A building digital twin model and modeling method based on semantic Web technology

Abstract

The present invention provides a building digital twin framework and modeling method based on semantic Web technology. The building digital twin framework includes physical space entities, virtual space models and associated databases, wherein the physical space entities provide building entity source data for the digital twin framework, the virtual space models are used to virtualize and abstract building resources, and the associated database provides data drive for framework operation based on the semantic function of the model. The associated database includes two relational databases for monitoring time series and structural analysis and three RDF models for monitoring, building information and structural analysis. By jointly querying data of RDF models in the same field and corresponding relational databases and establishing mapping relationships at the ontology level for RDF models in different fields, matching updates and real-time interactions of information flows of the digital twin framework are promoted, and by jointly querying and checking the consistency of measured responses and simulation results, the virtual-to-real mapping function of the model is verified at the data level.

Description

Technical Field

[0001] The present invention relates to the technical field of building structure digital twin modeling and construction digitization, and in particular to a building digital twin model and a modeling method based on semantic Web technology. Background Art

[0002] With the rapid development of computer science and technology, the technological wave of Industry 4.0 has swept across all walks of life in recent years. Therefore, the society's call for the digitization and intelligence of the construction industry has also been growing. It is under this circumstance that digital twins, as the core technology of Industry 4.0, have gradually been understood and actively explored by building structure practitioners.

[0003] The digital twin framework is a multi-dimensional and multi-scale model architecture that comprehensively considers the physical status of building assets, sensor network data updates, and data integration of all parties and stages of the project. The model uses advanced technologies such as IoT, big data, and cloud computing to achieve real-time mapping of building entities in real physical space, thereby simulating and simulating the entire life cycle of the building in the virtual network space. Through the digital twin framework, users can monitor and analyze the real-time status of physical entities, and apply numerical simulation and artificial intelligence algorithms to make regulatory decisions, thereby effectively managing the entire life cycle of building objects. After the introduction of digital twins into the field of building structures, big data modeling and management, heterogeneous data and model integration, and automatic decision-making algorithm development issues restrict the promotion and application of this technology. In essence, the lack of interoperability of conventional digital twin frameworks is the fundamental reason why it is difficult to be widely adopted. Therefore, digital twin modeling and big data integration management for multi-source heterogeneous data in the construction industry have become key research issues for this technology. Summary of the invention

[0004] In view of the defects in the prior art, the object of the present invention is to provide a high-fidelity, data-dynamically interactive building digital twin model and modeling method based on semantic Web technology.

[0005] To solve the above problems, the technical solution of the present invention is:

[0006] A building digital twin model based on semantic Web technology includes a physical space entity, a virtual space model and an associated database, wherein the physical space entity provides building entity source data for a digital twin framework, the virtual space model is used to virtualize and abstract building resources, and the associated database provides data drive for framework operation based on the semantic function of the model. The associated database includes two relational databases for monitoring time series and structural analysis and three RDF models for monitoring, building information and structural analysis. By jointly querying data of RDF models in the same field and corresponding relational databases and establishing mapping relationships at the ontology level for RDF models in different fields, the matching update and real-time interaction of the information flow of the entire digital twin framework are promoted, and the virtual-to-real mapping function of the model is verified at the data level through joint query and consistency check of measured responses and simulation results.

[0007] Optionally, the physical space entity information is collected through airborne 3D lidar scanning technology and a structural monitoring system, and the geometric configuration, building environment, and structural status-related data of the on-site building entity are sent to cyberspace via wireless transmission for digital twin virtual modeling.

[0008] Optionally, the virtual space model is composed of a point cloud model, a building information model, an engineering structure analysis model and ontology models of various fields.

[0009] Furthermore, the present invention also provides a method for modeling a building digital twin model based on semantic Web technology, the method comprising the following steps:

[0010] Create an initial 3D building information model based on the architectural design plan;

[0011] Use the point cloud model to modify the initial building information model and convert the model into a structural analysis model;

[0012] Acquire monitoring system information and store it in the database, and use the knowledge storage function of the semantic Web to store multi-source heterogeneous data of the project into the knowledge base;

[0013] The knowledge extraction function of the semantic Web is used to realize the joint query of the time series database, obtain the actual load information of the structure and modify the finite element model;

[0014] The structural analysis calculation results are stored in the database, and the RDF model in the structural analysis field is updated to achieve dynamic matching of simulation results;

[0015] The measured and simulated results of the associated query structure response are used to verify the virtual-real mapping of the digital twin framework using the consistency check algorithm.

[0016] Optionally, the step of creating an initial three-dimensional building information model according to the architectural design plan specifically includes: using Revit or ArchiCAD to create a three-dimensional model according to the geometric configuration, building materials, and site environment information given in the project design plan.

[0017] Optionally, the step of using the point cloud model to correct the initial building information model and converting the model to generate a structural analysis model specifically includes: converting the data obtained by laser scanning into a point cloud model, comparing the point cloud model with the initial building information model and correcting the building information model, and converting the corrected model into an IFC model and importing it into the structural analysis engineering application software to obtain an initial finite element model.

[0018] Optionally, the step of acquiring monitoring system information and storing it in a database, and using the semantic Web knowledge storage function to store the multi-source heterogeneous data of the project into the knowledge base specifically includes the following steps:

[0019] Establish a corresponding database according to the monitoring indicator system of the monitoring system, and use MySQL relational database to record the data of monitoring indicators in the form of multiple tables.

[0020] According to the SSN ontology framework and the sensor network layout, a custom SSN ontology model is established, and an ontology model suitable for the structural analysis field is developed according to the building structure form, structural analysis reference and structural monitoring scheme;

[0021] The corresponding RDF models are generated using the custom SSN ontology, structural analysis ontology and IfcOWL ontology, and stored in the knowledge base in the form of triples.

[0022] Optionally, the step of using the semantic Web knowledge extraction function to realize joint query of the time series database to obtain the actual load information of the structure to correct the finite element model specifically includes: determining the actual actions and loads on the structure through SQL and SPARQL joint query, and then replacing the assumed values ​​of the FEA model based on the design data with the measured parameter values, thereby mapping the stress state of the physical space structure to the virtual model, thereby realizing the correction of the initial finite element model.

[0023] Optionally, the step of storing the structural analysis calculation results in a database and updating the structural analysis field RDF model to achieve dynamic matching of simulation results specifically includes: determining key calculation indicators according to the building structure form, and establishing a corresponding relational database based on this for multi-table associated storage, and then associating the structural analysis RDF model with the data of the calculation results, and automatically completing the RDF model update through preset data query and model parameter modification algorithms.

[0024] Optionally, the measured and simulated results of the associated query structure response use a consistency check algorithm to verify the virtual-to-reality mapping of the digital twin framework, and the specific steps include: applying associated data technology to access, integrate and interoperate the sensor network RDF model and the structural analysis RDF model across data sources, determining the matching monitoring data and simulation results through a joint query of knowledge and data, and performing a consistency check on the two to verify the virtual-to-reality mapping function of the digital twin framework.

[0025] Compared with the existing technology, the present invention aims to apply semantic Web technology to realize the mutual transmission, transformation and interoperation between physical space measured data, general building information model and structural analysis model, so as to generate a high-fidelity digital twin framework architecture. The present invention uses semantic Web technology to realize the unified expression and integrated interaction of multi-source heterogeneous information at the data level, and provides a semantic interoperability development and integration environment for subsequent artificial intelligence algorithms and platform service function algorithms.

[0026] The present invention has the following advantages:

[0027] 1. Use 3D laser scanning technology to modify the initial building information model, map the real physical space structure geometry to the virtual space in a more achievable way, and improve the model fidelity;

[0028] 2. The modified building information model is directly converted into a finite element simulation model to avoid human errors in the finite element modeling process. In addition, the semantic Web technology is used to apply the actual effects on the structure to the simulation model to achieve real-time mapping of the physical state of the structure;

[0029] 3. Use ontology modeling technology to convert three types of computer-unrecognizable information, IFC, FEA, and sensor networks, into machine-understandable RDF models to enrich the semantics of the digital twin framework;

[0030] 4. Using RDF model as the link for consistency check of monitoring data and simulation results, it can realize the association query and interoperability of heterogeneous data sources;

[0031] 5. The established semantic digital twin framework not only reflects the virtual-real mapping in 3D modeling, but also verifies its real-time matching of the entity status of the physical space at the data source level through linked data technology;

[0032] 6. The modeling method of the present invention is not only suitable for creating a digital twin framework for the field of structural analysis, but can also be extended to other fields such as building energy analysis, building performance analysis, structural safety analysis, etc. through the replacement of the ontology model, and has universality and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0034] Figure 1 A schematic diagram of the architecture of a building digital twin model based on semantic Web technology provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of the underlying data flow of a building digital twin model based on semantic Web technology provided in an embodiment of the present invention;

[0036] Figure 3 A flowchart of a method for modeling a building digital twin model based on semantic Web technology provided in an embodiment of the present invention;

[0037] Figure 4 Another flowchart of a method for modeling a building digital twin model based on semantic Web technology provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0039] The present invention relies on the advantages of semantic Web technology in data modeling, knowledge storage and logical reasoning to propose a high-fidelity digital twin framework architecture that is semantically rich and can update data in real time. This embodiment aims to establish a digital twin framework consisting of three modules: physical space entity, virtual space model and associated database. Specifically, Figure 1 A schematic diagram of a building digital twin model structure based on semantic Web technology provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the digital twin model includes a physical space entity 1, a virtual space model 2 and an associated database 3, wherein the physical space entity 1 provides building entity source data for the digital twin framework, the virtual space model 2 aims to virtualize and abstract building resources, and the associated database 3 relies on the semantic function of the model to provide data drive for the framework operation.

[0040] The information of the physical space entity 1 will be collected by airborne 3D lidar scanning technology and structural monitoring system, and the geometric configuration, building environment, and structural status related data of the on-site building entity will be sent to cyberspace through wireless transmission for digital twin virtual modeling.

[0041] The virtual space model 2 is composed of a point cloud model, a building information model, an engineering structure analysis model and ontology models in various fields. This module realizes the direct abstraction of physical entities in the virtual space, and is also the core component for intuitively displaying the virtual-reality mapping of the digital twin framework.

[0042] The associated database 3 is composed of two relational databases for monitoring time series and structural analysis, and three RDF models for monitoring, building information and structural analysis. By jointly querying the data of the RDF model in the same field and the corresponding relational database, and establishing a mapping relationship between the RDF models in different fields at the ontology level, the matching update and real-time interaction of the information flow of the entire digital twin framework are promoted. The present invention takes physical space as the source of information, virtual model as the presentation form, and associated database as the driving core, laying a model foundation for the development of user-oriented application service layer.

[0043] Figure 2 From the data flow perspective of the building digital twin framework, the information interaction between modules and models is presented, such as Figure 2 As shown in the figure, the initial building information model is first established with reference to the design data, and then the IFC model file suitable for conversion by the structural analysis software is exported based on MVD, and the corresponding initial finite element model is generated based on this. The IFC-supported data from the 3D point cloud scanning and monitoring system can be converted into .ifc files according to needs, and for non-IFC-supported data, it is necessary to virtualize the resource information through the ontology model to obtain the corresponding RDF model, namely the .ttl file. Figure 2 The BIM-IFC-RDF data flow shown in the article is the process of virtualizing multi-source heterogeneous data into a unified data model resource, and the RDF-IFC-BIM data flow is the process of giving semantic data to the digital twin framework for visualizing building structure concepts. Based on these two data flows, data between modules and models are iterated, associated and interacted, thus providing the core driving force for the realization and practice of various functional requirements of the digital twin framework.

[0044] In addition, based on the digital twin framework of this embodiment, application services oriented to the needs of end users can be further developed. Figure 1 As shown in the figure, the digital twin framework that has been verified by the virtual-to-real mapping function can be used to develop five service functions: building environment monitoring and digital display, construction simulation and risk analysis, AI-enabled construction operation and maintenance decision-making, structural status monitoring and evaluation, and structural safety assessment and early warning. The created model can be applied to the five key areas of building structure monitoring, construction, operation and maintenance, safety, and management, thereby promoting digital twin empowerment of construction projects. The present invention aims to drive digital twin service construction projects with semantic Web technology, and proposes a novel digital twin framework and modeling method to integrate the advanced manufacturing concept of digital twins into the full life cycle management of construction projects, thereby facilitating the digital and intelligent transformation of the construction industry.

[0045] like Figure 3 As shown, the present invention provides a modeling method of a building digital twin model based on semantic Web technology, comprising the following steps:

[0046] S1: Create an initial 3D building information model based on the architectural design plan;

[0047] Specifically, the geometric dimensions of the structure are three-dimensionally modeled according to the architectural design plan, and the three-dimensional entities established include floors, slabs, columns, walls, stairs, roofs, common furniture and other building accessories; this embodiment focuses on the field of structural analysis, so HVAC, electrical and water supply and drainage related entities or systems are not modeled. Revit or ArchiCAD software is used to perform geometric modeling of the corresponding dimensions in the design plan in proportional form, and the material categories required by the design are added to the structural components. Navisworks can be used to divide the building information model into construction stages, and based on this, the structural three-dimensional information model of the project at different stages is created. The software rendering function is used to enhance the visual authenticity of the model, so as to intuitively display the basic characteristics and artistic effects of the design plan.

[0048] S2: Use the point cloud model to modify the initial building information model and convert the model into a structural analysis model;

[0049] Specifically, an airborne laser radar is used to scan the construction site after each construction stage is completed, and the corresponding point cloud model is generated using the equipment supporting data processing system. The point cloud model and key point cloud data are compared and verified with the building information model of the same construction stage, and the geometric configuration with errors exceeding the threshold is further analyzed. Based on the reasons for the errors exceeding the limit obtained by analysis, it is determined whether to modify the model. After that, the modified model is converted into an IFC-SPF file using the MVD view of IFC4, and then the IFC file is read into the structural analysis software commonly used in construction engineering to generate the corresponding finite element model. Before further operations are performed on the FEA model, its geometric dimensions and material categories need to be reviewed and adjusted; after the model is verified, loads and working conditions are applied, constraints are established, load combinations and analysis modes are formulated according to the general process of finite element modeling, so as to obtain a structural analysis model that preliminarily matches each construction stage.

[0050] S3: Obtain monitoring system information and store it in the database, and use the semantic Web knowledge storage function to store multi-source heterogeneous data of the project into the knowledge base;

[0051] Specifically, the ontology method in semantic Web technology is used to associate the structural monitoring system, the building information model of a specific construction stage, and the FEA model, so as to achieve the integration and interoperability of heterogeneous information from the data level.

[0052] like Figure 4 As shown, step S3 specifically includes the following steps:

[0053] Step S31: Establish a corresponding database according to the monitoring indicator system of the monitoring system, and use the MySQL relational database to record the monitoring indicators in the form of multiple tables for storage;

[0054] The wireless sensor network will give full play to the advantages of 5G and Wi-Fi in data transmission, send the in-situ monitoring data to the IoT data terminal in real time, and automatically transfer it to the preset relational database to realize the intelligent storage of monitoring data. Since most of the monitoring data is time series data, its matching with each construction stage can be achieved by adding timestamps to the data, so the storage of monitoring data does not need to be classified according to different stages.

[0055] Step S32: Establish a custom SSN ontology model based on the SSN ontology framework and the sensor network layout, and develop an ontology model suitable for the structural analysis field based on the building structure form, structural analysis reference and structural monitoring scheme;

[0056] The ontology is based on the five basic information including monitoring objects, monitoring indicators, monitoring points, sensor IDs, and timestamps. The ontology functions are expanded based on actual needs to expand the knowledge of the fields involved in the model. The ontology for finite element simulation is developed based on the characteristics of the construction project and the focus of structural analysis. The ontology includes three-dimensional models, analysis references, key indicators, calculation results, and related derivative terms. It aims to use the lightest model to describe the relevant simulation information used to verify the virtual-real mapping function of the digital twin. The developed ontology must pass the review and evaluation of experts before it can be applied to the digital twin modeling of construction projects. In addition, the developed ontology should be matched with IfcOWL, relying on the comprehensiveness and authority of the IfcOWL ontology for concepts in the construction field to achieve consistent mapping of the custom ontology at the terminology level.

[0057] Step S33: Generate corresponding RDF models using the custom SSN ontology, structural analysis ontology and IfcOWL ontology, and store them in the knowledge base in the form of triples.

[0058] Using the ontology model approved by experts in step S32, RDF models for the three fields of monitoring system, building information and structural analysis are created respectively. The main method is to use the Apache Jena framework to develop RDF models in the Java compilation environment. The created RDF model expresses multi-source heterogeneous data in the form of triples, providing a data environment for the framework to automatically obtain information using the knowledge extraction function of the semantic Web. In view of the fact that the RDF models for various fields of construction are not only large in scale, but also users have extremely high requirements for their data extraction efficiency, all RDF models are stored in the Blazegraph TripleStore knowledge base in the form of triples.

[0059] Step S4: Using the knowledge extraction function of the semantic Web to realize the joint query of the time series database, obtain the actual load information of the structure to modify the finite element model;

[0060] Specifically, by using the knowledge extraction function of the semantic Web, this embodiment uses the in-situ measured ambient temperature, support displacement and structural wind pressure data of the measuring point to correct the preset values ​​of the simulation model according to the design specifications. Taking the structural wind pressure as an example, the SPARQL query is first used to extract the number of a sensor that monitors the structural wind pressure of a specific monitoring object at a specific construction stage from the sensor network RDF model, and then the SQL query is used to automatically retrieve the wind pressure monitoring data of the sensor at the corresponding timestamp based on the query number. Referring to this query process, the required monitoring data is extracted in sequence, and then the load replacement is implemented in the engineering structure analysis software to correct and update the initial finite element model, and the mapping association of the effects on the structure is realized.

[0061] Step S5: storing the structural analysis calculation results in the database, and updating the structural analysis domain RDF model to achieve dynamic matching of simulation results;

[0062] Specifically, semantic Web technology is used to update and dynamically match simulation results from different working conditions in real time. First, key indicators and parameters are formulated according to the structural form and analysis type, and then interconnected storage tables in the database are established according to the formulated indicators. After the simulation result database is established, the modified finite element model is structurally analyzed, and the calculation results of key parameters such as component internal force, deformation, stress and stress ratio are exported to the preset database. Using the mapping relationship between the RDF model for structural analysis and the relational database, the joint query algorithm of SPARQL and SQL is developed using the Jena framework and JDBC interface in the Java compilation environment, so as to realize the automatic update of the data attributes of each instance of the RDF model.

[0063] Step S6: Associate the measured and simulated results of the query structure response, and use the consistency check algorithm to verify the virtual-real mapping of the digital twin framework.

