areas based on multi-source data collaboration based on graph convolutional networks | |
| CN112231799A (en) | BIM-based rapid modeling method for intelligent line selection and trend scheme of railway | |
| CN112733781A (en) | City functional area identification method combining POI data, storage medium and electronic equipment | |
| CN115391882A (en) | Construction method of multivariate data fusion holographic space system | |
| Jiang et al. | Building demolition estimation in urban road widening projects using as-is BIM models | |
| CN115619275B (en) | Ecological restoration decision method and device for railway engineering | |
| CN106855865B (en) | Water conservancy and hydropower big data architecture construction method | |
| KR102483722B1 (en) | BIM model building system and information provision method for building coded digital exterior network diagram using CATIA | |
| Soilán et al. | Deep Learning-Based Road Segmentation of 3D Point Clouds for Assisting Road Alignment Parameterization | |
| CN113569946A (en) | Open source map and professional data source road network adaptive matching method | |
| CN118196028A (en) | An improved YOLOv8 method for extracting rural cement pavement defects | |
| Tibaut et al. | BIM-based parametric modeling of roads and infrastructure objects | |
| CN112465072B (en) | Excavator image recognition method based on YOLOv4 model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 450046 No.9 Zeyu street, Zhengdong New District, Zhengzhou City, Henan Province Patentee after: Henan Zhonggong Design and Research Institute Group Co.,Ltd. Country or region after: China Address before: 450046 No.9 Zeyu street, Zhengdong New District, Zhengzhou City, Henan Province Patentee before: HENAN PROVINCIAL COMMUNICATIONS PLANNING & DESIGN INSTITUTE Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |