An intelligent building simulation method and system based on digital twin

Abstract

The present application provides an intelligent building simulation method and system based on digital twin. First, building structure information inside the building is collected, and then a twin mapping model inside the building is constructed; according to the topological structure characteristics between each sensing node and the associated elements of each sensing node, the association constraints of each sensing node in the building simulation process are determined, and further the simulation granularity of each sensing node is determined; then the dependency relationship of environmental changes in the building simulation is determined; the simulation control quantities of each virtual building scene in the twin mapping model are determined through the dependency relationship of environmental changes and the simulation granularity of each sensing node in the building simulation process, and all the simulation control quantities are loaded into the digital twin platform to update the twin mapping model of the target building. The solution of the present application can improve the collaborative response speed of multiple virtual building scenes in the digital twin system, thereby maintaining the data consistency between the virtual and real scenes.

Description

Technical Field

[0001] This application relates to the field of computer simulation technology. More specifically, this application relates to an intelligent building simulation method and system based on digital twin. Background Art

[0002] Computer simulation (i.e., building simulation in computer-aided design) is to conduct virtual tests and optimizations on various performances of a building by using advanced technologies. Among them, digital twin technology plays an important role in this process. Digital twin refers to creating a virtual copy of a building through sensors and real-time data, which can dynamically reflect the state of the building under different environmental and operating conditions. The application of this technology in building simulation enables designers to make more accurate predictions and adjustments before construction. In energy efficiency simulation, digital twin can monitor energy consumption in real time and optimize the configuration of air conditioning and heating systems. In structural simulation, it can provide real-time feedback on the loads and stresses borne by the building to ensure safety. In ventilation and acoustic simulation, digital twin can help designers analyze indoor air flow and noise control. By combining building simulation and digital twin technology, the building design process can be more efficient and accurate, thereby improving the performance and sustainability of the building.

[0003] Existing digital twin technology in the field of intelligent buildings is mainly applied to real-time monitoring of building energy efficiency, structural health, environmental control, etc. By collecting internal building data through a sensor network and generating a virtual model. However, although the intelligent sensor network in the building can collect structural information in real time, due to the large amount of data, the processing and transmission speeds often cannot meet the real-time requirements, resulting in data synchronization lag, leading to delays in the building simulation process and making it difficult to maintain consistency between multiple virtual scenarios and real scenarios, affecting the performance of the virtual building. Therefore, how to improve the collaborative response speed of multiple virtual building scenarios in the digital twin system to maintain data consistency between virtual and real scenarios has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an intelligent building simulation method and system based on digital twin, which can improve the collaborative response speed of multiple virtual building scenarios in the digital twin system, thereby maintaining data consistency between virtual and real scenarios.

[0005] In the first aspect, this application provides an intelligent building simulation method based on digital twin, including the following steps:

[0006] Set up an intelligent sensor network for the target building, collect the building structure information of the target building through the intelligent sensor network, import the building structure information into the digital twin platform, and then construct a twin mapping model of the target building;

[0007] Determine the association constraints of each sensor node in the building simulation process according to the topological structure characteristics among the sensor nodes in the intelligent sensing network and the association elements of each sensor node, and determine the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model;

[0008] Obtain the environmental parameters of the target building, and perform dependency association on each virtual building scene in the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation;

[0009] Determine the simulation control quantities of each virtual building scene in the twin mapping model through the dependency relationship of environmental changes and the simulation granularity of each sensor node in the building simulation process, and load all the simulation control quantities into the digital twin platform to update the twin mapping model of the target building.

[0010] In some embodiments, importing the building structure information into the digital twin platform and then constructing the twin mapping model of the target building specifically includes:

[0011] Preprocess the building structure information to obtain preprocessed building structure information;

[0012] Upload the preprocessed building structure information to the digital twin platform;

[0013] Initialize the building information tool of the digital twin platform;

[0014] Construct the twin mapping model of the target building through the preprocessed building structure information and the building information tool.

[0015] In some embodiments, determining the association constraints of each sensor node in the building simulation process according to the topological structure characteristics among the sensor nodes in the intelligent sensing network and the association elements of each sensor node specifically includes:

[0016] Perform topological analysis on the intelligent sensing network to obtain the topological structure characteristics among the sensing nodes in the intelligent sensing network;

[0017] Determine the dynamic association degree of each sensing node in the building simulation process according to the association elements of all sensing nodes;

[0018] Determine the association constraints of each sensing node in the building simulation process through the topological structure characteristics and the dynamic association degree of each sensing node in the building simulation process.

[0019] In some embodiments, determining the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model specifically includes:

[0020] Perform a linear fit on all the association constraints to obtain an association constraint fitting curve;

[0021] Determine the data feedback of each sensing node during the building simulation through all the digital twins within the twin mapping model;

[0022] Determine the simulation granularity of each sensing node during the building simulation according to the association constraint fitting curve and the data feedback of each sensing node during the building simulation.

[0023] In some embodiments, the dependency association of each virtual building scene within the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation specifically includes:

[0024] Extract the environmental relevance between each sensing node in the intelligent sensing network and each digital twin in each virtual building scene from the environmental parameters;

[0025] Determine the visual differences between each virtual building scene within the twin mapping model;

[0026] Determine the dependency relationship of environmental changes in the building simulation according to all the environmental relevances and the visual differences between each virtual building scene.

[0027] In some embodiments, determining the simulation control quantity of each virtual building scene within the twin mapping model through the dependency relationship of environmental changes and the simulation granularity of each sensor node during the building simulation specifically includes:

[0028] Cluster all the simulation granularities to obtain multiple simulation granularity clusters;

[0029] Select a virtual building scene from the twin mapping model as the selected virtual building scene;

[0030] Determine the simulation control quantity of the selected virtual building scene within the twin mapping model according to the simulation granularity of the sensing node corresponding to each digital twin within the selected virtual building scene, the dependency relationship of environmental changes, and all the simulation granularity clusters;

[0031] Continue to determine the simulation control quantity of the remaining virtual building scenes within the twin mapping model.

[0032] In some embodiments, the intelligent sensing network is a topological structure network composed of multiple sensing nodes.

[0033] In a second aspect, the present application provides an intelligent building simulation system based on digital twins, including:

[0034] A construction module for building an intelligent sensing network of a target building, collecting building structure information of the target building through the intelligent sensing network, importing the building structure information into a digital twin platform, and then constructing a twin mapping model of the target building;

[0035] A processing module for determining the association constraints of each sensor node in the building simulation process according to the topological structure characteristics between the sensor nodes in the intelligent sensing network and the associated elements of each sensor node, and determining the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model;

[0036] The processing module is further configured to obtain the environmental parameters of the target building, and perform dependency association on each virtual building scene in the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation;

[0037] An execution module for determining the simulation control quantities of each virtual building scene in the twin mapping model through the dependency relationship of environmental changes and the simulation granularity of each sensor node in the building simulation process, and loading all the simulation control quantities into the digital twin platform to update the twin mapping model of the target building.

[0038] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent building simulation method based on digital twins.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned intelligent building simulation method based on digital twins is implemented.

[0040] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0041] In the intelligent building simulation method and system based on digital twin provided by this application, first, an intelligent sensing network of the target building is established, and the building structure information of the target building is collected through the intelligent sensing network. The building structure information is imported into the digital twin platform, and then a twin mapping model of the target building is constructed; according to the topological structure characteristics between each sensor node in the intelligent sensing network and the associated elements of each sensor node, the association constraints of each sensor node in the building simulation process are determined, and the simulation granularity of each sensor node in the building simulation process is determined through all the association constraints and the twin mapping model; the environmental parameters of the target building are obtained, and the various virtual building scenes in the twin mapping model are dependently associated according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation; the simulation control quantities of the various virtual building scenes in the twin mapping model are determined through the dependency relationship of environmental changes and the simulation granularity of each sensor node in the building simulation process, and all the simulation control quantities are loaded into the digital twin platform to update the twin mapping model of the target building.

[0042] It can be seen that in this application, the simulation control quantities of the various virtual building scenes in the twin mapping model can be determined through the dependency relationship of environmental changes and the simulation granularity of each sensor node in the building simulation process; among them, first, by constructing an intelligent sensor network and collecting building structure information, the solution realizes accurate modeling of the target building. The structural data of the actual building is imported into the digital twin platform and a twin mapping model is constructed, enabling the virtual building to accurately reflect the physical characteristics of the actual building; then, by analyzing the topological structure and associated elements of each sensor node in the intelligent sensor network, the association constraints between the sensor nodes are determined. This link ensures precise control of the interaction between the sensor and the twin mapping model through a detailed division of the simulation granularity of each sensor node. This precise simulation granularity enables fine-grained coordination and feedback in the building simulation between different sensor nodes, enhancing the accurate simulation ability of the virtual building scene for the actual building environment; then, the environmental parameters of the target building are obtained, and the various virtual building scenes in the twin mapping model are dependently associated. The establishment of this dependency relationship enables the virtual scene to dynamically respond to environmental changes and adjust the virtual scene in the building simulation in real time. Through the dependent association, the twin model can better simulate the performance of the actual building under different environmental conditions, thereby ensuring the sensitivity and adaptability of the virtual building scene to environmental changes; finally, by combining the dependency relationship of environmental changes with the simulation granularity of the sensor nodes, the simulation control quantities of the virtual building scene are determined and these control quantities are loaded into the digital twin platform to update the twin mapping model of the target building; in summary, the solution of this application can improve the collaborative response speed of multiple virtual building scenes in the digital twin system, thereby maintaining the data consistency between the virtual and real scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an exemplary flowchart of a digital twin-based intelligent building simulation method shown in some embodiments of the present application;

[0044] Figure 2 is a schematic diagram of the communication network structure of a sensing node shown in some embodiments of the present application;

[0045] Figure 3 is a schematic diagram of the process of determining association constraints in some embodiments of the present application;

[0046] Figure 4 is a schematic diagram of the structure of a digital twin-based intelligent building simulation system in some embodiments of the present application;

[0047] Figure 5 is a schematic diagram of the structure of a computer device for implementing a digital twin-based intelligent building simulation method shown in some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0049] Refer to Figure 1 , which is an exemplary flowchart of a digital twin-based intelligent building simulation method shown in some embodiments of the present application. The digital twin-based intelligent building simulation method 100 mainly includes the following steps:

[0050] In step 101, an intelligent sensing network of the target building is established, and the building structure information of the target building is collected through the intelligent sensing network. The building structure information is imported into the digital twin platform, and then a twin mapping model of the target building is constructed.

[0051] Specifically, a distributed topology structure is adopted to form a centralized network by covering different areas in the building with multiple sensing nodes, and the obtained centralized network is used as the intelligent sensing network. Then, the building structure information in the target building is collected through the intelligent sensing network. In other embodiments, other methods may also be used to achieve this, which will not be elaborated here.

[0052] It should be noted that the intelligent sensing network in the present application is a topology network composed of multiple sensing nodes. The types of sensing nodes include stereo vision sensors, temperature and humidity sensors, strain gauges, light sensors, etc. Refer to Figure 2, This figure is a schematic diagram of the communication network structure of the sensing nodes shown in some embodiments of the present application. Among the network communication standards of the sensing nodes, IEEE802.15.4 is the most widely used one, which defines the physical layer and the media access control layer for communication between sensing nodes. To improve the adaptability and flexibility of the network, this standard also introduces an adaptive layer. Above these basic layers are the network layer and the application layer, which provide network services and application services. In addition, 6LoWPAN (IPv6 Low-Power Wireless Personal Area Network) as a network protocol enables the intelligent sensing network to utilize the IPv6 protocol stack to achieve seamless connection with the Internet. The realization of the functions of the entire network depends on the sensing nodes on the limited nodes in the network. These sensing nodes are responsible for data collection, processing, and transmission, and are the core components of the intelligent sensing network.

[0053] In addition, it should be noted that the building structure information described in the present application is the geometric information of the building internal structure, the strain information of the building internal structure, and the pressure information inside the building.

[0054] In some embodiments, importing the building structure information into the digital twin platform and then constructing the twin mapping model of the target building can be achieved by the following steps:

[0055] Preprocess the building structure information to obtain preprocessed building structure information;

[0056] Upload the preprocessed building structure information to the digital twin platform;

[0057] Initialize the building information tool of the digital twin platform;

[0058] Construct the twin mapping model of the target building through the preprocessed building structure information and the building information tool.

[0059] When specifically implemented, first, preprocess the building structure information. This step includes processes such as denoising, formatting, and standardization, aiming to ensure that the collected building structure information can be smoothly compatible with the digital twin platform; second, upload the preprocessed building structure information to the database of the digital twin platform; then, after the digital twin platform starts the Building Information Modeling (BIM) and the 3D modeling engine; finally, generate a virtual model of the target building in combination with the preprocessed building structure information, and map it to the real target building to achieve the digital twin of the building, and use the obtained virtual model as the twin mapping model of the target building. In other embodiments, other methods can also be used to achieve this, which will not be elaborated here.

[0060] It should be noted that the twin mapping model of the target building described in this application represents a digital mapping model that simulates the target building in a virtual environment. The twin mapping model maps the internal structure, functions, and behaviors of the building into the digital space through data integration, and continuously synchronizes the state and behavior changes of the physical building. By establishing the twin mapping model, various building parameters and dynamic changes of the target building can be monitored and optimized in real time. In addition, the twin mapping model contains multiple virtual building scenarios, and each virtual building scenario contains multiple digital twins. The digital twin is a virtual mapping model of the sensing node.

[0061] In step 102, according to the topological structure characteristics between each sensor node in the intelligent sensing network and the associated elements of each sensor node, the association constraints of each sensor node in the building simulation process are determined. Through all the association constraints and the twin mapping model, the simulation granularity of each sensor node in the building simulation process is determined.

[0062] In some embodiments, refer to Figure 3 As shown, this figure is a schematic flow chart of determining association constraints in some embodiments of this application. In this embodiment, the association constraints of each sensor node in the building simulation process can be determined according to the topological structure characteristics between each sensor node in the intelligent sensing network and the associated elements of each sensor node, and can be implemented by the following steps:

[0063] First, in step 1021, a topological analysis of the intelligent sensing network is performed to obtain the topological structure characteristics between each sensing node in the intelligent sensing network.

[0064] Secondly, in step 1022, according to the associated elements of all sensing nodes, the dynamic association degree of each sensing node in the building simulation process is determined.

[0065] Then, in step 1023, through the topological structure characteristics and the dynamic association degree of each sensing node in the building simulation process, the association constraints of each sensing node in the building simulation process are determined.

[0066] It should be noted that the topological structure characteristics described in this application represent the characteristic values of the information flow path in the network topology structure composed of each sensing node.

[0067] In addition, it should also be noted that the associated elements described in this application represent the characteristic values on which the sensing nodes in the intelligent sensing network depend on each other, and can be obtained by performing a correlation analysis on the data of different sensing nodes arranged at the same position in the target building. In other embodiments, other methods can be used to implement this, and it is not limited here.

[0068] In specific implementation, first, the logical connections between each pair of sensor nodes in the intelligent sensing network are regarded as edges to construct a network topology structure diagram. Among them, the logical connections can use the connection information of the sensor nodes, such as the network bandwidth between the sensor nodes. Then, the Dijkstra shortest path algorithm in graph theory is used to calculate the shortest paths between each pair of sensor nodes, and the sum of the shortest path lengths between each pair of sensor nodes is used as the topological structure feature between each pair of sensor nodes in the intelligent sensing network. Secondly, a sensor node is selected as the selected sensor node, and then the associated factor of the selected sensor node is divided by the associated factor of the sensor node closest to the selected sensor node, and the obtained value is used as the dynamic association degree of the selected sensor node in the building simulation process. Then, the dynamic association degrees of the remaining sensor nodes in the building simulation process are determined. Then, the dynamic association degree of each sensor node in the building simulation process is multiplied by the topological structure feature, and the obtained values are used as the association constraints of each sensor node in the building simulation process. In other embodiments, other methods can also be used for implementation, which are not limited herein.