[0064] Specifically, by using the associated query and semantic Web knowledge reasoning functions, this embodiment verifies the virtual-to-real mapping function of the digital twin framework based on the displacement information of some nodes, the stress state of key rods, and the deformation of components derived from monitoring and simulation. In view of the fact that the sensor network ontology and the structural analysis ontology have been mapped and matched at the terminology level, the RDF model for monitoring systems and structural analysis can access, extract, and interoperate information across data sources through associated data technology. The monitoring and simulation results of the same indicator at the same point are extracted through the joint query of SPARQL and SQL, and the extracted matching data are then input into the consistency check algorithm for verification. If the measured and simulated errors of each indicator do not exceed the set threshold, it can be considered that the established digital twin framework has the virtual-to-real mapping function, and it can be used as a model basis to develop a building life cycle management and control platform that serves engineering practice.

[0065] Through the above steps, you can create and verify a digital twin framework with virtual-to-reality mapping function, and further develop and build an application service layer for end users. The digital twin framework that has passed the virtual-to-reality mapping function verified by the underlying data can be used as the technical core. Driven by the functional requirements and technical characteristics of each service module, corresponding algorithms can be developed. The created model can be applied to the five key areas of building structure monitoring, construction, operation and maintenance, safety analysis, and intelligent decision-making. The concept of digital twin technology can be effectively integrated into the full life cycle management of building structures, adding new ideas, new directions and new impetus to the promotion of digital and intelligent transformation of the construction industry.

[0066] Compared with the existing technology, the present invention aims to apply semantic Web technology to realize the mutual transmission, transformation and interoperation between physical space measured data, general building information model and structural analysis model, so as to generate a high-fidelity digital twin framework architecture. The present invention uses semantic Web technology to realize the unified expression and integrated interaction of multi-source heterogeneous information at the data level, and provides a semantic interoperability development and integration environment for subsequent artificial intelligence algorithms and platform service function algorithms.

[0067] The present invention has the following advantages:

[0068] 1. Use 3D laser scanning technology to modify the initial building information model, map the real physical space structure geometry to the virtual space in a more achievable way, and improve the model fidelity;

[0069] 2. Directly convert the modified building information model into a finite element simulation model to avoid human errors in the finite element modeling process, and use semantic Web technology to apply the actual effects on the structure to the simulation model to achieve real-time mapping of the physical state of the structure;

[0070] 3. Use ontology modeling technology to convert three types of computer-unrecognizable information, IFC, FEA, and sensor networks, into machine-understandable RDF models to enrich the semantics of the digital twin framework;

[0071] 4. Using RDF model as the link for consistency check of monitoring data and simulation results, it can realize the association query and interoperability of heterogeneous data sources;

[0072] 5. The established semantic digital twin framework not only reflects the virtual-real mapping in 3D modeling, but also verifies its real-time matching of the entity status of the physical space at the data source level through linked data technology;

[0073] 6. The modeling method of the present invention is not only suitable for creating a digital twin framework for the field of structural analysis, but can also be extended to other fields such as building energy analysis, building performance analysis, structural safety analysis, etc. through the replacement of the ontology model, and has universality and scalability.

[0074] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A building digital twin model based on semantic Web technology, characterized in that: The building digital twin model includes physical space entities, virtual space models and associated databases, wherein the physical space entities provide building entity source data for the digital twin model, the virtual space model is used to virtualize and abstract building resources, the virtual space model includes point cloud models, building information models, and structural analysis models, and the associated database relies on the semantic function of the model to provide data drive for the operation of the building digital twin model. The associated database includes two relational databases for monitoring time series and structural analysis, and three RDF models for monitoring, building information and structural analysis. By jointly querying the data of the RDF model in the same field and the corresponding relational database, and establishing a mapping relationship between the RDF models in different fields at the ontology level, the matching update and real-time interaction of the information flow of the entire digital twin model are promoted, and the virtual-to-real mapping function of the model is verified at the data level through the joint query and consistency check of the measured response and simulation results.

