Digital twin simulation test method and system applied to building system

Abstract

The application provides a digital twin simulation test method and system applied to a building system. First, a knowledge graph of physical parameters of the building system is constructed, generating a physical parameter knowledge graph containing structure, equipment, environmental parameter nodes and various associated edges. Then, a digital twin graph model is constructed based on the knowledge graph, containing different parameter graph node layers and interlayer associated edge sets. Then, a graph test scene configuration sequence is generated according to the model, containing node parameter disturbance rules, etc. The sequence is input into the model to perform graph coupling simulation test, generating a graph test response dataset containing node response sequences, etc. Finally, a digital twin simulation test evaluation report is output based on the dataset, covering node response characteristics, etc. The method can comprehensively and accurately simulate the building system, improving test efficiency, accuracy and comprehensiveness.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology, and more specifically, to a digital twin simulation testing method and system for building systems. Background Technology

[0002] In the field of building systems, with the expansion of building scale and the increasing complexity of functions, higher requirements are placed on the performance monitoring, fault prediction, and optimized management of building systems. Traditional building system testing methods mainly rely on the construction of actual physical environments and on-site testing. This approach is not only costly, requiring a large amount of manpower, material resources, and time for equipment installation, debugging, and operation, but also has a long testing cycle, making it difficult to conduct comprehensive testing of various complex scenarios in a short period of time.

[0003] Meanwhile, traditional testing methods struggle to accurately grasp the complex relationships between various parameters within a building system, and cannot effectively simulate the impact of different parameter changes on the entire system. This results in inaccurate and incomplete test results, failing to meet the development needs of intelligent and refined management of modern building systems. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a digital twin simulation testing method for building systems, the method comprising:

[0005] Perform knowledge graph construction and processing of building system physical parameters to generate a physical parameter knowledge graph;

[0006] Based on the physical parameter knowledge graph, a digital twin graph model generation process is performed to construct a digital twin graph model of the building system;

[0007] A test scenario configuration sequence is generated based on the set of inter-layer related edges and node interaction paths of the digital twin graph model.

[0008] The graph test scenario configuration sequence is input into the digital twin graph model to perform graph coupling simulation testing, generating a graph test response dataset;

[0009] Based on the graph test response dataset, the graph structure test results are analyzed, and a digital twin simulation test evaluation report of the building system is output. The digital twin simulation test evaluation report includes the response characteristics of graph nodes, the influence characteristics of associated edges, and the risk characteristics of abnormal path graphs.

[0010] In another aspect, embodiments of the present invention also provide a digital twin simulation testing system for building systems, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0011] Based on the above, this invention constructs a physical parameter knowledge graph containing structural parameter nodes, equipment parameter nodes, environmental parameter nodes, and various associated edges. A digital twin graph model generated based on this physical parameter knowledge graph, with its hierarchical structure and inter-layer associated edge set, realizes parameter transmission and logical reasoning between different parameter layers, more realistically simulating the actual operation of the building system. According to the graph test scenario configuration sequence generated by the model, various test scenarios can be flexibly set, enhancing the diversity and relevance of the tests. Inputting the configuration sequence into the model to execute graph coupling simulation tests can quickly obtain a comprehensive graph test response dataset. Finally, based on the digital twin simulation test evaluation report output by this dataset, the building system performance is evaluated from multiple dimensions such as node response, associated edge impact, and abnormal path risk, significantly improving the efficiency, accuracy, and comprehensiveness of building system testing. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the execution flow of the digital twin simulation testing method for building systems provided in this embodiment of the invention.

[0013] Figure 2 This is a schematic diagram of exemplary hardware and software components of a digital twin simulation testing system for building systems provided in an embodiment of the present invention. Detailed Implementation

[0014] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a digital twin simulation testing method for building systems provided in one embodiment of the present invention. The following is a detailed description of this digital twin simulation testing method for building systems.

[0015] Step S110: Perform knowledge graph construction processing of building system physical parameters to generate a physical parameter knowledge graph. The physical parameter knowledge graph includes structural parameter nodes, equipment parameter nodes, environmental parameter nodes, and inter-node association edges. The inter-node association edges include location association edges, influence association edges, and interaction association edges.

[0016] In this embodiment, a commercial office building is used as the unified application scenario. The physical parameter knowledge graph can display the inherent relationships between the building's structure, equipment, and environment. First, it's important to clarify that structural parameter nodes represent various structural elements of the building, such as walls, floors, beams, and columns; equipment parameter nodes cover various equipment within the building, such as elevators, air conditioning, and lighting systems; and environmental parameter nodes reflect the environmental conditions of the building, such as indoor temperature, humidity, and light intensity. The edges connecting these nodes are the links between them. Location-related edges reflect the spatial relationship between the structure and equipment, such as elevators being installed on specific floors and in specific shaft locations; influence-related edges describe the impact of equipment on the environment or the environment on equipment, such as the operation of air conditioning changing indoor temperature; and interaction-related edges represent the interaction between the environment and the structure, such as outdoor humidity affecting the material properties of the walls.

[0017] Step S111: Collect physical parameter data of the building system, including structural parameter data, equipment parameter data and environmental parameter data.

[0018] In this step, collecting physical parameter data for commercial office buildings is a multi-channel and multi-method process. Structural parameter data can be obtained from the building's design drawings and construction documents. These documents record detailed information such as wall thickness, floor height, and beam and column dimensions. For example, design drawings clearly indicate the height of each floor and the material and thickness of the walls. For equipment parameter data, basic parameters can be obtained from the equipment's technical specifications, such as the load capacity and operating speed of elevators, and the cooling capacity and power of air conditioners.

[0019] On the other hand, the equipment's built-in monitoring system can collect real-time operational data, such as elevator running time and actual air conditioning power consumption. For environmental parameters, various sensors need to be installed throughout the building. Temperature, humidity, and light sensors should be installed on different floors and in different areas to obtain real-time data on indoor temperature, humidity, and light intensity. Simultaneously, outdoor meteorological data for the building's location, such as outdoor temperature, wind speed, and rainfall, can be obtained from meteorological departments.

[0020] Step S112: Perform graph node extraction processing on the structural parameter data to extract structural parameter entities and entity attributes, and generate structural parameter nodes. The structural parameter nodes include node identifiers, parameter types, and attribute description information.

[0021] Step S1121: Perform data cleaning on the collected structural parameter data to remove duplicate data records and invalid data fields, and retain valid data containing structural feature descriptions.

[0022] In the context of commercial office buildings, structural parameter data may be collected from multiple sources, such as design drawings, construction records, and subsequent maintenance documents. This data may contain duplicates and invalid data. For example, both design drawings and construction records may record the thickness of a wall, but due to differences in recording time and method, there may be inconsistencies in data format or slight differences in values. Additionally, some data fields may be invalid due to recording errors or incompleteness; for instance, a record might only record the wall's length without its width and thickness. To remove these duplicate and invalid data, key information such as the wall's location and dimensions can be compared to identify duplicate records, and the most accurate and complete one can be retained. Invalid data fields can be judged and corrected based on the data's context and other relevant records; if correction is not possible, they should be deleted. After data cleaning, the retained data contains valid descriptions of structural features, which will be used for subsequent entity recognition and attribute extraction.

[0023] Step S1122: Perform entity recognition processing on the cleaned structural parameter data, and identify keywords representing structural entities in the data based on the preset structural parameter entity dictionary. The structural entities include wall entities, floor entities, beam and column entities, and spatial area entities.

[0024] The cleaned structural parameter data needs to undergo entity recognition to identify keywords representing structural entities. A pre-defined structural parameter entity dictionary is a collection of names for various structural entities. In a commercial office building scenario, when the data contains "second-floor wall," comparison with the structural parameter entity dictionary identifies the floor entity corresponding to "second floor" and the wall entity corresponding to "wall." The dictionary defines the name of each entity and related synonyms and near-synonyms to improve the accuracy of entity recognition. For the terms "column" and "beam-column," the dictionary clearly states that they both belong to the beam-column entity category. By traversing the cleaned structural parameter data and matching its words with keywords in the dictionary, the structural entities contained in the data are identified.

[0025] Step S1123: Perform attribute extraction processing on the identified structural entities to extract attribute information for each structural entity from the data. The attribute information includes entity size attributes, material attributes, location attributes, and connection attributes.

[0026] After identifying the structural entities, it is necessary to extract the attribute information of each entity from the data. For wall entities in commercial office buildings, their attribute information includes multiple aspects. Dimensional attributes can be obtained from design drawings, such as the wall's length, width, and thickness. Material attributes can be obtained from construction documents or material inspection reports, indicating whether the wall is constructed of brick, concrete, or other materials. Location attributes can be determined based on the floor level and specific coordinates, specifying the wall's location on which floor. Connection attributes describe how the wall connects to other structural entities, whether it is directly connected or connected via beams and columns. For floor entities, their attribute information may include the floor's height, area, and connection relationships with floors above and below. By analyzing the data, these attribute information for each structural entity are extracted.

[0027] Step S1124: Assign a unique node identifier to each structural entity. The node identifier consists of an entity type prefix and a sequence number.

[0028] To accurately identify each structural entity in the knowledge graph, a unique node identifier needs to be assigned to each. In the construction of structural parameter nodes for a commercial office building, the node identifier consists of an entity type prefix followed by a sequence number. For a wall entity, the node identifier is prefixed with "wall-", followed by a sequence number, such as "wall-01", "wall-02", etc. This identification method clearly indicates the entity type represented by the node and distinguishes different entities of the same type through the sequence number. For a floor entity, the node identifier might be "floor-01", "floor-02", etc. By assigning a unique node identifier to each identified structural entity in this way, it is easier to manage and query these nodes in the knowledge graph.

[0029] Step S1125: Classify the nodes into parameter types according to the type of structural entity. The parameter types include wall parameter types, floor parameter types, beam and column parameter types, and spatial area parameter types.

[0030] After assigning node identifiers to structural entities, it is necessary to classify the nodes by parameter type according to the type of structural entity. In commercial office buildings, different types of structural entities have different parameter characteristics. Nodes of the wall parameter type mainly focus on attributes such as wall size, material, location, and connection; nodes of the floor parameter type focus on attributes such as floor height, area, and load-bearing capacity; nodes of the beam and column parameter type focus on attributes such as beam and column size, strength, and material; and nodes of the space area parameter type involve attributes such as space size, purpose, and lighting. By classifying nodes by parameter type, these structural parameter nodes can be organized and managed more clearly, and targeted queries and analyses in the knowledge graph are also facilitated.

[0031] Step S1126: Integrate the node identifier, parameter type and extracted attribute information to generate a structural parameter node. The attribute description information of the structural parameter node includes entity size attribute value, material attribute value, position attribute value and connection attribute value.

[0032] After completing node identifier assignment and parameter type classification, the node identifiers, parameter types, and extracted attribute information are integrated to generate structural parameter nodes. In the scenario of a commercial office building, for a wall node, its node identifier is "Wall-01", the parameter type is wall parameter type, and the attribute description information includes the wall's dimensional attribute values ​​(such as length, width, and thickness), material attribute values ​​(such as bricks), location attribute values ​​(such as being located at a certain position on the second floor), and connection attribute values ​​(such as being connected to other walls via concrete). By integrating this information, a complete structural parameter node is formed, which can comprehensively describe the characteristics and attributes of the wall.

[0033] Step S1127: Perform attribute integrity verification on the generated structural parameter nodes to ensure that each node contains at least one core attribute. Perform attribute completion processing on nodes that are missing core attributes, and verify again after completion, until all structural parameter nodes pass the attribute integrity verification.

[0034] The generated structural parameter nodes need to undergo attribute integrity verification to ensure that each node contains at least one core attribute. In commercial office buildings, for wall nodes, the core attributes might be thickness and material. If a wall node only contains the location attribute and lacks the thickness and material attributes, then the wall node does not meet the attribute integrity requirements. For nodes missing core attributes, attribute completion processing needs to be performed. Missing attribute information can be obtained by consulting relevant design documents, construction records, or conducting on-site measurements. After completing the attributes, the node is verified again to check if any core attributes are still missing. This process is repeated until all structural parameter nodes pass the attribute integrity verification, ensuring the quality and accuracy of the structural parameter nodes.

[0035] Step S113: Perform graph node extraction processing on the device parameter data to extract device parameter entities and entity attributes, and generate device parameter nodes. The device parameter nodes include node identifier, parameter type and attribute description information.

[0036] In this step, graph node extraction is performed on the equipment parameter data of the commercial office building. First, the equipment parameter data is cleaned to remove duplicate and invalid data. This data may come from equipment manuals, monitoring systems, and maintenance records, which may contain duplicate operating data or incorrect parameter records. After cleaning, entity recognition is performed on the equipment parameter data, identifying keywords representing equipment entities based on a pre-defined equipment parameter entity dictionary, such as elevators, air conditioning, and lighting systems. Then, attribute extraction is performed on the identified equipment entities, extracting their attribute information, including equipment model, power, and operating parameters. A unique node identifier is assigned to each equipment entity, such as "Elevator-01" or "Air Conditioner-02," and nodes are categorized by parameter type according to equipment type, such as elevator parameter type or air conditioning parameter type. The node identifier, parameter type, and extracted attribute information are integrated to generate equipment parameter nodes. Finally, attribute integrity is verified for each equipment parameter node to ensure that each node contains at least one core attribute; for example, the core attributes of an elevator node might be load capacity and operating speed.

[0037] Step S114: Perform graph node extraction processing on the environmental parameter data to extract environmental parameter entities and entity attributes, and generate environmental parameter nodes. The environmental parameter nodes include node identifier, parameter type and attribute description information.

[0038] For environmental parameter data from commercial office buildings, graph node extraction is performed in this step. First, the environmental parameter data is cleaned to remove potential anomalies and duplicate records. This data comes from sensors and meteorological departments within the building, and outliers may occur due to sensor malfunctions or data transmission problems. After cleaning, entity recognition is performed based on a pre-defined environmental parameter entity dictionary to identify environmental entities such as indoor temperature, humidity, and light intensity. Next, attribute extraction is performed on the identified environmental entities to extract attribute information, such as the measurement time of temperature and the range of humidity variation. A unique node identifier is assigned to each environmental entity, such as "Indoor Temperature-01" or "Humidity-02," and the nodes are categorized by parameter type according to the type of environmental entity, such as temperature parameter type, humidity parameter type, etc. The node identifier, parameter type, and extracted attribute information are integrated to generate environmental parameter nodes. Then, the attribute integrity of the environmental parameter nodes is verified to ensure that each node contains at least one core attribute; for example, the core attributes of a temperature node might be the measured value and the measurement time.

[0039] Step S115: Perform edge relationship extraction processing on the physical association relationship between the structural parameter node and the device parameter node to generate position association edges, wherein the position association edges include edge identifier, association type and association strength description.

[0040] In commercial office buildings, physical relationships exist between structural parameter nodes and equipment parameter nodes. Location-related edges are generated through edge relationship extraction. For example, there is a locational relationship between elevator equipment and the building's floor structure. This relationship is determined by analyzing the equipment's installation location and the building's spatial layout. An edge identifier is used to uniquely identify this location-related edge, such as "Structure-Elevator Location-Related-01". The association type clarifies that the relationship is locational. The association strength can be determined based on the closeness between the equipment and the structure; elevators are closely connected to the shaft structure of their respective floors, resulting in a higher association strength; while some small lighting equipment has a relatively lower association strength with the wall structure. Through detailed analysis of the physical relationships between structural parameter nodes and equipment parameter nodes, the information of location-related edges is accurately extracted.

[0041] Step S116: Perform edge relationship extraction processing on the physical association relationship between the device parameter node and the environmental parameter node to generate an influencing association edge, wherein the influencing association edge includes an edge identifier, association type and association strength description.

[0042] In the scenario of a commercial office building, there are physical relationships between equipment parameter nodes and environmental parameter nodes. Influence-related edges are generated through edge relationship extraction. The operation of air conditioning equipment affects environmental parameters such as indoor temperature and humidity. By analyzing the changes in equipment operating parameters and environmental parameters, the aforementioned influence-related relationships are determined. Edge identifiers are used to uniquely identify this influence-related edge, such as "Equipment-Environmental Impact Association-01". The association type clarifies that the association is the impact of the equipment on the environment. The association strength description can be determined based on the degree of influence of the equipment on environmental parameters. Large air conditioning equipment has a greater impact on indoor temperature, resulting in a higher association strength; while small ventilation equipment has a relatively smaller impact on indoor air quality, resulting in a lower association strength. Through in-depth research on the physical relationships between equipment parameter nodes and environmental parameter nodes, information on influence-related edges is accurately extracted.

[0043] Step S117: Perform edge relationship extraction processing on the physical association relationship between the environmental parameter node and the structural parameter node to generate interactive association edges. The interactive association edges include edge identifier, association type and association strength description.

[0044] In commercial office buildings, there are physical relationships between environmental parameter nodes and structural parameter nodes. Interactive relationships are generated through edge relationship extraction. Outdoor environmental parameters such as humidity and temperature affect the material properties of the walls, while the wall structure also affects indoor environmental parameters. The interactive relationships are determined by analyzing the interaction between environmental and structural parameters. An edge identifier is used to uniquely identify this interactive relationship edge, such as "Environment-Structure Interactive Relationship-01". The relationship type clarifies that the relationship is an interaction between the environment and the structure. The relationship strength can be determined based on the degree of influence of the environment on the structure and the degree of feedback of the structure to the environment. Long-term high humidity has a greater impact on wooden structure walls, resulting in a higher relationship strength; while ordinary wall structures have a relatively smaller impact on indoor light intensity, resulting in a lower relationship strength. Through a comprehensive analysis of the physical relationships between environmental parameter nodes and structural parameter nodes, the information of interactive relationships is accurately extracted.

[0045] Step S118: Integrate the structural parameter nodes, equipment parameter nodes, environmental parameter nodes, and location-related edges, influence-related edges, and interaction-related edges, and verify the integrity of node attributes and the rationality of edge relationships through a graph consistency verification tool to generate a physical parameter knowledge graph.

[0046] After generating structural parameter nodes, equipment parameter nodes, environmental parameter nodes, and location-related edges, influence-related edges, and interaction-related edges, they are integrated together. In the construction of the knowledge graph for the commercial office building, all structural, equipment, and environmental nodes and their associated edges are combined into a whole. Then, a graph consistency verification tool is used to verify the integrated result. This tool checks the completeness of node attributes, ensuring that the attribute information of each node is accurate and complete. Simultaneously, it verifies the rationality of edge relationships, checking whether the association type and strength of associated edges conform to reality. For example, it checks whether location-related edges accurately reflect the actual location relationship between the structure and equipment, and whether influence-related edges reasonably describe the degree of equipment's impact on the environment. If incomplete node attributes or unreasonable edge relationships are found, the corresponding nodes and edges need to be corrected. After multiple verifications and corrections until all node attributes are complete and edge relationships are reasonable, the final physical parameter knowledge graph is generated. This physical parameter knowledge graph can comprehensively and accurately describe the physical parameters of the commercial office building and their interrelationships.

[0047] Step S120: Based on the physical parameter knowledge graph, perform digital twin graph model generation processing to construct a digital twin graph model of the building system. The digital twin graph model includes a structural parameter graph node layer, an equipment parameter graph node layer, an environmental parameter graph node layer, and a set of inter-layer association edges. The set of inter-layer association edges is used to realize parameter transmission and logical reasoning between different graph node layers.

[0048] After generating the physical parameter knowledge graph of the commercial office building, this step performs digital twin graph model generation based on this knowledge graph. The digital twin graph model is a digital mapping of the physical system of the commercial office building, consisting of structural parameter graph node layers, equipment parameter graph node layers, environmental parameter graph node layers, and a set of inter-layer connections. The structural parameter graph node layer organizes the structural parameter nodes in the knowledge graph according to certain rules; the equipment parameter graph node layer performs similar processing on the equipment parameter nodes; and the environmental parameter graph node layer integrates the environmental parameter nodes. The set of inter-layer connections connects different graph node layers, enabling parameter transmission and logical reasoning between different graph node layers. For example, when the load-bearing capacity of a floor node in the structural parameter graph node layer changes, this change information can be transmitted to the equipment parameter graph node layer through the set of inter-layer connections, affecting the operation of the equipment on that floor; simultaneously, based on preset logical reasoning rules, the potential impact of the above change on the indoor environmental parameters in the environmental parameter graph node layer can also be inferred.

[0049] Step S121: Extract structural parameter nodes from the physical parameter knowledge graph, and generate a structural parameter graph node layer by hierarchical aggregation according to parameter type. The structural parameter graph node layer contains multiple hierarchical child nodes, and the hierarchical child nodes are connected by internal association edges.

