Building control model construction method, system and storage medium based on digital twin
Through the digital twin model technology combined with Revit and Unreal 5 engine, the problem of modeling accuracy and rendering authenticity in building control model construction is solved, the visual interactive environment and real-time management of the building are realized, and the accuracy and equipment of control are improved. Maintenance efficiency.
Patent Information
- Application Number
- CN202411112164.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-08-14
AI Technical Summary
The existing building control model construction technology cannot provide a visual interactive environment for building while ensuring the accuracy of building modeling and rendering authenticity, so as to realize real-time simulation, monitoring and optimization management, especially the modeling effect of irregular building geometry is poor. .
Use Revit software to model buildings, import the model into Unreal 5 engine, establish a digital twin model, build a data interaction structure through OPC-UA technology, and combine the Informer model to build the equipment maintenance model to realize real-time control and management of buildings .
While ensuring the accuracy of modeling and rendering authenticity, it provides a visual interactive environment for building, real-time simulation, monitoring and optimization management, discover equipment failures in advance, extend equipment life, reduce maintenance costs, and improve control accuracy and General use.
Smart Images

Figure CN118642376B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of building control model construction, and specifically to a building control model construction method, system and storage medium based on digital twins. Background Art
[0002] Building control model construction technology uses computers, network technology, automatic control technology and communication technology to connect various devices inside the building to a control network, and use computers to conduct comprehensive control of the interior of the building. This technology, through automated management and control systems, not only covers the centralized control of various types of equipment, but also includes energy saving, safety, convenience and other needs. In practical applications, this technology has broad prospects and important significance.
[0003] Existing building control model construction technology usually uses BIM technology to model building information, and then integrates the internal information of the building through manual or management models and fixed algorithms, or directly integrates the internal information of the building without modeling. This method technology basically has the ability to sense, know and control the operating status of the building, but it cannot realize a visual interactive environment of the building structure that can be seen, heard and interacted with, and perform real-time simulation, monitoring, analysis and optimization management of the internal environment of the building. For example, the patent application with publication number CN117570512A discloses a building temperature control system based on a temperature adaptive control model. This solution is to collect internal building information and integrate the internal information of the building through management models and fixed algorithms, and does not use BIM. Technology is used to model building information, but there is no visual interactive environment for building structures, and it is impossible to realize real-time simulation and analysis of buildings. At the same time, the model rendering effect of the BIM software is poor, especially for irregular building geometric shapes, such as arcs, irregular part structures, etc., and it is impossible to use the internal information of the building for real-time calculations. The rendering effect of the game engine is realistic and can perform real-time calculations, but the modeling function is poor, and it is impossible to accurately model the structural layout of the building in detail, and it is impossible to provide a building visualization interactive environment while ensuring the accuracy of building modeling and the authenticity of rendering, so as to realize real-time simulation, monitoring, analysis and optimization management of the building environment. Summary of the invention
[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent. The building is modeled by Revit software, and then the model is imported into Unreal Engine 5, a digital twin model of the building is constructed based on Unreal Engine 5, and the building is controlled based on the digital twin model; so as to solve the problem that the existing building control model construction technology cannot provide a building visualization interactive environment while ensuring the accuracy of building modeling and rendering authenticity, and realize real-time simulation, monitoring analysis and optimization management of the building environment.
[0005] To achieve the above objectives, in a first aspect, the present application provides a method for constructing a building control model based on digital twins, comprising the following steps:
[0006] Obtain building construction data, use Revit software to model the building based on the building construction data, and obtain the BIM of the building;
[0007] Export the BIM data of the building from Revit software, and import the BIM data into Unreal Engine 5 to obtain the Unreal building model;
[0008] Establish building equipment coding standards, map and code the equipment in the building, obtain equipment coding data, and obtain internal building data;
[0009] Building equipment maintenance model using internal building data based on the Informer model;
[0010] Use OPC-UA technology to build a data interaction structure, map the internal building data to the virtual building model based on the device encoding data, and obtain a digital twin model;
[0011] Control buildings based on digital twin models.
[0012] Furthermore, obtaining building construction data, modeling the building using Revit software based on the building construction data, and obtaining the BIM of the building includes the following sub-steps:
[0013] Obtain building geometry data: including the geometric shapes and dimensions of all building components, as well as the specific locations of all building components in space;
[0014] Obtain building material data: including material types, material specifications and material properties of all building components;
[0015] Obtain building structure data: including load performance and mechanical performance parameters of the building structure;
[0016] Obtain building equipment data: including the model, specification, location and connection method of the building's electromechanical equipment and fire-fighting equipment;
[0017] Based on the building construction data, the BIM of the building is established using Revit software, and the BIM of the building is obtained and saved. The building construction data includes: building geometry data, building material data, building structure data and building equipment data.
[0018] Furthermore, exporting the BIM data of the building from the Revit software and importing the BIM data into the Unreal Engine 5 to obtain the Unreal building model includes the following sub-steps:
[0019] Install the corresponding version of the Datasmith plug-in based on the Revit software, use the Datasmith plug-in to export the BIM of the building, and obtain the BIM data of the building in the udatasmith format. Install the corresponding version of the Datasmith plug-in based on the Unreal 5 engine, use the Datasmith plug-in to import the BIM data of the building in the udatasmith format into the Unreal 5 engine, and obtain the BIM of the building under the Unreal 5 engine. Perform material rendering on the BIM of the building under the Unreal 5 engine according to the building material data, and obtain the Unreal building model after completion.
[0020] Furthermore, establishing the building equipment coding standard includes the following sub-steps:
[0021] Based on the building construction data, the building, profession, equipment type, equipment name, spatial location and equipment number of all equipment in the building are obtained to establish a total of 6 levels of building equipment coding standards. The building equipment coding standards include: 1-level building code, 2-level professional code, 3-level type code, 4-level name code, 5-level location code and 6-level number code;
[0022] Mapping and encoding the equipment in the building to obtain equipment coding data includes the following sub-steps:
[0023] Based on the building equipment coding standard, the building equipment in the actual scene and the corresponding equipment model in the virtual building model are encoded to obtain equipment coding data. The coding of the building equipment in the actual scene is consistent with the coding of the corresponding equipment model in the virtual building model, and it is ensured that the coding of any two building equipment in the actual scene is not repeated, and the coding of any two equipment models in the virtual building model is not repeated.
[0024] Furthermore, obtaining the internal data of the building includes the following sub-steps:
[0025] The building equipment data based on the building construction data obtains the basic attribute parameters of all equipment in the building, marked as equipment parameter information, obtains the operation data of all equipment in the building, including historical operation data and current operation data, marked as equipment operation information, and obtains the maintenance records of all equipment in the building, marked as equipment maintenance information;
[0026] The equipment parameter information, equipment operation information and equipment maintenance information are marked as internal building data, and the internal building data is transferred to the corresponding equipment code according to the equipment coding data.
[0027] Furthermore, constructing an equipment maintenance model based on the Informer model using the internal building data includes the following sub-steps:
[0028] Based on the historical operation data in the equipment maintenance information and the equipment operation information, the equipment status is obtained once at a first time interval within a first time length, and the equipment status includes: maintenance, repair, damage and normal, which are classified and stored according to the equipment number, and a time label is bound to each data, marked as a first data set, and the first data set is divided into a training set and a test set at a ratio of 8:2. The first time length is set to T, and the first time interval is set to a;
[0029] Set the mean absolute percentage error MAPE and root mean square error RMSE as evaluation indicators, and set qualified parameters m and r based on the evaluation indicators;
[0030] Based on the Informer model, training is performed using the training set. After the training is completed, the trained Informer model is tested using the test set, and the evaluation results M and R are output. If the evaluation indicators satisfy M≤m and R≤r, the test is ended and the equipment maintenance model is obtained. If the evaluation indicators do not satisfy M≤m and R≤r, training is performed again using the training set until M and R satisfy M≤m and R≤r to obtain the equipment maintenance model.
[0031] Furthermore, the OPC-UA technology is used to construct a data interaction structure, and based on the device encoding data, the internal building data is mapped to the virtual building model to obtain the digital twin model, which includes the following sub-steps:
[0032] Based on OPC-UA technology, a data interaction structure between internal building data and the virtual building model is constructed. The data interaction structure includes the management layer, the digital twin layer, and the physical device layer. The physical device layer includes various devices inside the building in the actual scene and various systems composed of devices. The digital twin layer includes the virtual building model, the Unreal Engine 5, and the device maintenance model. The management layer is used to generate management instructions to manage the equipment in the building.
[0033] The data interaction structure and the content contained in the data interaction structure are recorded as a digital twin model.
[0034] Furthermore, controlling a building based on a digital twin model includes the following sub-steps:
[0035] Obtain real-time internal building data from the physical device layer through OPC-UA technology, and transmit the real-time internal building data to the digital twin layer and management layer based on the device coding data;
[0036] The digital twin layer uses the Unreal Engine 5 to drive the Unreal Building model to simulate operations based on the real-time internal building data, and uses the equipment maintenance model to predict the operating status of the equipment to obtain the prediction results, and then transmits the prediction results to the management level;
[0037] The management layer generates management instructions based on the internal building data of the physical equipment layer and the prediction results of the digital twin layer, and transmits the management instructions to the physical equipment layer; the physical equipment layer controls the equipment in the building according to the management instructions to complete the management instructions.
[0038] In a second aspect, the present application provides a building control model construction system based on digital twins, including a BIM module, a virtual building module, a device coding module, a model construction module, a digital twin module and a building control module;
[0039] The BIM module includes a building data unit and a building modeling unit. The building data unit is used to obtain building construction data, and the building construction data includes building geometry data, building material data, building structure data, building equipment data and building external data. The building modeling unit includes Revit software, and Revit software is used to model the building based on the building construction data to obtain the BIM of the building.
[0040] The Unreal Building module includes the Unreal 5 engine, which is used to export the BIM data of the building from the Revit software and import the BIM data into the Unreal 5 engine to obtain the Unreal Building model;
[0041] The equipment coding module includes a coding establishment unit, an automatic coding unit and a data acquisition unit. The coding establishment unit is used to establish the building equipment coding standard. The automatic coding unit is used to map and code the equipment in the building to obtain equipment coding data. The data acquisition unit is used to obtain the internal data of the building. The internal data of the building includes equipment parameter information, equipment operation information and equipment maintenance information.
[0042] The model building module builds the equipment maintenance model based on the Informer model and uses the internal building data;
[0043] The digital twin module uses OPC-UA technology to build a data interaction structure and maps the internal building data to the virtual building model based on the device encoding data to obtain a digital twin model;
[0044] The building control module includes a digital twin model, and the building is controlled based on the digital twin model.
[0045] In a third aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.
[0046] Beneficial effects of the present invention: The present invention first obtains building construction data, models the building based on the building construction data using Revit software to obtain the BIM of the building; exports the BIM data of the building from the Revit software, and imports the BIM data into the Unreal 5 engine to obtain the Unreal building model; then establishes the building equipment coding standard, maps and codes the equipment in the building to obtain equipment coding data, and obtains the internal data of the building; then builds the equipment maintenance model based on the Informer model using the internal data of the building; then builds the data interaction structure using OPC-UA technology, maps the internal data of the building to the Unreal building model based on the equipment coding data, and obtains the digital twin model; finally, controls the building based on the digital twin model; The present invention uses Revit software for modeling, and then builds the digital twin model based on the Unreal 5 engine, while ensuring the accuracy of building modeling and the authenticity of rendering, provides a building visualization interactive environment, and realizes real-time simulation, monitoring, analysis and optimization management of the building environment;
[0047] The present invention uses Revit software to construct a BIM model of a building. Revit provides a powerful three-dimensional visualization function, which can realize accurate modeling of the building structure layout, and obtain a BIM model of a building with extremely accurate size layout, thereby improving the accuracy of the digital twin model; BIM data is imported into the Unreal 5 engine, and the powerful rendering effect and real-time calculation ability of the Unreal 5 engine can be utilized to make the model display effect after modeling more realistic, so that the control experience of building control using the digital twin model is stronger and the control accuracy is higher; the Informer model is used to build an equipment maintenance model, which can detect potential equipment failures in advance, extend equipment life, reduce maintenance costs, improve equipment efficiency, and improve the versatility and optimization ability of the model; the OPC-UA technology is used to map the internal data of the building. Since the OPC-UA architecture can run in different environments and is scalable, the digital twin model can be connected to various models, algorithms or solutions according to needs, thereby improving the versatility and robustness of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 is a functional block diagram of the system of the present invention;
[0049] Figure 2 is a flow chart of the method steps of the present invention;
[0050] Figure 3 It is a schematic diagram of the device coding standard of the present invention;
[0051] Figure 4 This is a schematic diagram of the structure of the Informer model of the present invention;
[0052] Figure 5 It is a schematic diagram of the data interaction structure of the present invention. DETAILED DESCRIPTION
[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] Example 1, please refer to Figure 1 As shown, the present application provides a building control model construction system based on digital twins, including a BIM module, a virtual building module, an equipment coding module, a model construction module, a digital twin module and a building control module;
[0055] The building BIM module includes a building data unit and a building modeling unit. The building data unit is used to obtain building construction data. The building construction data includes building geometry data, building material data, building structure data, building equipment data and building external data.
[0056] The building data unit is configured with a building data acquisition strategy, which includes:
[0057] Obtain building geometry data: including the geometry and dimensions of all building components, as well as the specific locations of all building components in space; for example, the geometry and dimensions of walls, columns, beams, doors and windows in the building, and their specific locations in the building;
[0058] Obtain building material data: including material types, material specifications and material properties of all building components; in specific instances, obtaining material information can make modeling more accurate and also provide a reference for later material rendering;
[0059] Obtain building structure data: including load performance and mechanical performance parameters of the building structure; such as the deadweight of the floor, wind load and snow load of the building, as well as elastic modulus, compressive strength and seismic grade;
[0060] Obtain building equipment data: including the model, specification, location and connection method of the building's electromechanical equipment and fire-fighting equipment; for example, the model, specification, location and connection method of HVAC, lighting, fire-fighting equipment, etc., the configuration and connection method of electrical lines, switches, sockets, etc., and the connection method includes inclusion, nesting, connection, etc.;
[0061] The building modeling unit is configured with a building modeling strategy, which includes: using Revit software to establish a building information model (BIM) of the building based on the building construction data, obtaining and saving the building information model (BIM) of the building, wherein the building information model (BIM) of the building includes: a building model and a surrounding environment scene model, and the building construction data includes: building geometry data, building material data, building structure data, and building equipment data; in this embodiment, using Revit software to establish a building information model (BIM) of the building includes the following steps: Step 1, project preparation, creating and editing elevations, drawing Step 2: Create family components by parameterization, including creating a new family, selecting a family template, drawing shapes, adding parameters, and loading into the project; Build parameterization of a specific family, such as creating structural columns, beams, piers, etc., and parameterize the size of the relevant family; Step 3: Structural layout, add structural components, and arrange structural columns, beams and other load-bearing components in Revit according to the pre-set axis grid and elevation information, and edit and set properties for these components; Step 4: Design performance, after the design is completed, use the built-in tools in Revit to visualize and check the overall effect of the design;
[0062] In the specific implementation process, obtaining detailed building construction data and understanding the detailed information of each part of the building can ensure the spatial accuracy and logical consistency of the model, ensure the accuracy and realism of the model, and thus build a highly realistic BIM; this is also an important basis for later building control, ensuring the reliability and safety of building control; in the process of using Revit software to establish BIM, pay attention to the consistency of BIM unit settings with building construction data to avoid major modifications in the later stage; when arranging components, consider the connection and rationality between components.
[0063] The Unreal Building module includes the Unreal 5 engine, which is used to export the BIM data of the building from the Revit software and import the BIM data into the Unreal 5 engine to obtain the Unreal Building model;
[0064] The Unreal Building module is configured with the Unreal Building Strategy, which includes: installing the corresponding version of the Datasmith plug-in based on the Revit software, using the Datasmith plug-in to export the BIM of the building, obtaining the BIM data of the building in the udatasmith format, installing the corresponding version of the Datasmith plug-in based on the Unreal 5 engine, using the Datasmith plug-in to import the BIM data of the building in the udatasmith format into the Unreal 5 engine, obtaining the BIM of the building under the Unreal 5 engine, and performing material rendering on the BIM of the building under the Unreal 5 engine according to the building material data, and obtaining the Unreal Building model after completion; Revit software has high hardware requirements, low model rendering efficiency, and poor rendering effect, especially for irregular building geometric shapes, such as arcs and irregular part structures, while the rendering effect of the Unreal 5 engine is realistic, but the modeling function of the building is not as good as that of the Revit software, so using the Revit software to establish the BIM of the building and then importing it into the Unreal 5 engine can give full play to the advantages of both and avoid the disadvantages of both;
[0065] In the specific implementation process, Datasmith supports a series of 3D modeling software, including but not limited to 3ds Max, SketchUp, Revit, etc. The Datasmith plug-in can be directly installed through official channels such as the Epic Games Store or the official website. When installing the Datasmith plug-in, pay attention to the corresponding model version of the software to avoid the situation where export and import cannot be encountered.
[0066] The equipment coding module includes a coding establishment unit, an automatic coding unit and a data acquisition unit. The coding establishment unit is used to establish a building equipment coding standard. The automatic coding unit is used to map and code the equipment in the building to obtain equipment coding data. The data acquisition unit is used to obtain internal building data, which includes equipment parameter information, equipment operation information and equipment maintenance information.
[0067] The coding establishment unit is configured with a coding establishment strategy, which includes: Figure 3 As shown, based on the building construction data, the building, profession, equipment type, equipment name, spatial location and equipment number of all equipment in the building are obtained to establish a total of 6 levels of building equipment coding standards. The building equipment coding standards include: level 1 building code, level 2 professional code, level 3 type code, level 4 name code, level 5 location code and level 6 number code. The equipment coding standard is established to ensure a one-to-one real-time mapping between the data generated by the equipment in the building and the equipment model in the virtual building model;
[0068] The automatic encoding unit is configured with an automatic encoding strategy, which includes: based on the building equipment encoding standard, encoding the building equipment in the actual scene and the corresponding equipment model in the virtual building model to obtain equipment encoding data, the encoding of the building equipment in the actual scene is consistent with the encoding of the corresponding equipment model in the virtual building model, and it is ensured that the encoding of any two building equipment in the actual scene is not repeated, and the encoding of any two equipment models in the virtual building model is not repeated;
[0069] The data acquisition unit is configured with a data acquisition strategy, which includes: acquiring basic attribute parameters of all equipment in the building based on building equipment data of the building construction data, marked as equipment parameter information, acquiring operation data of all equipment in the building, including historical operation data and current operation data, marked as equipment operation information, for example, the operation information of a surveillance camera includes: monitoring screen, input voltage, input current, working mode and operation time, acquiring maintenance records of all equipment in the building, marked as equipment maintenance information;
[0070] Mark the equipment parameter information, equipment operation information and equipment maintenance information as internal building data, and transfer the internal building data to the corresponding equipment code according to the equipment code data;
[0071] In the specific implementation process, a model automatic encoding plug-in can be developed based on the digital model creation tool to automatically encode all device models. For example, the blueprint system of the Unreal 5 engine can be used to automatically encode all device models in the Unreal building model by writing a blueprint script, thereby improving the encoding efficiency. After the encoding is completed, the encoded data is checked to check whether there is any repeated encoding to ensure that the encoding of any two building devices in the actual scene is not repeated, and the encoding of any two device models in the Unreal building model is not repeated, laying the model foundation for subsequent processing.