[0069] It should be noted that the association constraint described in this application represents a parameter that restricts the information interaction between different sensor nodes in the building simulation process. Through the association constraint, the association relationship and interaction boundary between the sensor nodes can be clarified, ensuring that the sensors can cooperate efficiently, reducing redundant calculations and ineffective communications, thereby improving the operating efficiency of the system.

[0070] In some embodiments, the simulation granularity of each sensor node in the building simulation process can be determined through all the association constraints and the twin mapping model by the following steps:

[0071] Perform linear fitting on all the association constraints to obtain an association constraint fitting curve;

[0072] Determine the data feedback of each sensor node in the building simulation process through all the digital twins in the twin mapping model;

[0073] Determine the simulation granularity of each sensor node in the building simulation process according to the association constraint fitting curve and the data feedback of each sensor node in the building simulation process.

[0074] In specific implementation, first, an existing linear fitting algorithm (such as the least squares support vector machine algorithm) is used to perform linear fitting on all association constraints, and the fitted curve is used as the association constraint fitting curve. Each value on the association constraint fitting curve is used as an association constraint fitting value, and each association constraint fitting value corresponds to an association constraint. Secondly, the Kalman filtering algorithm is used to perform state estimation on the data obtained by all digital twins in the twin mapping model, and the values obtained by the state estimation are used as the data feedback of the sensing nodes corresponding to each digital twin during the building simulation process. Then, a sensing node is selected as the selected sensing node. The absolute value is taken after subtracting the association constraint fitting value corresponding to the association constraint of the selected sensing node from the association constraint of the selected sensing node. The value obtained by taking the absolute value is divided by the data feedback of the selected sensing node during the building simulation process, and the value obtained by the division is used as the simulation granularity of the selected sensing node during the building simulation process. The simulation granularity of the remaining sensing nodes during the building simulation process is continuously determined. In other embodiments, other methods can also be used for implementation, which will not be elaborated here.

[0075] It should be noted that the data feedback in this application refers to the parameters of the operating state of the digital twin corresponding to the monitoring sensing node during the building simulation process; the simulation granularity refers to the fineness degree to which the data collected by the sensing node is decomposed and processed during the building simulation process. The simulation granularity determines the accuracy and refinement degree of various parameters, feedbacks, and regulations in the building simulation system. It not only reflects the detail accuracy of the internal physical environment of the building but also affects the collaborative response speed and data consistency of each building environment in multiple virtual scenarios.

[0076] In step 103, the environmental parameters of the target building are obtained, and each virtual building scene in the twin mapping model is dependently associated according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation.

[0077] In specific implementation, the environmental parameters of the target building are obtained through the management system of the intelligent sensing network. The environmental parameters refer to the environmental change data sensed by each sensing node in the building environment, and the environmental change data includes the data composed of temperature, humidity, and light intensity at intervals of one minute in the past hour.

[0078] It should be noted that each digital twin in each virtual building scene in the twin mapping model of this application includes virtual environmental change data, where the virtual environmental change data refers to the virtual data composed of temperature, humidity, and light intensity at intervals of one minute in the past hour in the twin mapping model.

[0079] In some embodiments, the dependency association of each virtual building scene in the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in building simulation can be implemented by the following steps:

[0080] Extract the environmental relevance between each sensor node in the intelligent sensing network and each digital twin in each virtual building scene in the twin mapping model from the environmental parameters;

[0081] Determine the visual differences between each virtual building scene in the twin mapping model;

[0082] Determine the dependency relationship of environmental changes in building simulation based on all the environmental relevance and the visual differences between each virtual building scene.

[0083] It should be noted that the visual difference described in this application represents the difference characteristics in visual performance of different virtual building scenes.

[0084] Specifically, during implementation, first, obtain the virtual environmental change data of each digital twin in each virtual building scene in the twin mapping model, select a sensor node from the intelligent sensing network as the selected sensor node, calculate the Pearson correlation coefficient between the environmental change data of the selected sensor node and the virtual environmental change data of the digital twin corresponding to the selected sensor node, continue to determine the Pearson correlation coefficient between the environmental change data of the remaining sensor nodes and the virtual environmental change data of the digital twin corresponding to the selected sensor node, then sum all the Pearson correlation coefficients, and use the obtained sum value as the global correlation coefficient. Further, divide the Pearson correlation coefficient between the virtual environmental change data of each sensor node corresponding digital twin by the global correlation coefficient, and use the obtained quotient value as the environmental relevance between each sensor node and the corresponding digital twin in each virtual building scene in the twin mapping model; second, use image difference detection technology (such as structural similarity) to compare each virtual building scene in the twin mapping model at different times, then calculate the average value of the values obtained by comparing each virtual building scene at different times, further sum the obtained average values, and use the obtained sum value as the visual difference between each virtual building scene; then, divide each environmental relevance by the visual difference, then sum all the obtained quotient values, and use the obtained sum value as the dependency relationship of environmental changes in building simulation.

[0085] It should be noted that the dependency relationship of environmental changes described in this application represents the parameter of environmental co - change generated by each virtual building scene in the twin mapping model being driven by the environmental change data in the target building.

[0086] In step 104, the simulation control quantities of each virtual building scene in the twin mapping model are determined based on the dependency relationship of the environmental changes and the simulation granularity of each sensor node during the building simulation process. All the simulation control quantities are loaded into the digital twin platform to update the twin mapping model of the target building.

[0087] In some embodiments, the determination of the simulation control quantities of each virtual building scene in the twin mapping model based on the dependency relationship of the environmental changes and the simulation granularity of each sensor node during the building simulation process can be implemented by the following steps:

[0088] Cluster all the simulation granularities to obtain multiple simulation granularity clusters;

[0089] Select a virtual building scene from the twin mapping model as the selected virtual building scene;

[0090] Determine the simulation control quantity of the selected virtual building scene in the twin mapping model based on the simulation granularity of the sensing node corresponding to each digital twin in the selected virtual building scene, the dependency relationship of the environmental changes, and all the simulation granularity clusters;

[0091] Continue to determine the simulation control quantities of the remaining virtual building scenes in the twin mapping model.

[0092] Specifically, during implementation, first, use the DBSCAN clustering algorithm to cluster all the simulation granularities to obtain multiple clusters, and regard the obtained clusters as simulation granularity clusters. Each simulation granularity cluster consists of multiple simulation granularities. Secondly, select a digital twin from the selected virtual building scene as the selected digital twin, sum all the simulation granularities in the simulation granularity cluster to which the simulation granularity of the sensing node corresponding to the selected digital twin belongs during the building simulation process, then divide the obtained sum by the dependency relationship of the environmental changes, and regard the obtained value as the simulation coordination degree of the selected digital twin. Continue to determine the simulation coordination degrees of the remaining digital twins in the selected digital twin. Further, perform a difference operation on the simulation coordination degrees of all the digital twins in the selected virtual building scene, then sum all the obtained difference values, and regard the obtained sum as the simulation control quantity of the selected virtual building scene. Continue to determine the simulation control quantities of the remaining virtual building scenes in the twin mapping model. In other embodiments, other methods can also be used for implementation, which are not limited here.

[0093] It should be noted that the simulation control quantity described in this application represents the parameter value for the collaborative work between the digital twin and the environmental condition elements in the virtual building scene in the control twin mapping model. Through the simulation control quantity, the response speed between these virtual scenes can be improved, ensuring that the changes occurring in one scene can be quickly and accurately transmitted and reflected in other scenes.

[0094] In specific implementation, loading all the simulation control quantities into the digital twin platform and then updating the twin mapping model of the target building can be achieved in the following way: Use the RESTful API interface to transmit all the simulation control quantities to the digital twin platform. Take the simulation control quantity of each virtual building scene in the twin mapping model as the compensation coefficient of each digital twin in each virtual building scene, and use the time delay estimation technology (such as the synchronous clock protocol) to compensate for the time delay of the data of each digital twin in each virtual building scene, so as to complete the update of the twin mapping model of the target building. In other embodiments, other methods can also be used to achieve this, which will not be elaborated here.