[0050] In the scenario of a commercial office building, structural parameter nodes are extracted from the physical parameter knowledge graph and then aggregated hierarchically according to parameter type to generate a structural parameter graph node layer. Based on the type of structural parameter nodes, such as wall parameters, floor parameters, beam and column parameters, and spatial area parameters, they are aggregated into different levels. For floor parameter type nodes, nodes from different floors are aggregated together to form a level. Each level may have multiple level child nodes. Within the floor level, each specific floor node is a level child node. Level child nodes are connected by internal association edges, which can represent hierarchical relationships, adjacency relationships, etc., between nodes. A first-floor node and a second-floor node are connected by an internal association edge, indicating that they are adjacent floors. Through the above hierarchical aggregation and the connection of internal association edges, a well-defined and clearly structured structural parameter graph node layer is formed.

[0051] Step S122: Extract device parameter nodes from the physical parameter knowledge graph, and generate a device parameter graph node layer by hierarchical aggregation according to parameter type. The device parameter graph node layer contains multiple hierarchical child nodes, and the hierarchical child nodes are connected by internal association edges.

[0052] In commercial office buildings, after extracting equipment parameter nodes from a physical parameter knowledge graph, they are aggregated hierarchically according to parameter type to generate an equipment parameter graph node layer. Based on the type of equipment parameter nodes, such as elevator parameters, air conditioning parameters, and lighting parameters, they are aggregated into different levels. For elevator parameter type nodes, nodes of different elevators are aggregated together to form a level. Each level also has multiple level child nodes, with each elevator node being a level child node. Level child nodes are connected by internal association edges, which can represent the collaborative working relationships, positional relationships, etc., between devices. Multiple elevators on the same floor are connected by internal association edges, indicating that they jointly serve passenger transportation on that floor. Through the above hierarchical aggregation and the connection of internal association edges, an ordered equipment parameter graph node layer is formed.

[0053] Step S123: Extract environmental parameter nodes from the physical parameter knowledge graph, and aggregate them hierarchically according to parameter type to generate an environmental parameter graph node layer. The environmental parameter graph node layer contains multiple hierarchical child nodes, and the hierarchical child nodes are connected by internal association edges.

[0054] In the construction of the environmental parameter graph node layer for commercial office buildings, environmental parameter nodes are extracted from the physical parameter knowledge graph and then aggregated hierarchically according to parameter type. Based on the type of environmental parameter nodes, such as temperature, humidity, and light intensity, they are aggregated into different levels. For temperature parameter nodes, temperature nodes at different locations and times are aggregated together to form a level. Each level can have multiple sub-nodes, with each specific temperature measurement node being a sub-node. Sub-nodes are connected by internal association edges, which can represent the mutual influence and spatial relationships between environmental parameters. Temperature nodes in adjacent areas on the same floor are also connected by internal association edges, indicating that they are spatially adjacent and their temperatures may influence each other. Through the above hierarchical aggregation and the connection of internal association edges, a reasonable environmental parameter graph node layer is formed.

[0055] Step S124: Extract position-related edges from the physical parameter knowledge graph, bind the hierarchical child nodes of the structural parameter graph node layer with the hierarchical child nodes of the equipment parameter graph node layer through position-related edges, and generate a subset of inter-structure and inter-equipment layer related edges.

[0056] In the construction of a digital twin graph model for a commercial office building, after extracting location-related edges from the physical parameter knowledge graph, the hierarchical child nodes of the structural parameter graph node layer are bound to the hierarchical child nodes of the equipment parameter graph node layer through location-related edges. Elevator equipment nodes are bound to the floor nodes of their respective floors through location-related edges, forming a subset of inter-layer connections between the structure and equipment. These subsets record the spatial relationships between the structure and equipment, enabling parameter transmission between the structural parameter graph node layers and the equipment parameter graph node layers. When the structure of a floor node changes, this change information can be transmitted to the corresponding elevator equipment node through the subset of inter-layer connections between the structure and equipment, affecting elevator operational safety assessments, etc.

[0057] Step S125: Extract the influence association edges from the physical parameter knowledge graph, and bind the hierarchical child nodes of the device parameter graph node layer with the hierarchical child nodes of the environment parameter graph node layer through the influence association edges to generate a subset of inter-device environment layer association edges.

[0058] In commercial office buildings, after extracting influence-related edges from the physical parameter knowledge graph, the hierarchical child nodes of the equipment parameter graph node layer are bound to the hierarchical child nodes of the environmental parameter graph node layer through these influence-related edges. Air conditioning equipment nodes are bound to environmental parameter nodes such as indoor temperature and humidity through these influence-related edges, generating a subset of inter-device / environmental layer influence edges. These edge subsets record the equipment's impact on the environment, enabling parameter transmission between the equipment parameter graph node layers and the environmental parameter graph node layers. When the operating parameters of the air conditioning equipment node change, this change information can be transmitted to the environmental parameter graph node layer through the subset of inter-device / environmental layer influence edges, affecting indoor environmental parameters such as temperature and humidity.

[0059] Step S126: Extract interactive association edges from the physical parameter knowledge graph, bind the hierarchical child nodes of the environmental parameter graph node layer with the hierarchical child nodes of the structural parameter graph node layer through interactive association edges, and generate a subset of inter-environmental and inter-structural association edges.

[0060] In constructing the digital twin graph model of a commercial office building, after extracting interactive edges from the physical parameter knowledge graph, the hierarchical child nodes of the environmental parameter graph node layer are bound to the hierarchical child nodes of the structural parameter graph node layer through interactive edges. Outdoor humidity environmental parameter nodes are bound to wall structure nodes through interactive edges, generating a subset of inter-environmental and inter-structure interconnected edges. These edge subsets record the interaction information between the environment and structure, enabling parameter transmission between the environmental parameter graph node layers and the structural parameter graph node layers. When the humidity value of the outdoor humidity environmental parameter node changes, this change information can be transmitted to the structural parameter graph node layer through the inter-environmental and inter-structure interconnected edge subsets, affecting the material properties of the wall structure, etc.

[0061] Step S127: Integrate the inter-layer related edge subsets of the structure and equipment, the inter-layer related edge subsets of the equipment environment, and the inter-layer related edge subsets of the environment and structure to form an inter-layer related edge set, wherein the inter-layer related edge set includes an edge weight attribute to represent the parameter transmission strength.

[0062] In the digital twin graph model of a commercial office building, subsets of inter-floor connections between structural equipment, equipment and environment, and environment and structure are integrated to form a set of inter-floor connections. This set of inter-floor connections includes edge weight attributes to represent the strength of parameter transmission. For edges in the structural equipment inter-floor connection subset, if an elevator is closely connected to the structure of its floor, its edge weight attribute value is higher, indicating a stronger parameter transmission strength; while for edges connecting smaller equipment to the structure, the edge weight attribute value is relatively lower. Through the edge weight attribute, the strength of parameter transmission between different graph node layers can be accurately described, making parameter transmission and logical reasoning more accurate and reasonable.

[0063] Step S128: Construct a graph reasoning engine. The graph reasoning engine realizes parameter transmission calculation and logical relationship reasoning based on the inter-layer association edge set. The structural parameter graph node layer, equipment parameter graph node layer, environmental parameter graph node layer, inter-layer association edge set are integrated with the graph reasoning engine to generate a digital twin graph model.

[0064] Step S1281: Design the parameter transmission calculation module of the graph inference engine. The parameter transmission calculation module receives the parameter values ​​of the starting graph nodes and the edge weight attributes of the inter-layer related edges, and calculates the input parameter values ​​of the intermediate graph nodes through a weighted summation algorithm. The input of the weighted summation algorithm is the product of the parameter values ​​of the starting graph nodes and the edge weight attributes, and the output is the input parameter values ​​of the intermediate graph nodes.

[0065] In the graph reasoning engine of a commercial office building, the parameter propagation calculation module is responsible for calculating the input parameter values ​​of intermediate graph nodes. When the parameter value of the starting graph node changes, this module receives the parameter value along with the edge weight attributes of the inter-floor connections connecting the starting and intermediate graph nodes. Using a weighted summation algorithm, the starting graph node's parameter value is multiplied by the edge weight attributes to obtain the input parameter values ​​of the intermediate graph nodes. If the starting graph node is a floor node and its load-bearing capacity parameter value changes, the inter-floor connections connecting this floor node and the elevator equipment node on that floor have certain edge weight attributes. Multiplying the floor node's load-bearing capacity parameter value by the edge weight attributes yields the input parameter value of the elevator equipment node. This input parameter value reflects the degree of impact of floor structure changes on the elevator equipment.

[0066] Step S1282: Design the logical relationship reasoning module of the graph reasoning engine. The logical relationship reasoning module calls the preset logical reasoning rule library based on the association type of the inter-layer association edge to reason about the parameter relationship between different graph node layers. The logical reasoning rule library includes position association reasoning rules, influence association reasoning rules and interaction association reasoning rules.

[0067] In the graph reasoning engine of a commercial office building, the logical relationship reasoning module invokes a pre-defined logical reasoning rule library to perform reasoning based on the association type of inter-layer edges. For location association reasoning rules, if the location association between a device node and a structural node does not meet the pre-defined safety distance requirements, the logical relationship reasoning module can infer that the installation of that device may pose a safety hazard. For impact association reasoning rules, when the operating power of an air conditioning device node increases, it can be inferred that the indoor temperature will decrease, and the humidity may also change, according to the impact association reasoning rule. For interaction association reasoning rules, when the humidity value of the outdoor humidity environmental parameter node increases, it can be inferred that the material properties of the wall structural node may be affected, according to the interaction association reasoning rule. Through these logical reasoning rules, the logical relationship reasoning module can accurately infer the parameter relationships between different graph node layers.

[0068] Step S1283: Design the node state update module of the graph inference engine. The node state update module receives the input parameter values ​​of the intermediate graph nodes, and calculates the output parameter values ​​of the nodes by combining the node's own attribute description information through a state transition function. The state transition function is determined based on the node's parameter type.

[0069] In the graph reasoning engine of a commercial office building, the node state update module is responsible for updating the node's state. When an intermediate graph node receives an input parameter value, the node state update module combines the node's own attribute description information and calculates the node's output parameter value through a state transition function. For elevator equipment nodes, their attribute description information includes load capacity, operating speed, etc. When they receive input parameter values ​​due to changes in the floor structure, they calculate the new operating state parameter values ​​of the elevator equipment node according to the state transition function determined based on the elevator parameter type, such as adjusting the operating speed to adapt to changes in the floor structure. Different types of nodes have different state transition functions to ensure accurate calculation of the node's output parameter values.

[0070] Step S1284: Design the path search module of the graph reasoning engine. The path search module uses a depth-first search algorithm or a breadth-first search algorithm based on the set of inter-layer related edges to find all possible propagation paths between any two graph nodes, and outputs the graph node identifiers and inter-layer related edge identifiers contained in the path.

[0071] In the graph reasoning engine of a commercial office building, the path search module is used to find all possible pathways between any two graph nodes. Based on the set of inter-floor edges, this module can use either a depth-first search (DFS) or breadth-first search (BFS) algorithm for path searching. When searching for a pathway between a floor node and a lighting fixture node located on that floor, the path search module starts from the floor node and searches along the inter-floor edges. If a DFS algorithm is used, it can search as deep as possible along a path until it cannot continue, then backtracks to the previous node and continues searching for other paths. If a BFS algorithm is used, it can search adjacent nodes layer by layer until the target node is found or all possible paths have been traversed. Finally, the path search module outputs the graph node identifiers and inter-floor edge identifiers contained in the path.

[0072] Step S1285: Integrate the parameter transmission calculation module, logical relationship reasoning module, node state update module and path search module to construct the core processing unit of the graph reasoning engine, and define the data interaction interface and calling order between each module.

[0073] In the construction of the graph reasoning engine for commercial office buildings, the parameter propagation calculation module, logical relationship reasoning module, node state update module, and path search module are integrated into a core processing unit. To ensure that the modules can work together, it is necessary to define the data interaction interfaces and calling order between the modules. When the parameter value of the starting graph node changes, the parameter propagation calculation module first calculates the input parameter value of the intermediate graph node based on the edge weight attribute of the inter-layer connection edge; then, the input parameter value is passed to the node state update module, which updates the node's state based on the node's own attribute information; simultaneously, the logical relationship reasoning module infers the parameter relationship based on the association type of the inter-layer connection edge and the preset logical reasoning rules; the path search module can find the propagation path between any two graph nodes when needed. By clearly defining the data interaction interfaces and calling order between the modules, the graph reasoning engine can run efficiently and accurately.

[0074] Step S1286: Verify the accuracy of parameter transmission calculation, the correctness of logical relationship reasoning, and the real-time performance of node state updates of the graph inference engine by inputting preset test parameter values ​​and known transmission paths. Adjust the algorithm parameters and inference rules in the module until the graph inference engine meets the preset performance indicators.

[0075] After the graph reasoning engine for the commercial office building is built, it needs to be verified and adjusted. By inputting preset test parameter values ​​and known transmission paths, the accuracy of parameter transmission calculations, the correctness of logical relationship reasoning, and the real-time performance of node state updates are tested. A known floor node load-bearing capacity change parameter value and its corresponding transmission path are input, and the accuracy of the input parameter values ​​for elevator equipment nodes calculated by the graph reasoning engine is observed. Simultaneously, the reasonableness of the impact inferred by the logical relationship reasoning module on other related nodes is checked; the real-time performance of node state updates by the node state update module is also examined. If the performance of the graph reasoning engine does not meet the preset performance indicators, the algorithm parameters and reasoning rules in the modules need to be adjusted. This includes adjusting certain coefficients in the weighted summation algorithm of the parameter transmission calculation module or modifying the logical reasoning rules of the logical relationship reasoning module. After multiple verifications and adjustments, the graph reasoning engine is refined until it meets the preset performance indicators and can accurately and efficiently complete tasks such as parameter transmission calculations, logical relationship reasoning, and node state updates.

[0076] Step S130: Generate a graph test scenario configuration sequence based on the set of inter-layer related edges and node interaction paths of the digital twin graph model. The graph test scenario configuration sequence includes graph node parameter perturbation rules, related edge triggering conditions, and test path control logic.

[0077] After the digital twin graph model of the commercial office building is constructed, a graph test scenario configuration sequence is generated based on its inter-layer connection edge set and node interaction paths. This configuration sequence is a crucial basis for conducting graph coupling simulation tests. Graph node parameter perturbation rules are used to control the parameter changes of the initial graph nodes, connection edge triggering conditions determine when inter-layer connection edges are triggered, and test path control logic guides the testing process. By rationally designing the graph test scenario configuration sequence, the performance and accuracy of the digital twin graph model can be comprehensively tested.

[0078] Step S131: parse the set of inter-layer association edges of the digital twin graph model, identify all possible interaction paths between the structural parameter graph node layer, the device parameter graph node layer, and the environmental parameter graph node layer. Each interaction path includes a starting graph node, an intermediate graph node, a ending graph node, and inter-layer association edges connecting each node.

[0079] In the scenario of a commercial office building, the set of inter-layer connections in the digital twin graph model is analyzed to identify all possible interaction paths between different graph node layers. Starting from a floor node in the structural parameter graph node layer, an interaction path is formed by connecting to an elevator device node in the equipment parameter graph node layer via an inter-layer connection edge, and then connecting to an indoor temperature node in the environmental parameter graph node layer via another inter-layer connection edge. Each interaction path includes a starting graph node (e.g., a floor node), intermediate graph nodes (e.g., an elevator device node), an ending graph node (e.g., an indoor temperature node), and the inter-layer connection edges connecting each node. Detailed analysis of the set of inter-layer connection edges identifies all possible interaction paths, providing a foundation for subsequent test scenario configuration.

[0080] Step S132: Divide the test scenario types based on the node types and inter-layer association edge attributes of the interaction path. Each test scenario type corresponds to the collaborative testing requirements of one or more interaction paths. Determine the scenario test objectives for each test scenario type.

[0081] In the testing of digital twin graph models for commercial office buildings, test scenario types are categorized based on the node types of interaction paths and the attributes of inter-layer connecting edges. Test scenarios are divided into different types according to the types of starting, intermediate, and ending graph nodes in the interaction path, as well as the association types and edge weight attributes of inter-layer connecting edges. If the interaction path mainly involves the locational association between structures and equipment, it is classified as a structure-equipment location association test scenario; if the interaction path mainly reflects the impact of equipment on the environment, it is classified as a device-environment impact test scenario. Each test scenario type corresponds to the collaborative testing requirements of one or more interaction paths, and a scenario testing objective is determined for each test scenario type. For the structure-equipment location association test scenario type, the scenario testing objective may be to verify whether the impact of structural changes on equipment installation and operation meets safety requirements; for the device-environment impact test scenario type, the scenario testing objective may be to evaluate whether the adjustment effect of equipment operation on environmental parameters meets expectations.

[0082] Step S133: For each test scenario type, design graph node parameter perturbation rules based on the starting graph node parameter type of the corresponding interaction path and the scenario test target. The graph node parameter perturbation rules include the initial parameter value setting of the starting graph node, the parameter continuous change mode, and the parameter cooperative perturbation relationship.

[0083] In the testing of digital twin graph models for commercial office buildings, perturbation rules for graph node parameters are designed for each test scenario type. For the structure-equipment location association test scenario, if the initial graph node is a floor node, perturbation rules for graph node parameters are designed based on its parameter type (e.g., load-bearing capacity) and the scenario test objective (verifying the impact of structural changes on equipment). The initial load-bearing capacity parameter value for the floor node is set, and the continuous change mode of the parameter is determined—whether it is linear or non-linear. Simultaneously, the cooperative perturbation relationship of parameters is considered. If the load-bearing capacity of a floor node changes, it may generate cooperative perturbation relationships with the parameters of multiple equipment nodes on that floor; for example, the load limit of elevator equipment may need to be adjusted accordingly. By reasonably designing graph node parameter perturbation rules, different actual situations can be simulated, comprehensively testing the performance of the digital twin graph model.

[0084] Step S134: Design the associated edge triggering conditions based on the inter-layer associated edge attributes of the scenario test target and interaction path. The associated edge triggering conditions include the threshold conditions of the starting graph node parameters, the state conditions of the intermediate graph nodes, and the transmission strength conditions of the inter-layer associated edges.

[0085] In the testing of digital twin graph models for commercial office buildings, triggering conditions for associated edges are designed based on the scenario testing objectives and the inter-layer association edge attributes of the interaction paths. For the device-environment impact testing scenario, the objective is to evaluate the effect of air conditioning equipment on indoor temperature regulation. Triggering conditions for associated edges are designed based on the inter-layer association edge attributes of the interaction paths, such as edge weight attributes reflecting the intensity of the air conditioning equipment's influence on indoor temperature. The parameter threshold condition for the initial graph node (air conditioning equipment node) can be that the air conditioning's operating power reaches a certain value; the state condition for intermediate graph nodes (such as temperature sensor nodes) can be that the indoor temperature has not reached the preset target temperature; the inter-layer association edge transmission strength condition can be that the edge weight attribute reaches a certain range. When all these conditions are met, the associated edge is triggered, and parameter transmission and logical reasoning begin.

[0086] Step S135: Design test path control logic based on graph node parameter perturbation rules and associated edge triggering conditions. The test path control logic includes interactive path selection strategy, node parameter injection order and test interruption mechanism.

[0087] In the testing of a digital twin graph model for a commercial office building, test path control logic is designed based on graph node parameter perturbation rules and associated edge triggering conditions. The interaction path selection strategy determines which paths to test from among many possible interaction paths. The most representative interaction path can be selected based on the focus of the test scenario and resource constraints. The node parameter injection order determines when the parameters of the starting graph node are injected to ensure the rationality of the testing process. If there are multiple starting graph nodes, parameters need to be injected in a certain order to avoid parameter conflicts. The test interruption mechanism specifies under what circumstances the test process should be interrupted. When the test results are abnormal or the preset test time is reached, the test is interrupted to ensure the safety and effectiveness of the test.

[0088] Step S136: Associate and integrate the graph node parameter perturbation rules, associated edge triggering conditions, and test path control logic according to the test scenario type to generate a graph test scenario configuration sequence.

[0089] In the testing of digital twin graph models for commercial office buildings, graph node parameter perturbation rules, associated edge triggering conditions, and test path control logic are integrated and associated according to test scenario types to generate a graph test scenario configuration sequence. For each test scenario type, the corresponding graph node parameter perturbation rules, associated edge triggering conditions, and test path control logic are combined together. For the structure-equipment location association test scenario type, the graph node parameter perturbation rules, associated edge triggering conditions, and test path control logic under this scenario are integrated into a single configuration unit; the same integration is performed for the equipment-environment impact test scenario type. Finally, the configuration units of all test scenario types are combined together to form a complete graph test scenario configuration sequence.

[0090] Step S140: Input the graph test scenario configuration sequence into the digital twin graph model to perform graph coupling simulation test and generate a graph test response dataset. The graph test response dataset includes graph node response sequences, associated edge propagation relationship data, and abnormal path graph data.

[0091] In the testing of digital twin graph models for commercial office buildings, graph test scenario configuration sequences are input into the digital twin graph model to perform graph coupling simulation tests. The graph node parameter perturbation rules in the graph test scenario configuration sequence cause changes in the parameters of the initial graph nodes. The edge triggering conditions determine when parameters are propagated between layers, and the test path control logic guides the testing process. During the test, the graph inference engine of the digital twin graph model performs parameter propagation and logical inference based on the set of inter-layer edges, recording the response status of graph nodes, the propagation relationships of edges, and possible abnormal paths. Finally, a graph test response dataset is generated, which includes graph node response sequences, edge propagation relationship data, and abnormal path graph data.

[0092] Step S141: Analyze the graph node parameter perturbation rules in the graph test scenario configuration sequence to generate a graph node parameter injection sequence for the digital twin graph model to be injected. The graph node parameter injection sequence includes the parameter values ​​of the starting graph node in the interaction path and the parameter injection time point.

[0093] In the testing of digital twin graph models for commercial office buildings, the graph node parameter perturbation rules in the configuration sequence of the analytical graph test scenarios are used to generate a graph node parameter injection sequence. For the graph node parameter perturbation rules of the structure-equipment location association test scenario type, the initial load-bearing capacity parameter values ​​of floor nodes and the continuous parameter change pattern are set. Based on these rules, the parameter values ​​of the starting graph nodes (floor nodes) in the interaction path and the parameter injection time points are determined. If the continuous parameter change pattern is linear, the floor node load-bearing capacity parameter values ​​at different time points are calculated at certain time intervals to form a graph node parameter injection sequence. This graph node parameter injection sequence will be injected into the digital twin graph model to simulate the impact of hierarchical structure changes on equipment in actual situations.

[0094] Step S142: Monitor the graph node status of the digital twin graph model according to the associated edge triggering conditions in the graph test scenario configuration sequence. When the triggering conditions are met, inject the graph node parameter injection sequence into the corresponding starting graph node in the order of parameter injection time.

[0095] In the testing of digital twin graph models for commercial office buildings, the status of graph nodes in the digital twin graph model is monitored according to the associated edge triggering conditions in the graph test scenario configuration sequence. For the device-environment impact test scenario type, the associated edge triggering conditions include the parameter threshold conditions for the initial graph node (air conditioning equipment node), the status conditions for intermediate graph nodes (temperature sensor nodes), and the inter-layer associated edge conduction strength conditions. These conditions are continuously monitored, and when all conditions are met, the graph node parameter injection sequence is injected into the corresponding initial graph node in the order of parameter injection time. If the operating power of the air conditioning equipment node reaches the parameter threshold condition, the temperature sensor node's state has not reached the preset target temperature, and the inter-layer associated edge conduction strength meets the condition, then the parameter injection sequence for the air conditioning equipment node is injected in the order of time points, starting the simulation of the air conditioning equipment's impact on the indoor environment.

[0096] Step S143: The graph inference engine of the digital twin graph model performs parameter propagation processing based on the set of inter-layer related edges. After the starting graph node receives the parameter injection value, it propagates to the intermediate graph node through the inter-layer related edges. After the intermediate graph node updates its own state, it continues to propagate to the terminating graph node, forming a graph coupling propagation link.

[0097] In the testing of the digital twin graph model for a commercial office building, after the starting graph node receives the parameter injection value, the graph inference engine of the digital twin graph model performs parameter propagation processing based on the set of inter-layer related edges. The starting graph node (e.g., a floor node) stores the parameter injection value in its current state attribute. The path search module of the graph inference engine searches for all directly connected inter-layer related edges originating from the starting graph node based on the set of inter-layer related edges, determining the intermediate graph nodes directly connected to the starting graph node (e.g., elevator equipment nodes on that floor). The parameter propagation calculation module calls the edge weight attribute of the inter-layer related edges between the starting graph node and the intermediate graph nodes, multiplying the parameter injection value of the starting graph node by the edge weight attribute to obtain the input parameter value of the intermediate graph node. Upon receiving the input parameter value, the node state update module calls the state transition function corresponding to the parameter type of the intermediate graph node, fusing the input parameter value with the current state attribute value of the intermediate graph node to calculate and update the state attribute value, thus completing its own state update. The path search module continues to search for all directly connected inter-layer edges originating from the intermediate graph node after its update, determining the next-level intermediate graph node or the terminal graph node (such as the indoor temperature node) directly connected to the intermediate graph node. If the connection is to the next-level intermediate graph node, the weighted calculation of the parameter transmission calculation module and the state update steps of the node state update module are repeated until the transmission reaches the terminal graph node. If the connection is to the terminal graph node, the parameter transmission calculation module calculates the input parameter value for the terminal graph node, and the terminal graph node updates its own state attribute value after receiving the input parameter value, completing one parameter transmission cycle. All graph node identifiers, inter-layer edge identifiers, parameter values, and transmission time points involved in the transmission process from the starting graph node to the terminal graph node are recorded, forming a graph coupling transmission link.

[0098] Step S144: During the operation of the graph coupling transmission link, the structural node response sequence of the structural parameter graph node layer, the device node response sequence of the device parameter graph node layer, and the environmental node response sequence of the environmental parameter graph node layer are collected according to the test path control logic, and integrated to generate the graph node response sequence.

[0099] In the testing of the digital twin graph model of a commercial office building, during the operation of the graph coupling transmission link, the node response sequences of each graph node layer are collected according to the test path control logic. The test path control logic specifies the time interval and node range for collection. Following this logic, response sequences of structural nodes such as floor nodes and wall nodes in the structural parameter graph node layer are collected, recording the changes in their parameter values ​​over time; response sequences of equipment nodes such as elevator equipment nodes and air conditioning equipment nodes in the equipment parameter graph node layer are collected; and response sequences of environmental nodes such as indoor temperature nodes and humidity nodes in the environmental parameter graph node layer are collected. These structural node response sequences, equipment node response sequences, and environmental node response sequences are integrated to generate a graph node response sequence, which reflects the response of each node in the graph node layer to parameter changes during the graph coupling transmission process.

[0100] Step S145: Perform correlation analysis on the structural node response sequence, device node response sequence and environment node response sequence in the graph node response sequence, extract the parameter value change relationship between different graph node layers through inter-layer correlation edges, and generate correlation edge transmission relationship data.

[0101] In the testing of a digital twin graph model for a commercial office building, correlation analysis was performed on the structural node response sequences, equipment node response sequences, and environmental node response sequences within the graph node response sequences. By comparing the node response sequences of different graph node layers, the parameter value changes transmitted between different graph node layers through inter-layer correlation edges were extracted. If the load-bearing capacity parameter value of a floor node changes, the changes in the operating parameters (such as load limits) of the elevator equipment nodes on that floor were observed, and the parameter value change relationship between the two was analyzed. Simultaneously, the impact of the elevator equipment node operation on environmental node parameters such as indoor temperature was analyzed. Through the above correlation analysis, correlation edge transmission relationship data is generated, which can help to gain a deeper understanding of the parameter transmission mechanism between different graph node layers.

[0102] Step S146: During the operation of the graph coupling transmission link, monitor the status value of each graph node. When the status value of a graph node exceeds the normal range, trace the path of the abnormal status value from the starting abnormal graph node through the intermediate transmission graph nodes to the final affected graph node through the graph inference engine. Record the graph node identifier, inter-layer association edge identifier and transmission order in the abnormal path, and generate abnormal path graph data.

[0103] In the testing of digital twin graph models for commercial office buildings, the status values ​​of each graph node are monitored during the operation of the graph coupling transmission links. If the status value (e.g., operating speed) of a graph node (such as an elevator equipment node) exceeds the normal range, the transmission path of the abnormal status value is traced through the graph inference engine. The path search module of the graph inference engine searches for all possible transmission paths starting from the initial abnormal graph node (elevator equipment node) based on the set of inter-floor associated edges, determining intermediate transmission graph nodes (such as structural nodes of the floor) and the final influencing graph nodes (such as indoor environment nodes of the floor). The graph node identifiers, inter-floor associated edge identifiers, and transmission order in the abnormal path are recorded to generate abnormal path graph data. This abnormal path graph data can help analyze the causes and scope of impact of abnormal situations.

[0104] Step S147: Integrate the graph node response sequence, associated edge propagation relationship data, and abnormal path graph data to generate a graph test response dataset.

[0105] In the testing of a digital twin graph model for a commercial office building, graph node response sequences, associated edge propagation relationship data, and anomaly path graph data are integrated to generate a graph test response dataset. The graph node response sequences reflect the response of nodes at each graph node layer to parameter changes; the associated edge propagation relationship data demonstrates the parameter propagation mechanism between different graph node layers; and the anomaly path graph data records the propagation path and impact range of anomalies. Integrating these data forms a complete graph test response dataset.

[0106] Step S150: Analyze the graph structure test results based on the graph test response dataset, and output a digital twin simulation test evaluation report of the building system. The digital twin simulation test evaluation report includes graph node response characteristics, associated edge impact characteristics, and abnormal path graph risk characteristics.

[0107] After the digital twin graph model of the commercial office building is tested, graph structure test results are analyzed based on the graph test response dataset, and a digital twin simulation test evaluation report is output. Analysis of the graph test response dataset provides a comprehensive understanding of the performance of the digital twin graph model and the actual situation of the building system. Graph node response characteristics reflect the response patterns of nodes at each graph node layer to parameter changes; edge influence characteristics reflect the parameter transmission impact between different graph node layers; and abnormal path graph risk characteristics assess the risk level and impact range of abnormal situations. These characteristics are compared and analyzed with preset graph structure test evaluation benchmarks to determine the degree of compliance of each characteristic and the graph nodes or edges that need optimization. Finally, a digital twin simulation test evaluation report is output according to the preset report format.

[0108] Step S151: Extract graph node response sequences from the graph test response dataset, analyze the response patterns of structural node response sequences in the structural parameter graph node layer as parameter injection values ​​change, the response patterns of device node response sequences in the device parameter graph node layer as parameter injection values ​​change, and the response patterns of environmental node response sequences in the environmental parameter graph node layer as parameter injection values ​​change, and integrate them to generate graph node response characteristics.

[0109] In the analysis of test results for the digital twin graph model of a commercial office building, graph node response sequences are extracted from the graph test response dataset. The structural node response sequences of the structural parameter graph node layer are analyzed to observe the changes in the load-bearing capacity parameter values ​​of floor nodes with the parameter injection values ​​of the initial graph node (e.g., upper-level structural node), summarizing the response patterns and determining whether they are linear or nonlinear. For the equipment node response sequences of the equipment parameter graph node layer, the response patterns of elevator equipment node operating parameters (e.g., load limits, operating speed) with changes in the load-bearing capacity parameters of floor nodes are analyzed. For the environmental node response sequences of the environmental parameter graph node layer, the response patterns of indoor temperature node temperature values ​​with changes in the operating parameters of air conditioning equipment nodes are analyzed. These node response patterns from different graph node layers are integrated to generate graph node response characteristics. These characteristics help to understand the sensitivity and response mode of nodes in each graph node layer to parameter changes.

[0110] Step S152: Extract the associated edge transmission relationship data from the graph test response dataset, analyze the parameter influence law between the structural parameter graph node layer and the equipment parameter graph node layer through the associated edge between the structural and equipment layers, the parameter influence law between the equipment parameter graph node layer and the environmental parameter graph node layer through the associated edge between the equipment and environmental layers, and the parameter influence law between the environmental parameter graph node layer and the structural parameter graph node layer through the associated edge between the environmental and structural layers, and integrate them to generate associated edge influence characteristics.

[0111] In the analysis of test results for a digital twin graph model of a commercial office building, data on the transmission relationships of associated edges are extracted from the graph test response dataset. The study analyzes the parameter influence patterns transmitted between structural parameter graph node layers and equipment parameter graph node layers through inter-layer structural and equipment associated edges, examining how changes in the load-bearing capacity of floor nodes affect the operating parameters of elevator equipment on that floor. For the parameter influence patterns transmitted between equipment parameter graph node layers and environmental parameter graph node layers through inter-layer equipment and environmental associated edges, the study analyzes how the operation of air conditioning equipment alters indoor environmental parameters such as temperature and humidity. For the parameter influence patterns transmitted between environmental parameter graph node layers and structural parameter graph node layers through inter-layer environmental and structural associated edges, the study analyzes the impact of outdoor humidity on the performance of wall structure materials. These parameter influence patterns between different graph node layers are integrated to generate associated edge influence characteristics, which help understand the role and degree of influence of inter-layer associated edges in the parameter transmission process.

[0112] Step S153: Extract abnormal path graph data from the graph test response dataset, analyze the path pattern of abnormal state values ​​from the initial abnormal graph node through intermediate transmission graph nodes to the final affected graph node, the range pattern of the graph node layers involved, and the speed pattern of transmission through inter-layer associated edges, and combine the importance pattern of abnormal graph nodes in the digital twin graph model to integrate and generate the risk characteristics of abnormal path graph.

[0113] In the analysis of test results for a digital twin graph model of a commercial office building, abnormal path graph data was extracted from the graph test response dataset. The path patterns of abnormal state values ​​were analyzed to determine the order of graph node types in which abnormal state values ​​were transmitted—whether it was from structural nodes to equipment nodes to environmental nodes, or some other order. The number of graph node layers involved in each abnormal path graph data was counted to determine the range of graph node layers covered by the abnormal state value—whether it was a local or global range. The propagation time difference of abnormal state values ​​between adjacent graph nodes was calculated based on the propagation time sequence, and the speed pattern of propagation through inter-layer connections was analyzed—whether it was fast or slow propagation. The importance labeling table of the graph node in the digital twin graph model was queried to obtain the importance label corresponding to the initial abnormal graph node identifier—whether it was a core node or a general node. A correlation analysis was performed on the path patterns, range patterns, speed patterns, and importance labels. The combination of the global range pattern and the fast propagation pattern of core node labels corresponds to a specific risk characteristic; the combination of the local range pattern and the slow propagation pattern of general node labels corresponds to another specific risk characteristic; other combinations correspond to corresponding risk characteristics. By integrating risk characteristic descriptions corresponding to different combinations, an anomaly path diagram risk characteristic is generated. This anomaly path diagram risk characteristic can help assess the risk level and impact range of anomalies.

[0114] For example, step S1531: Extract all abnormal path graph data from the graph test response dataset. Each abnormal path graph data includes the starting abnormal graph node identifier, the intermediate transmission graph node identifier sequence, the final impact graph node identifier, the inter-layer association edge identifier sequence, and the transmission time point sequence.

[0115] In the analysis of test results for the digital twin graph model of a commercial office building, all abnormal path graph data were extracted from the graph test response dataset. Each abnormal path graph record details the transmission process of the abnormal situation. The initial abnormal graph node identifier clearly identifies the starting point of the abnormal situation; the intermediate transmission graph node identifier sequence records the intermediate nodes traversed by the abnormal state value; the final impact graph node identifier indicates the final effect of the abnormal situation; the inter-layer association edge identifier sequence records the inter-layer association edges traversed by the abnormal state value transmission; and the transmission time point sequence records the transmission time of the abnormal state value between various nodes and edges. For example, in the digital twin graph model test of a commercial office building, there might be an abnormal state value transmission situation involving elevator equipment nodes. The abnormal path graph data would clearly record the initial abnormal graph node as the identifier of that elevator equipment node, the intermediate structural nodes that might be passed through (their identifiers are reflected in the intermediate transmission graph node identifier sequence), and the final impact graph node that affects the indoor environment of that floor (its identifier is the final impact graph node identifier). Simultaneously, it can record the sequence of inter-floor association edges from the elevator equipment node to the structural node through specific structural equipment inter-floor association edges, and then to the indoor environment node through other association edges, as well as the specific time point of each transmission, forming a transmission time point sequence.

[0116] Step S1532: For each abnormal path graph data, analyze the type of the initial abnormal graph node identifier, the intermediate transmission graph node identifier sequence, and the final impact graph node identifier, determine the graph node type order of abnormal state value transmission, and summarize the path rules. The path rules include the structural equipment environment path pattern, the equipment environment structure path pattern, and the environment structure equipment path pattern.

[0117] In this step, for each extracted anomaly path graph data, a detailed analysis is conducted on the types of the initial anomaly graph node identifier, the sequence of intermediate transmission graph node identifiers, and the type of the final impact graph node identifier. In the scenario of a commercial office building, the initial anomaly graph node may be an equipment type (e.g., elevator equipment node), a structural type (e.g., floor structure node), or an environmental type (e.g., an environmental node with an abnormal indoor temperature). The node types contained in the intermediate transmission graph node identifier sequence also vary, possibly passing through structural nodes, equipment nodes, etc. The final impact graph node may also be of different types. By analyzing the order of these node types, the order of graph node types in which the abnormal state value is transmitted can be determined. If the initial anomaly graph node is an equipment type, passes through a structural node, and ultimately affects an environmental node, then a device-structure-environment path pattern is formed. Based on the analysis results of a large amount of anomaly path graph data, common path patterns are summarized, such as the structure-equipment-environment path pattern, the equipment-environment-structure path pattern, and the environment-structure-equipment path pattern.

[0118] Step S1533: Count the number of graph node layers involved in each abnormal path graph data, determine the range of graph node layers covered by the abnormal state value, and summarize the range pattern of the graph node layers involved. The range pattern includes a local range pattern covering two graph node layers and a global range pattern covering three graph node layers.

[0119] In the analysis of test results for the digital twin graph model of commercial office buildings, it is necessary to count the number of graph node layers involved in each abnormal path graph data. Graph node layers include structural parameter graph node layers, equipment parameter graph node layers, and environmental parameter graph node layers. If an abnormal path graph data only involves nodes in the structural parameter graph node layer and the equipment parameter graph node layer, then the number of graph node layers covered by the abnormal state value is two, which belongs to the local scope mode. For example, the abnormal state value of the elevator equipment node only propagates to the structural node of that floor and does not affect the nodes in the environmental parameter graph node layer. However, if the abnormal path graph data involves nodes in the structural parameter graph node layer, the equipment parameter graph node layer, and the environmental parameter graph node layer, then the number of graph node layers covered by the abnormal state value is three, which belongs to the global scope mode. For example, the abnormal state value of the elevator equipment node first propagates to the structural node of that floor, and then affects the environmental parameter nodes such as indoor temperature and humidity. Through the statistical analysis of a large amount of abnormal path graph data, the scope pattern of the graph node layers involved is summarized.

[0120] Step S1534: Calculate the transmission time difference of abnormal state values ​​between adjacent graph nodes based on the transmission time point sequence, and analyze the speed law of transmission through inter-layer associated edges. The speed law includes a fast transmission mode with a short transmission time difference and a slow transmission mode with a long transmission time difference.

[0121] In anomaly path analysis of a digital twin model of a commercial office building, the propagation time difference between adjacent graph nodes is calculated based on the propagation time point sequence in the anomaly path graph data. The propagation time point sequence records the specific time when the anomaly value arrives at each graph node. By subtracting the propagation time of the preceding adjacent graph node from the propagation time of the subsequent graph node, the propagation time difference between these two adjacent graph nodes can be obtained. If an anomaly value propagates from an elevator equipment node to a structural node on the same floor, the propagation time point sequence shows that the time of arrival at the elevator equipment node is at a specific moment, and the time of arrival at the structural node is at another moment later. Subtracting these two times gives the propagation time difference. When the propagation time difference is short, it indicates that the anomaly value propagates quickly between these two adjacent graph nodes, belonging to a fast propagation mode; conversely, when the propagation time difference is long, it belongs to a slow propagation mode.

[0122] Step S1535: Query the graph node importance label table of the digital twin graph model to obtain the importance label corresponding to the initial abnormal graph node identifier. The importance label includes core node label and general node label.

[0123] In the digital twin model of a commercial office building, there exists a node importance labeling table. This table labels the importance of each node, with label types including core node labels and general node labels. Core nodes are typically those that play a crucial role in the normal operation of the entire building system, such as the main control elevator node in the elevator equipment node and key beam-column nodes in the structural parameter node layer. General nodes are those with relatively minor impact on system operation, such as some auxiliary lighting equipment nodes. When analyzing abnormal path graph data, it is necessary to query this node importance labeling table to obtain the importance label corresponding to the initial abnormal node. If the initial abnormal node is the main control elevator node, the table shows that its importance label is a core node; if it is a regular lighting equipment node, its importance label is a general node.

[0124] Step S1536: Perform correlation analysis on path patterns, range patterns, speed patterns and importance markings. The combination of the global range pattern and the fast transmission pattern of the core node markings corresponds to a specific risk characteristic. The combination of the local range pattern and the slow transmission pattern of the general node markings corresponds to another specific risk characteristic. Other combinations correspond to the corresponding risk characteristics.

[0125] In the anomaly risk analysis of the digital twin model of a commercial office building, it is necessary to perform correlation analysis on the path patterns, range patterns, speed patterns, and importance labels obtained from the previous analysis. When the importance label of the initial anomaly node is a core node, and the propagation of the anomaly state value conforms to a global range pattern and belongs to a rapid propagation pattern, the above combination corresponds to specific high-risk characteristics. Anomalies at core nodes will quickly spread to the three node layers of structure, equipment, and environment, potentially causing serious problems in the operation of the entire building system. For example, an anomaly at the main control elevator node and its rapid propagation will affect the floor structure and indoor environment, potentially endangering personnel safety and the normal operation of equipment. Conversely, when the importance label of the initial anomaly node is a general node, and the propagation of the anomaly state value conforms to a local range pattern and belongs to a slow propagation pattern, it corresponds to relatively low-risk characteristics. Anomalies at ordinary lighting equipment nodes slowly affect local environmental parameters, with a smaller impact on the entire building system. Other combinations of path patterns, range patterns, speed patterns, and importance labels also correspond to corresponding risk characteristics. Through the above correlation analysis, the risk level of anomalies can be assessed more accurately.

[0126] Step S1537: Integrate the risk characteristic descriptions corresponding to different combinations to generate anomaly path diagram risk characteristics.

[0127] After completing the correlation analysis of path patterns, range patterns, speed patterns, and importance annotations, the risk characteristic descriptions corresponding to different combinations are integrated. In the digital twin model of a commercial office building, the combination of global range mode and fast propagation mode for core node annotations may pose a serious threat to the operation of the entire building system, potentially leading to casualties and major equipment damage. Conversely, the combination of local range mode and slow propagation mode for general node annotations may have a minor impact on the local environment, without affecting the normal operation of the overall system. These risk characteristic descriptions of different combinations are integrated according to a certain logic to form a comprehensive anomaly path graph risk characteristic. This characteristic can comprehensively reflect the propagation risk of anomaly values ​​in the digital twin model.

[0128] Step S154: Compare and analyze the graph node response characteristics, associated edge impact characteristics, and abnormal path graph risk characteristics with the preset graph structure test and evaluation benchmarks to determine the degree of compliance of each characteristic and the graph nodes or associated edges that need to be optimized.

[0129] In the analysis of test results for the digital twin graph model of a commercial office building, the obtained graph node response characteristics, associated edge influence characteristics, and abnormal path graph risk characteristics are compared with the preset graph structure test evaluation benchmark. The preset graph structure test evaluation benchmark is formulated based on the building system design requirements and safety standards, specifying the reasonable range of graph node response, the normality of associated edge influence, and the acceptable level of abnormal path graph risk. For graph node response characteristics, the node response patterns of each graph node layer are compared and analyzed to see if they conform to the response patterns specified in the benchmark. If a floor node's response to parameter changes is too sensitive or lagging, exceeding the benchmark range, then the response characteristics of that floor node do not meet the requirements. For associated edge influence characteristics, the parameter influence patterns between different graph node layers are checked to see if they are consistent with the benchmark. If the degree of influence of air conditioning equipment on indoor temperature differs significantly from the degree of influence specified in the benchmark, then the corresponding equipment environment layer-to-layer associated edges may need optimization. For abnormal path graph risk characteristics, the risk level is compared with the acceptable risk level in the benchmark. If the risk characteristics of abnormal situations exceed the benchmark range, then the initial abnormal graph node or related layer-to-layer associated edges that lead to high risk need to be identified and optimized. Through the above comparative analysis, the degree of conformity of each characteristic is determined, and the graph nodes or related edges that need to be optimized are identified.

[0130] Step S155: Integrate the graph node response characteristics, associated edge impact characteristics, abnormal path graph risk characteristics, and comparative analysis results according to the preset report format, and output a digital twin simulation test evaluation report.

[0131] After the digital twin graph model testing of the commercial office building is completed, relevant information is integrated and a digital twin simulation test evaluation report is output according to a preset report format. The preset report format typically includes a title, table of contents, main body, and conclusion. The main body first describes the response characteristics of the graph nodes in detail, including the node response patterns of each graph node layer, using specific analysis results and examples to illustrate the node's response to parameter changes. Next, it explains the influence characteristics of associated edges, introducing the parameter influence patterns transmitted between different graph node layers through inter-layer associated edges, and the impact of these patterns on the building system operation. Then, it describes the risk characteristics of the abnormal path graph, including the path patterns, range patterns, and speed patterns of abnormal state values, as well as the corresponding risk levels. Next, it presents a detailed comparative analysis of the graph node response characteristics, associated edge influence characteristics, and abnormal path graph risk characteristics with the preset graph structure test evaluation benchmark, indicating the degree of conformity of each characteristic and the graph nodes or associated edges that need optimization. Finally, the conclusion summarizes the main findings and recommendations of the test, providing a reference for the optimization and improvement of the building system. By integrating data according to a preset report format, the output digital twin simulation test evaluation report can clearly and comprehensively present the test results, providing a basis for decision-making for relevant personnel.

[0132] Figure 2 The illustration shows exemplary hardware and software components of a digital twin simulation test system 100 for building systems, which can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 can be used in the digital twin simulation test system 100 for building systems and to perform the functions in this application.

[0133] For example, a digital twin simulation test system 100 applied to a building system may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the digital twin simulation test system 100 applied to a building system may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The digital twin simulation test system 100 applied to a building system also includes an I / O interface 150 between the computer and other input / output devices.

[0134] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned digital twin simulation test method applied to building systems is implemented.

[0135] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for digital twin simulation test applied to a building system, characterized in that, The method comprises: Performing knowledge graph construction processing of physical parameters of a building system to generate a physical parameter knowledge graph; Performing digital twin graph model generation processing based on the physical parameter knowledge graph to construct a digital twin graph model of the building system; Generating a graph test scene configuration sequence according to an inter-layer association edge set and a node interaction path of the digital twin graph model, wherein a structural parameter node is extracted from the physical parameter knowledge graph, and a structural parameter graph node layer is generated by hierarchical aggregation according to a parameter type, the structural parameter graph node layer comprising a plurality of hierarchical sub-nodes connected by internal association edges; Inputting the graph test scene configuration sequence into the digital twin graph model to perform graph coupling simulation testing and generating a graph test response data set; Performing graph structure test result analysis based on the graph test response data set to output a digital twin simulation test evaluation report of the building system, the digital twin simulation test evaluation report comprising graph node response characteristics, association edge influence characteristics, and abnormal path graph risk characteristics.

2. The digital twin simulation test method applied to a building system according to claim 1, wherein, The method comprises: Collecting physical parameter data of the building system, the physical parameter data comprising structural parameter data, equipment parameter data, and environmental parameter data; Performing graph node extraction processing on the structural parameter data to extract structural parameter entities and entity attributes, and generating structural parameter nodes, the structural parameter nodes comprising node identifiers, parameter types, and attribute description information; Performing graph node extraction processing on the equipment parameter data to extract equipment parameter entities and entity attributes, and generating equipment parameter nodes, the equipment parameter nodes comprising node identifiers, parameter types, and attribute description information; Performing graph node extraction processing on the environmental parameter data to extract environmental parameter entities and entity attributes, and generating environmental parameter nodes, the environmental parameter nodes comprising node identifiers, parameter types, and attribute description information; Performing edge relationship extraction processing on the physical association relationship between the structural parameter nodes and the equipment parameter nodes to generate location association edges, the location association edges comprising edge identifiers, association types, and association strength descriptions; Performing edge relationship extraction processing on the physical association relationship between the equipment parameter nodes and the environmental parameter nodes to generate influence association edges, the influence association edges comprising edge identifiers, association types, and association strength descriptions; Performing edge relationship extraction processing on the physical association relationship between the environmental parameter nodes and the structural parameter nodes to generate interaction association edges, the interaction association edges comprising edge identifiers, association types, and association strength descriptions; Integrating the structural parameter nodes, the equipment parameter nodes, the environmental parameter nodes, the location association edges, the influence association edges, and the interaction association edges, verifying node attribute integrity and edge relationship rationality through a graph consistency verification tool, and generating a physical parameter knowledge graph. 3.The digital twin simulation test method applied to a building system according to claim 1, wherein, The method comprises: extracting device parameter nodes from the physical parameter knowledge graph, hierarchically aggregating the device parameter nodes according to parameter types to generate a device parameter graph node layer, the device parameter graph node layer including a plurality of hierarchical sub-nodes, the hierarchical sub-nodes being connected by internal association edges; extracting environment parameter nodes from the physical parameter knowledge graph, hierarchically aggregating the environment parameter nodes according to parameter types to generate an environment parameter graph node layer, the environment parameter graph node layer including a plurality of hierarchical sub-nodes, the hierarchical sub-nodes being connected by internal association edges; extracting position association edges from the physical parameter knowledge graph, binding the hierarchical sub-nodes of the structure parameter graph node layer and the hierarchical sub-nodes of the device parameter graph node layer through the position association edges to generate a structure-device inter-layer association edge subset; extracting influence association edges from the physical parameter knowledge graph, binding the hierarchical sub-nodes of the device parameter graph node layer and the hierarchical sub-nodes of the environment parameter graph node layer through the influence association edges to generate a device-environment inter-layer association edge subset; extracting interaction association edges from the physical parameter knowledge graph, binding the hierarchical sub-nodes of the environment parameter graph node layer and the hierarchical sub-nodes of the structure parameter graph node layer through the interaction association edges to generate an environment-structure inter-layer association edge subset; integrating the structure-device inter-layer association edge subset, the device-environment inter-layer association edge subset, and the environment-structure inter-layer association edge subset to form an inter-layer association edge set, the inter-layer association edge set including edge weight attributes for representing parameter transmission strengths; constructing a graph reasoning engine, the graph reasoning engine being based on the inter-layer association edge set to implement parameter transmission calculation and logical relationship reasoning, integrating the structure parameter graph node layer, the device parameter graph node layer, the environment parameter graph node layer, the inter-layer association edge set, and the graph reasoning engine to generate a digital twin graph model.