2. The building digital twin model based on semantic Web technology according to claim 1, characterized in that: The physical space entity information is collected through airborne 3D lidar scanning technology and a structural monitoring system, and the geometric configuration, building environment, and structural status-related data of the on-site building entity are sent to cyberspace through wireless transmission for digital twin virtual modeling.

3. A method for modeling a building digital twin model based on semantic Web technology according to claim 1 or 2, characterized in that: The method comprises the following steps: Create an initial 3D building information model based on the architectural design plan; Use the point cloud model to modify the initial building information model and convert the model into a structural analysis model; Acquire monitoring system information and store it in the database, and use the knowledge storage function of the semantic Web to store multi-source heterogeneous data of the project into the knowledge base; The knowledge extraction function of the semantic Web is used to realize the joint query of the time series database, obtain the actual load information of the structure and modify the finite element model; The structural analysis calculation results are stored in the database, and the RDF model in the structural analysis field is updated to achieve dynamic matching of simulation results; The measured and simulated results of the associated query structure response are used to verify the virtual-real mapping of the digital twin model using the consistency check algorithm.

4. The method for modeling a building digital twin model based on semantic Web technology according to claim 3 is characterized in that: The step of creating an initial three-dimensional building information model according to the architectural design plan specifically includes: using Revit or ArchiCAD to create a three-dimensional model based on the geometric configuration, building materials, and site environment information given in the project design plan.

5. The method for modeling a building digital twin model based on semantic Web technology according to claim 3, characterized in that: The steps of using the point cloud model to correct the initial building information model and converting the model to generate a structural analysis model specifically include: converting the data obtained by laser scanning into a point cloud model, comparing the point cloud model with the initial building information model and correcting the building information model, and converting the corrected model into an IFC model and importing it into the structural analysis engineering application software to obtain an initial finite element model.

6. The method for modeling a building digital twin model based on semantic Web technology according to claim 3, characterized in that: The step of acquiring monitoring system information and storing it in a database, and using the semantic Web knowledge storage function to store the multi-source heterogeneous data of the project into a knowledge base specifically includes the following steps: Establish a corresponding database according to the monitoring indicator system of the monitoring system, and use MySQL relational database to record the data of monitoring indicators in the form of multiple tables. According to the SSN ontology framework and the sensor network layout, a custom SSN ontology model is established, and an ontology model suitable for the structural analysis field is developed according to the building structure form, structural analysis reference and structural monitoring scheme; The corresponding RDF models are generated using the custom SSN ontology, structural analysis ontology and IfcOWL ontology, and stored in the knowledge base in the form of triples.

7. The method for modeling a building digital twin model based on semantic Web technology according to claim 3, characterized in that: The steps of using the semantic Web knowledge extraction function to realize joint query of the time series database and obtain the actual load information of the structure to correct the finite element model specifically include: determining the actual actions and loads on the structure through SQL and SPARQL joint query, and then replacing the assumed values ​​of the FEA model based on the design data with the measured parameter values, thereby mapping the stress state of the physical space structure to the virtual model, and realizing the correction of the initial finite element model.

8. The method for building digital twin model based on semantic Web technology according to claim 3 is characterized in that: The steps of storing the structural analysis calculation results in a database and updating the structural analysis field RDF model to realize dynamic matching of simulation results specifically include: determining key calculation indicators according to the building structure form, and establishing a corresponding relational database for multi-table associated storage based on this, and then associating the structural analysis RDF model with the calculation results data, and automatically completing the RDF model update through preset data query and model parameter modification algorithms.

9. The method for building digital twin model based on semantic Web technology according to claim 3, characterized in that: The measured and simulated results of the associated query structure response and the steps of verifying the virtual-to-real mapping of the digital twin model using a consistency check algorithm specifically include: applying associated data technology to access, integrate and interoperate the sensor network RDF model and the structural analysis RDF model across data sources, determining the matching monitoring data and simulation results through a joint query of knowledge and data, and performing a consistency check on the two to verify the virtual-to-real mapping function of the digital twin model.

Images