[0095] In addition, on the other hand of this application, in some embodiments, this application provides an intelligent building simulation system based on digital twins. Refer to Figure 4 , this figure is a schematic structural diagram of an intelligent building simulation system based on digital twins according to some embodiments of this application. The intelligent building simulation system 400 based on digital twins includes: a construction module 401, a processing module 402, and an execution module 403, which are described as follows:

[0096] The construction module 401. In this application, the acquisition module 401 is mainly used to form the intelligent sensing network of the target building, collect the building structure information of the target building through the intelligent sensing network, import the building structure information into the digital twin platform, and then construct the twin mapping model of the target building;

[0097] The processing module 402. In this application, the processing module 402 is used to determine the association constraints of each sensor node in the building simulation process according to the topological structure characteristics between the sensor nodes in the intelligent sensing network and the associated elements of each sensor node, and determine the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model;

[0098] It should be noted that the processing module 402 in this application is also used to obtain the environmental parameters of the target building, and perform dependency association on each virtual building scene in the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation;

[0099] Execution module 403. In this application, the execution module 403 is mainly used to determine the simulation control amounts of each virtual building scene in the twin mapping model based on the dependency relationship of the environmental changes and the simulation granularity of each sensor node during the building simulation process, and load all the simulation control amounts into the digital twin platform to update the twin mapping model of the target building.

[0100] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent building simulation method based on digital twins.

[0101] In some embodiments, refer to Figure 5 , this figure is a schematic structural diagram of a computer device for implementing the intelligent building simulation method based on digital twins according to some embodiments of this application. The intelligent building simulation method based on digital twins in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0102] The processor 501 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the intelligent building simulation method based on digital twins in this application.

[0103] The communication bus 502 can be used to transmit information between the above components.

[0104] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0105] Among them, the memory 503 is used to store the program code for executing the solution of this application and is controlled by the processor 501 for execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The methods described in the above method embodiments can be implemented by one or more software modules in the program code in the processor 501 and the memory 503.

[0106] The communication interface 504 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0107] In a specific implementation, as an embodiment, the computer device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0108] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0109] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-described intelligent building simulation method based on digital twins is implemented.

[0110] In summary, in the intelligent building simulation method and system based on digital twins disclosed in the embodiments of the present application, first, an intelligent sensing network of the target building is formed, and the building structure information of the target building is collected through the intelligent sensing network, and the building structure information is imported into the digital twin platform, and then a twin mapping model of the target building is constructed; according to the topological structure characteristics between each sensor node in the intelligent sensing network and the associated elements of each sensor node, the association constraints of each sensor node in the building simulation process are determined, and the simulation granularity of each sensor node in the building simulation process is determined through all the association constraints and the twin mapping model; the environmental parameters of the target building are obtained, and each virtual building scene in the twin mapping model is dependently associated according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation; the simulation control quantities of each virtual building scene in the twin mapping model are determined through the dependency relationship of environmental changes and the simulation granularity of each sensor node in the building simulation process, and all the simulation control quantities are loaded into the digital twin platform to update the twin mapping model of the target building. The solution of the present application can improve the collaborative response speed of multiple virtual building scenes in the digital twin system, so as to maintain the data consistency between the virtual and real scenes.