[0072] The model building module builds the equipment maintenance model based on the Informer model and uses the internal building data;
[0073] The model building module is configured with a model building strategy, and the model building module includes: based on the historical operation data in the equipment maintenance information and the equipment operation information, obtaining the equipment status once at a first time interval within a first time length, the equipment status includes: maintenance, repair, damage and normal, and storing them according to the equipment number, and binding a time label to each data, marking it as a first data set, dividing the first data set into a training set and a test set at 8:2, the first time length is set to T, and the first time interval is set to a;
[0074] The mean absolute percentage error (MAPE) and the root mean square error (RMSE) are set as evaluation indicators, and qualified parameters m and r are set based on the evaluation indicators. In this embodiment, m is set to 0.08, r is set to 8.00, and the mean absolute percentage error formula is: ; The root mean square error formula is: ;
[0075] Where MAPE stands for mean absolute percentage error; RMSE stands for root mean square error; Represents the actual device status at time t; represents the model-predicted device state at time t, and N represents the number of data of the same type;
[0076] Based on the Informer model, use the training set for training. Figure 4 As shown, the Informer model mainly includes two parts: an encoder and a decoder; after the training is completed, the trained Informer model is tested using the test set, and the evaluation results M and R are output. The smaller the mean absolute percentage error and the root mean square error output by the equipment maintenance model are, the better the performance of the equipment maintenance model is, that is, the higher the prediction accuracy is; if the evaluation index satisfies M≤m and R≤r, the test is terminated to obtain the equipment maintenance model; if the evaluation index does not satisfy M≤m and R≤r, the training set is used to train again until M and R satisfy M≤m and R≤r to obtain the equipment maintenance model. In this embodiment, the hyperparameters of the Informer model training are set to, the learning rate is set to 0.001; the batch size is set to 32; the number of model training rounds is set to 200 rounds;
[0077] In the specific implementation process, using the Informer model to predict equipment maintenance can detect potential faults in advance and issue early warnings, which helps reduce the possibility of failures and unplanned downtime; through prediction, excessive maintenance and unnecessary replacement of equipment can be reduced, thereby extending the service life of the equipment. Maintenance prediction can ensure that the equipment operates in the best condition, thereby improving production efficiency and equipment performance, and optimize maintenance plans based on prediction results to reduce maintenance costs; the first time length T and the first time interval a are set according to the prediction requirements. For example, if the equipment status in the next 3 days needs to be predicted, the first time length can be 60 days, that is, the equipment status in the previous 60 days is obtained, and the first time interval a can be 10 minutes, 15 minutes or 30 minutes, etc.;
[0078] The digital twin module uses OPC-UA technology to build a data interaction structure and maps the internal building data to the virtual building model based on the device encoding data to obtain a digital twin model;
[0079] The digital twin module is configured with a digital twin strategy, which includes: Figure 5 As shown, the data interaction structure between the internal data of the building and the virtual building model is constructed based on OPC-UA technology. The data interaction structure includes the management layer, the digital twin layer and the physical device layer. The physical device layer includes various devices inside the building in the actual scene and various systems composed of devices. The digital twin layer includes the virtual building model, the Unreal 5 engine and the equipment maintenance model. The management layer is used to generate management instructions to manage the equipment in the building.
[0080] Record the data interaction structure and the contents contained in the data interaction structure as a digital twin model;
[0081] In the specific implementation process, OPC-UA is a standardized technical framework that uses Internet integration technology and is not dependent on a specific operating system or hardware platform. OPC-UA can run in different environments, such as Windows, Linux, and embedded systems, and has independence, security, scalability, and modelability. Through information modeling, OPC-UA supports adding new objects and functions to the address space without changing existing programs or services. OPC-UA provides a rich information model that can represent various types of data and objects and supports modeling of complex structures and levels. This enables OPC-UA to integrate data from different sources and formats to meet the needs of digital twin model data mapping and improve data interoperability and reusability. OPC-UA not only supports data access, but also provides advanced functions such as alarm and event processing, historical data storage, and complex data processing, which improves the intelligence of the digital twin model and the control ability of the building. The building control module includes a digital twin model, and the building is controlled based on the digital twin model.
[0082] The building control module configures the building control strategy, which includes: Figure 5 As shown, the real-time acquisition of internal building data from the physical device layer is done through OPC-UA technology, and the real-time acquired internal building data is transmitted to the digital twin layer and management layer based on the device coding data;
[0083] The digital twin layer uses the Unreal Engine 5 to drive the Unreal Building model to simulate operations based on the real-time internal building data, and uses the equipment maintenance model to predict the operating status of the equipment to obtain the prediction results, and then transmits the prediction results to the management level;
[0084] The management layer generates management instructions based on the internal building data of the physical device layer and the prediction results of the digital twin layer, and transmits the management instructions to the physical device layer; the physical device layer controls the equipment in the building according to the management instructions to complete the management instructions;
[0085] During the specific implementation process, the management layer is also used to generate management instructions through external operations. For example, the lighting in the building is turned on or off manually through the management layer. Management and emergency models, systems, and solution models can also be introduced into the management layer to improve the intelligence of the digital twin model.
[0086] Example 2, please refer to Figure 2 As shown, in the second aspect, the present application provides a method for constructing a building control model based on digital twins, comprising the following steps:
[0087] Step S1, acquiring building construction data, modeling the building using Revit software based on the building construction data, and obtaining the BIM of the building; Step S1 includes the following sub-steps:
[0088] Step S101, obtaining building geometric data: including geometric shapes and geometric dimensions of all building components, and specific positions of all building components in space;
[0089] Step S102, obtaining building material data: including material types, material specifications and material properties of all building components;
[0090] Step S103, acquiring building structure data: including load performance and mechanical performance parameters of the building structure;
[0091] Step S104, obtaining building equipment data: including the model, specification, location and connection method of the building's electromechanical equipment and fire-fighting equipment;
[0092] Step S104, using Revit software to establish the BIM of the building based on the building construction data, obtaining the BIM of the building and saving it, the building construction data includes: building geometry data, building material data, building structure data and building equipment data.
[0093] Step S2, exporting the BIM data of the building from the Revit software, and importing the BIM data into the Unreal Engine 5 to obtain an Unreal building model; Step S2 includes the following sub-steps:
[0094] Step S201, installing the corresponding version of the Datasmith plug-in based on the Revit software, using the Datasmith plug-in to export the BIM of the building, and obtaining the BIM data of the building in the udatasmith format;
[0095] Step S202, installing the corresponding version of the Datasmith plug-in based on the Unreal Engine 5, and using the Datasmith plug-in to import the BIM data of the building in the udatasmith format into the Unreal Engine 5, to obtain the BIM of the building under the Unreal Engine 5;
[0096] Step S203, performing material rendering on the BIM of the building under the Unreal Engine 5 according to the building material data, and obtaining an Unreal building model after completion.
[0097] Step S3, establish a building equipment coding standard, map and code the equipment in the building, obtain equipment coding data, and obtain internal building data; Step S3 includes the following sub-steps:
[0098] Step S301, based on the building construction data, obtain the building, profession, equipment type, equipment name, spatial location and equipment number of all equipment in the building to establish a total of 6 levels of building equipment coding standards, the building equipment coding standards include: 1 level building code, 2 level professional code, 3 level type code, 4 level name code, 5 level location code and 6 level number code;
[0099] Step S302: Based on the building equipment coding standard, the building equipment in the actual scene and the corresponding equipment model in the virtual building model are encoded to obtain equipment coding data. The coding of the building equipment in the actual scene is consistent with the coding of the corresponding equipment model in the virtual building model, and it is ensured that the coding of any two building equipment in the actual scene is not repeated, and the coding of any two equipment models in the virtual building model is not repeated;
[0100] Step S303, obtaining basic attribute parameters of all equipment in the building based on the building equipment data of the building construction data, and marking them as equipment parameter information;
[0101] Step S304, obtaining the operating data of all equipment in the building, including historical operating data and current operating data, and marking them as equipment operating information;
[0102] Step S305, obtaining the maintenance records of all equipment in the building and marking them as equipment maintenance information;
[0103] Step S306: Mark the device parameter information, device operation information and device maintenance information as internal building data, and transmit the internal building data to the corresponding device code according to the device code data.
[0104] Step S4, constructing an equipment maintenance model using the internal building data based on the Informer model; Step S4 includes the following sub-steps:
[0105] Step S401, based on the historical operation data in the equipment maintenance information and the equipment operation information, obtain the equipment status once at a first time interval within a first time length, the equipment status includes: maintenance, repair, damage and normal, and is classified and stored according to the equipment number, and a time tag is bound to each data, marked as a first data set, the first time length is set to T, and the first time interval is set to a;
[0106] Step S402, dividing the first data set into a training set and a test set at a ratio of 8:2;
[0107] Step S403, setting mean absolute percentage error MAPE and root mean square error RMSE as evaluation indicators, and setting qualified parameters m and r based on the evaluation indicators;
[0108] Step S404, training is performed based on the Informer model using the training set, and after the training is completed, the trained Informer model is tested using the test set, and evaluation results M and R are output;
[0109] Step S405: If the evaluation index satisfies M≤m and R≤r, the test is terminated and the equipment maintenance model is obtained. If the evaluation index does not satisfy M≤m and R≤r, training is performed again using the training set until M and R satisfy M≤m and R≤r to obtain the equipment maintenance model.