4. The digital twin simulation test method applied to a building system according to claim 1, wherein, The graph test scene configuration sequence is generated according to the inter-layer association edge set and the node interaction path of the digital twin graph model, including: analyzing the inter-layer association edge set of the digital twin graph model to identify all possible interaction paths between the structure parameter graph node layer, the device parameter graph node layer, and the environment parameter graph node layer, each interaction path including a starting graph node, intermediate graph nodes, a terminal graph node, and inter-layer association edges connecting the nodes; dividing test scene types based on the node types of the interaction paths and the attributes of the inter-layer association edges, each test scene type corresponding to the cooperative test requirements of one or more interaction paths, and determining scene test targets for each test scene type; for each test scene type, designing a graph node parameter perturbation rule according to the starting graph node parameter type of the corresponding interaction path and the scene test target, the graph node parameter perturbation rule including initial parameter value settings, parameter continuous change modes, and parameter cooperative perturbation relationships of the starting graph node; designing an association edge trigger condition according to the scene test target and the attributes of the inter-layer association edges of the interaction path, the association edge trigger condition including starting graph node parameter threshold conditions, intermediate graph node state conditions, and inter-layer association edge transmission strength conditions; The test path control logic is designed based on a graph node parameter disturbance rule and an associated edge trigger condition, and includes an interaction path selection strategy, a node parameter injection sequence, and a test process interruption mechanism; The graph node parameter disturbance rule, the associated edge trigger condition, and the test path control logic are associated and integrated according to a test scene type to generate a graph test scene configuration sequence.

5. The digital twin simulation test method applied to a building system according to claim 1, wherein, The graph test scene configuration sequence is input into the digital twin graph model to perform graph coupling simulation testing and generate a graph test response dataset, including: The graph node parameter disturbance rule in the graph test scene configuration sequence is parsed to generate a graph node parameter injection sequence for the digital twin graph model, which includes parameter values and parameter injection time points of starting graph nodes in an interaction path; The graph node state of the digital twin graph model is monitored according to the associated edge trigger condition in the graph test scene configuration sequence, and when the trigger condition is met, the graph node parameter injection sequence is injected into the corresponding starting graph node in order of the parameter injection time points; The graph reasoning engine of the digital twin graph model performs parameter conduction processing based on the inter-layer associated edge set, and the starting graph node receives the parameter injection value and conducts it to the intermediate graph node through the inter-layer associated edge, and the intermediate graph node updates its state and continues to conduct it to the terminal graph node, forming a graph coupling conduction link; During the operation of the graph coupling conduction link, the structural node response sequence of the structural parameter graph node layer, the device node response sequence of the device parameter graph node layer, and the environmental node response sequence of the environmental parameter graph node layer are collected according to the test path control logic, and a graph node response sequence is integrated and generated; The structural node response sequence, the device node response sequence, and the environmental node response sequence in the graph node response sequence are associated and analyzed to extract the parameter value change relationship conducted through the inter-layer associated edge between different graph node layers, and an associated edge conduction relationship data is generated; During the operation of the graph coupling conduction link, the state value of each graph node is monitored, and when the state value of a certain graph node exceeds the normal range, the graph reasoning engine is used to track the path of the abnormal state value from the starting abnormal graph node to the final affected graph node through the intermediate conduction graph node, and the graph node identifier, the inter-layer associated edge identifier, and the conduction order in the abnormal path are recorded to generate abnormal path graph data; The graph node response sequence, the associated edge conduction relationship data, and the abnormal path graph data are integrated to generate a graph test response dataset.

6. The digital twin simulation test method for building system according to claim 1, wherein, The graph structure test result analysis is performed based on the graph test response dataset, and a digital twin simulation test evaluation report of the building system is output, including: The graph node response sequence is extracted from the graph test response dataset, and the response law of the structural node response sequence of the structural parameter graph node layer with respect to the parameter injection value, the response law of the device node response sequence of the device parameter graph node layer with respect to the parameter injection value, and the response law of the environmental node response sequence of the environmental parameter graph node layer with respect to the parameter injection value are analyzed, and a graph node response characteristic is integrated and generated; extracting associated edge conduction relationship data from the graph test response dataset, analyzing parameter influence laws of the associated edges between the structure parameter graph node layer and the device parameter graph node layer, the parameter influence laws of the associated edges between the device parameter graph node layer and the environment parameter graph node layer, and the parameter influence laws of the associated edges between the environment parameter graph node layer and the structure parameter graph node layer, and integrating to generate associated edge influence characteristics; extracting abnormal path graph data from the graph test response dataset, analyzing path laws of abnormal state values from the starting abnormal graph node to the final influence graph node through intermediate conduction graph nodes, range laws involving graph node layers, and speed laws of conduction through interlayer associated edges, combining with importance laws of abnormal graph nodes in the digital twin graph model, and integrating to generate abnormal path graph risk characteristics; comparing and analyzing the graph node response characteristics, the associated edge influence characteristics, and the abnormal path graph risk characteristics with the preset graph structure test evaluation benchmark to determine the compliance degree of each characteristic and the graph node or associated edge that needs to be optimized; integrating the graph node response characteristics, the associated edge influence characteristics, the abnormal path graph risk characteristics, and the comparison and analysis results in a preset report format, and outputting a digital twin simulation test evaluation report.

7. The digital twin simulation test method applied to a building system according to claim 2, wherein, The graph node extraction processing is performed on the structure parameter data, and structure parameter entities and entity attributes are extracted to generate structure parameter nodes, including: performing data cleaning processing on the collected structure parameter data to remove duplicate data records and invalid data fields, and retaining valid data containing structure feature descriptions; performing entity recognition processing on the cleaned structure parameter data, identifying keywords representing structure entities in the data based on a preset structure parameter entity dictionary, the structure entities including wall entity, floor entity, beam column entity, and space region entity; performing attribute extraction processing on the identified structure entities to extract attribute information of each structure entity from the data, the attribute information including entity size attribute, material attribute, position attribute, and connection attribute; assigning a unique node identifier to each structure entity, the node identifier consisting of an entity type prefix and a serial number; dividing the nodes into parameter types according to the types of the structure entities, the parameter types including wall parameter type, floor parameter type, beam column parameter type, and space region parameter type; integrating the node identifier, the parameter type, and the extracted attribute information to generate a structure parameter node, the attribute description information of the structure parameter node including entity size attribute value, material attribute value, position attribute value, and connection attribute value; performing attribute integrity verification on the generated structure parameter nodes to ensure that each node contains at least one core attribute, performing attribute completion processing on the nodes missing core attributes, and verifying again after completion until all structure parameter nodes pass the attribute integrity verification.

8. The digital twin simulation test method applied to a building system according to claim 3, wherein, The graph reasoning engine includes: The parameter conduction calculation module of the design graph reasoning engine receives parameter values of starting graph nodes and edge weight attributes of inter-layer associated edges, calculates input parameter values of intermediate graph nodes through a weighted summation algorithm, and the input of the weighted summation algorithm is the product of the parameter values of the starting graph nodes and the edge weight attributes, and the output is the input parameter values of the intermediate graph nodes; The logical relationship reasoning module of the design graph reasoning engine calls a preset logical reasoning rule library based on the association types of the inter-layer associated edges, reasons the parameter relationships between different graph node layers, and the logical reasoning rule library includes position association reasoning rules, influence association reasoning rules and interaction association reasoning rules; The node state updating module of the design graph reasoning engine receives the input parameter values of the intermediate graph nodes, combines the attribute description information of the nodes themselves, calculates the output parameter values of the nodes through a state conversion function, and the state conversion function is determined based on the parameter types of the nodes; The path search module of the design graph reasoning engine searches all possible conduction paths between any two graph nodes based on the inter-layer associated edge set by using a depth-first search algorithm or a breadth-first search algorithm, and outputs the graph node identifiers and inter-layer associated edge identifiers included in the paths; The parameter conduction calculation module, the logical relationship reasoning module, the node state updating module and the path search module are integrated to construct the core processing unit of the graph reasoning engine, and the data interaction interfaces and calling sequences between the modules are defined; The parameter conduction calculation accuracy, the logical relationship reasoning correctness and the node state updating real-time performance of the graph reasoning engine are verified by inputting preset test parameter values and known conduction paths, the algorithm parameters and reasoning rules in the modules are adjusted until the graph reasoning engine meets the preset performance indicators. 9.The digital twin simulation test method applied to a building system according to claim 5, wherein, The graph reasoning engine of the digital twin graph model performs parameter conduction processing based on the inter-layer associated edge set, the starting graph node receives the parameter injection value and conducts it to the intermediate graph node through the inter-layer associated edge, the intermediate graph node updates its own state and continues to conduct to the terminal graph node, forming a graph coupling conduction link, including: The starting graph node receives the parameter injection value in the graph node parameter injection sequence, and stores the parameter injection value in the current state attribute of the starting graph node; The path search module of the graph reasoning engine finds all directly connected inter-layer associated edges starting from the starting graph node based on the inter-layer associated edge set, and determines the intermediate graph nodes directly connected to the starting graph node; The parameter conduction calculation module calls the edge weight attributes of the inter-layer associated edges between the starting graph node and the intermediate graph node, multiplies the parameter injection value of the starting graph node by the edge weight attributes to obtain the input parameter value of the intermediate graph node; The intermediate graph node receives the input parameter value, the node state updating module calls the state conversion function corresponding to the parameter type of the intermediate graph node, fuses and calculates the input parameter value and the current state attribute value of the intermediate graph node to update the state attribute value, and completes the state update of the intermediate graph node; The path search module continues to find all directly connected inter-layer associated edges starting from the intermediate graph node after the state update, and determines the next level intermediate graph node or the terminal graph node directly connected to the intermediate graph node. If the next level of intermediate graph node is connected, the weighted calculation of the parameter conduction calculation module and the state update of the node state update module are repeated until the termination graph node is reached. If the termination graph node is connected, the parameter conduction calculation module calculates the input parameter value of the termination graph node, and the termination graph node updates its own state attribute value after receiving the input parameter value, completing a parameter conduction. All graph node identifiers, inter-layer associated edge identifiers, parameter values and conduction time points involved in the conduction process from the starting graph node to the termination graph node are recorded to form a conduction log of the graph coupling conduction link.

10. A digital twin simulation test system applied to a building system, characterized in that, The application discloses a digital twin simulation test method applied to a building system, and relates to the technical field of building system simulation. The application discloses a digital twin simulation test method applied to a building system, and relates to the technical field of building system simulation.

Images