[0111] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0112] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for simulating an intelligent building based on digital twins, characterized in that: The steps include: Establishing an intelligent sensor network of the target building, collecting the building structure information of the target building through the intelligent sensor network, importing the building structure information into the digital twin platform, and then constructing a twin mapping model of the target building; Determine the association constraints of each sensor node in the building simulation process according to the topological structure characteristics between each sensor node in the intelligent sensor network and the association elements of each sensor node, and determine the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model; Acquire environmental parameters of the target building, and perform dependency association on each virtual building scene in the twin mapping model according to the environmental parameters to obtain the dependency relationship of environmental changes in the building simulation; Determine the simulation control quantity of each virtual building scene in the twin mapping model through the dependency relationship of the environmental changes and the simulation granularity of each sensor node in the building simulation process, load all the simulation control quantities into the digital twin platform, and then update the twin mapping model of the target building; Among them, the dependency association of each virtual building scene in the twin mapping model is performed according to the environmental parameters to obtain the dependency relationship of the environmental change in the building simulation, which specifically includes: Extracting the environmental correlation between each sensor node in the intelligent sensor network and each digital twin in each virtual building scene in the twin mapping model from the environmental parameters; Determining visual differences between virtual building scenes within the twin mapping model; Determine the dependencies of environmental changes in building simulations based on all environmental relevance and visual differences between various virtual building scenes; Among them, determining the simulation control amount of each virtual building scene in the twin mapping model through the dependency relationship of the environmental changes and the simulation granularity of each sensor node in the building simulation process specifically includes: Clustering all simulation granularities to obtain multiple simulation particle clusters; Selecting a virtual building scene from the twin mapping model as a selected virtual building scene; Determining the simulation control amount of the selected virtual building scene in the twin mapping model according to the simulation granularity of the sensor node corresponding to each digital twin in the selected virtual building scene during the building simulation process, the dependency of the environmental change and all simulation particle clusters; Continue to determine the simulation control quantity of the remaining virtual building scenes in the twin mapping model.

2. The method according to claim 1, characterized in that Importing the building structure information into the digital twin platform and then constructing a twin mapping model of the target building specifically includes: Preprocessing the building structure information to obtain building structure preprocessing information; Uploading the building structure preprocessing information to the digital twin platform; Initializing a building information tool of the digital twin platform; A twin mapping model of the target building is constructed by using the building structure preprocessing information and the building information tool.

3. The method according to claim 1, characterized in that Determining the association constraints of each sensor node in the building simulation process according to the topological structure characteristics between each sensor node in the intelligent sensor network and the association elements of each sensor node specifically includes: Performing topological analysis on the intelligent sensor network to obtain topological structure characteristics between various sensor nodes in the intelligent sensor network; Determine the dynamic correlation degree of each sensor node in the building simulation process according to the correlation factors of all sensor nodes; The association constraint of each sensor node in the building simulation process is determined by the topological structure characteristics and the dynamic association degree of each sensor node in the building simulation process.

4. The method according to claim 1, characterized in that The simulation granularity of each sensor node in the building simulation process is determined by all associated constraints and the twin mapping model, specifically including: Perform linear fitting on all associated constraints to obtain an associated constraint fitting curve; Determine the data feedback of each sensor node during the building simulation process through all digital twins in the twin mapping model; The simulation granularity of each sensor node in the building simulation process is determined according to the associated constraint fitting curve and the data feedback of each sensor node in the building simulation process.

5. The method according to claim 1, characterized in that The intelligent sensor network is a topological structure network composed of multiple sensor nodes.

6. An intelligent building simulation system based on digital twins, the system adopts the method described in any one of claims 1 to 5 to perform intelligent building simulation, characterized in that: The system includes: A construction module is used to establish an intelligent sensor network of the target building, collect the building structure information of the target building through the intelligent sensor network, import the building structure information into the digital twin platform, and then build a twin mapping model of the target building; A processing module, used for determining the association constraints of each sensor node in the building simulation process according to the topological structure characteristics between each sensor node in the intelligent sensor network and the association elements of each sensor node, and determining the simulation granularity of each sensor node in the building simulation process through all the association constraints and the twin mapping model; The processing module is further used to obtain environmental parameters of the target building, and to perform dependency association on each virtual building scene in the twin mapping model according to the environmental parameters to obtain dependency relationships of environmental changes in the building simulation; An execution module is used to determine the simulation control quantity of each virtual building scene in the twin mapping model through the dependency of the environmental changes and the simulation granularity of each sensor node in the building simulation process, load all the simulation control quantities into the digital twin platform and then update the twin mapping model of the target building.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the digital twin-based intelligent building simulation method described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the digital twin-based intelligent building simulation method as described in any one of claims 1 to 5 is implemented.

Images