[0110] Step S5, using OPC-UA technology to build a data interaction structure, based on the device coding data, mapping the internal building data to the virtual building model to obtain a digital twin model; Step S5 includes the following sub-steps:
[0111] Step S501, constructing a data interaction structure between the internal data of the building and the virtual building model based on OPC-UA technology, the data interaction structure includes a management layer, a digital twin layer and a physical device layer, the physical device layer includes various devices inside the building in the actual scene and various systems composed of the devices, the digital twin layer includes the virtual building model, the Unreal 5 engine and the device maintenance model, and the management layer is used to generate management instructions to manage the devices in the building;
[0112] Step S502: record the data interaction structure and the content contained in the data interaction structure as a digital twin model.
[0113] Step S6, controlling the building based on the digital twin model; Step S6 includes the following sub-steps:
[0114] Step S601, obtaining real-time internal building data from the physical device layer through OPC-UA technology, and transmitting the real-time internal building data to the digital twin layer and management layer based on the device coding data;
[0115] Step S602: The digital twin layer uses the Unreal Engine 5 to drive the virtual building model to simulate operation based on the real-time internal building data, and uses the equipment maintenance model to predict the operating status of the equipment to obtain the prediction results, and then transmits the prediction results to the management layer.
[0116] Step S603: The management layer generates management instructions based on the internal building data of the physical device layer and the prediction results of the digital twin layer, and transmits the management instructions to the physical device layer; the physical device layer controls the equipment in the building according to the management instructions to complete the management instructions.
[0117] Embodiment 3. The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a building control model construction method based on digital twins provided by the above methods, the method including: obtaining building construction data, modeling the building using Revit software based on the building construction data, and obtaining the BIM of the building; exporting the BIM data of the building from the Revit software, and importing the BIM data into the Unreal 5 engine to obtain an Unreal building model; establishing a building equipment coding standard, mapping and coding the equipment in the building, obtaining equipment coding data, and obtaining the internal data of the building; constructing an equipment maintenance model using the internal building data based on the Informer model; constructing a data interaction structure using OPC-UA technology, and mapping the internal building data to the Unreal building model based on the equipment coding data to obtain a digital twin model; and controlling the building based on the digital twin model.
[0118] Embodiment 4, the present application also provides a computer-readable storage medium, the present application provides a storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method for constructing a building control model based on digital twins are executed to achieve the following functions: obtain building construction data, model the building based on the building construction data using Revit software to obtain the BIM of the building; export the BIM data of the building from the Revit software, and import the BIM data into the Unreal 5 engine to obtain an Unreal building model; establish a building equipment coding standard, map and encode the equipment in the building, obtain equipment coding data, and obtain the internal data of the building; construct an equipment maintenance model based on the Informer model using the internal data of the building; construct a data interaction structure using OPC-UA technology, map the internal data of the building to the Unreal building model based on the equipment coding data, and obtain a digital twin model; control the building based on the digital twin model.
[0119] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0120] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.
[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for constructing a building control model based on digital twins, characterized in that: The steps include: Obtain building construction data, use Revit software to model the building based on the building construction data, and obtain the BIM of the building; Export the BIM data of the building from Revit software, and import the BIM data into Unreal Engine 5 to obtain the Unreal building model; Establish building equipment coding standards, map and code the equipment in the building, obtain equipment coding data, and obtain internal building data; The establishment of building equipment coding standards includes the following sub-steps: Based on the building construction data, the building, profession, equipment type, equipment name, spatial location and equipment number of all equipment in the building are obtained to establish a total of 6 levels of building equipment coding standards. The building equipment coding standards include: 1-level building code, 2-level professional code, 3-level type code, 4-level name code, 5-level location code and 6-level number code; Mapping and encoding the equipment in the building to obtain equipment coding data includes the following sub-steps: Based on the building equipment coding standard, the building equipment in the actual scene and the corresponding equipment model in the virtual building model are encoded to obtain equipment coding data. The coding of the building equipment in the actual scene is consistent with the coding of the corresponding equipment model in the virtual building model, and it is ensured that the coding of any two building equipment in the actual scene is not repeated, and the coding of any two equipment models in the virtual building model is not repeated; Obtaining internal building data includes the following sub-steps: The building equipment data based on the building construction data obtains the basic attribute parameters of all equipment in the building, marked as equipment parameter information, obtains the operation data of all equipment in the building, including historical operation data and current operation data, marked as equipment operation information, and obtains the maintenance records of all equipment in the building, marked as equipment maintenance information; Mark the equipment parameter information, equipment operation information and equipment maintenance information as internal building data, and transfer the internal building data to the corresponding equipment code according to the equipment code data; Building equipment maintenance model using internal building data based on the Informer model; Building an equipment maintenance model using building internal data based on the Informer model includes the following sub-steps: Based on the historical operation data in the equipment maintenance information and the equipment operation information, the equipment status is obtained once at a first time interval within a first time length, and the equipment status includes: maintenance, repair, damage and normal, which are classified and stored according to the equipment number, and a time label is bound to each data, marked as a first data set, and the first data set is divided into a training set and a test set at a ratio of 8:
2. The first time length is set to T, and the first time interval is set to a; The mean absolute percentage error (MAPE) and the root mean square error (RMSE) are set as evaluation indicators, and the qualified parameters m and r are set based on the evaluation indicators. The formula for the mean absolute percentage error is: ; The root mean square error formula is: ; Where MAPE stands for mean absolute percentage error; RMSE stands for root mean square error; Represents the actual device status at time t; represents the model-predicted device state at time t, and N represents the number of data of the same type; Based on the Informer model, the training set is used for training. After the training is completed, the trained Informer model is tested with the test set, and the evaluation results M and R are output. If the evaluation index satisfies M≤m and R≤r, the test is terminated and the equipment maintenance model is obtained. If the evaluation index does not satisfy M≤m and R≤r, the training set is used for training again until M and R satisfy M≤m and R≤r, and the equipment maintenance model is obtained. Use OPC-UA technology to build a data interaction structure, map the internal building data to the virtual building model based on the device encoding data, and obtain a digital twin model; Using OPC-UA technology to build a data interaction structure, based on the device encoding data, the internal building data is mapped to the virtual building model to obtain the digital twin model, which includes the following sub-steps: Based on OPC-UA technology, a data interaction structure between internal building data and the virtual building model is constructed. The data interaction structure includes the management layer, the digital twin layer, and the physical device layer. The physical device layer includes various devices inside the building in the actual scene and various systems composed of devices. The digital twin layer includes the virtual building model, the Unreal Engine 5, and the device maintenance model. The management layer is used to generate management instructions to manage the equipment in the building. Record the data interaction structure and the contents contained in the data interaction structure as a digital twin model; Controlling a building based on a digital twin model includes the following sub-steps: Obtain real-time internal building data from the physical device layer through OPC-UA technology, and transmit the real-time internal building data to the digital twin layer and management layer based on the device coding data; The digital twin layer uses the Unreal Engine 5 to drive the Unreal Building model to simulate operations based on the real-time internal building data, and uses the equipment maintenance model to predict the operating status of the equipment to obtain the prediction results, and then transmits the prediction results to the management level; The management layer generates management instructions based on the internal building data of the physical device layer and the prediction results of the digital twin layer, and transmits the management instructions to the physical device layer; the physical device layer controls the equipment in the building according to the management instructions.
2. The method for constructing a building control model based on digital twin according to claim 1, characterized in that: Obtaining building data, modeling the building using Revit software based on the building data, and obtaining the BIM of the building includes the following sub-steps: Obtain building geometry data: including the geometric shapes and dimensions of all building components, as well as the specific locations of all building components in space; Obtain building material data: including material types, material specifications and material properties of all building components; Obtain building structure data: including load performance and mechanical performance parameters of the building structure; Obtain building equipment data: including the model, specification, location and connection method of the building's electromechanical equipment and fire-fighting equipment; Based on the building construction data, the BIM of the building is established using Revit software, and the BIM of the building is obtained and saved. The building construction data includes: building geometry data, building material data, building structure data and building equipment data.
3. The method for constructing a building control model based on digital twin according to claim 2, characterized in that: Exporting the BIM data of a building from Revit software and importing the BIM data into Unreal Engine 5 to obtain an Unreal building model includes the following sub-steps: Install the corresponding version of the Datasmith plug-in based on the Revit software, use the Datasmith plug-in to export the BIM of the building, and obtain the BIM data of the building in the udatasmith format. Install the corresponding version of the Datasmith plug-in based on the Unreal 5 engine, use the Datasmith plug-in to import the BIM data of the building in the udatasmith format into the Unreal 5 engine, and obtain the BIM of the building under the Unreal 5 engine. Perform material rendering on the BIM of the building under the Unreal 5 engine according to the building material data, and obtain the Unreal building model after completion.
4. A building control model construction system based on digital twins, used to implement a building control model construction method based on digital twins as described in any one of claims 1 to 3, characterized in that: include: BIM module, Unreal Building module, Equipment Coding module, Model Building module, Digital Twin module and Building Control module; The BIM module includes a building data unit and a building modeling unit. The building data unit is used to obtain building construction data, and the building construction data includes building geometry data, building material data, building structure data, building equipment data and building external data. The building modeling unit includes Revit software, and Revit software is used to model the building based on the building construction data to obtain the BIM of the building. The Unreal Building Module includes Unreal 5 Engine, which is used to export BIM data of the building from Revit software and import the BIM data into Unreal 5 Engine to obtain an Unreal Building Model; The equipment coding module includes a coding establishment unit, an automatic coding unit and a data acquisition unit. The coding establishment unit is used to establish a building equipment coding standard. The automatic coding unit is used to map and code the equipment in the building to obtain equipment coding data. The data acquisition unit is used to obtain internal building data, which includes equipment parameter information, equipment operation information and equipment maintenance information. The model building module builds an equipment maintenance model based on the Informer model using the internal building data; The digital twin module uses OPC-UA technology to build a data interaction structure, and based on the device coding data, maps the internal building data to the virtual building model to obtain a digital twin model; The building control module includes a digital twin model, and controls the building based on the digital twin model.
5. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are performed.
