Method of extracting integrity of equipment connections of a building electromechanical system based on graph machine learning

Abstract

The invention discloses a graph machine learning-based building electromechanical system equipment connection relation integrity extraction method, which comprises the following steps of: firstly, based on a preset distance threshold value and a normal included angle threshold value, retrieving non-same component neighbor ports of component ports with connection missing or false connection, and generating a plurality of first candidate edges; then calculating a matching degree score of each first candidate edge; when the first candidate edge with the highest score meets a first matching degree score threshold value, taking the first candidate edge with the highest score as a unique effective connection of a component port; and when the first candidate edge with the highest score does not meet the first matching degree score threshold value, repairing the connection relationship of the component ports through the electromechanical system equipment connection relationship link prediction model so as to realize integrity extraction of the building electromechanical system equipment connection relationship graph in the low-quality BIM model. According to the method, the integrity extraction of the equipment connection relation of the building electromechanical system can be completed in the low-quality BIM model, and the dependence on high-quality modeling is remarkably reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of building operation and maintenance, and particularly relates to a building mechanical and electrical system device connection relationship integrity extraction method based on graph machine learning. BACKGROUND

[0002] The building mechanical and electrical system is the core infrastructure supporting building operation, covering multiple professional subsystems such as heating, ventilation, electrical, water supply and drainage, and fire fighting. Each professional subsystem is connected by a large number of mechanical and electrical equipment through pipelines to form a complete medium and signal transmission network. The connection relationship between mechanical and electrical equipment constitutes the logical framework of the operation mechanism of the building mechanical and electrical system, and plays a key supporting role in scenarios such as operation and maintenance management, fault tracing, energy efficiency analysis, and simulation training. Especially in large public buildings, the number of mechanical and electrical equipment is huge, and the system is complex. Directly querying and analyzing the upstream and downstream relationships of mechanical and electrical equipment by manual work is very inefficient and prone to errors. Based on this, the field adopts a graph theory method to generate the building mechanical and electrical system device connection relationship in the building information model (BIM) of the building. The disadvantage is that the universality of this method is poor, and it is usually only applicable to high-quality BIM models with high modeling accuracy. For low-quality BIM models, due to problems such as component omission, spatial offset, or incomplete attribute definition in the modeling process, false connections, missing ports, and default connector attributes may occur between the components of the building mechanical and electrical system, resulting in incomplete extraction of the building mechanical and electrical system device connection relationship. SUMMARY

[0003] The purpose of the present application is to provide a building mechanical and electrical system device connection relationship integrity extraction method based on graph machine learning, to solve the problem of incomplete extraction of the building mechanical and electrical system device connection relationship due to false connections, missing ports, and default connector attributes when using the graph theory method to automatically extract the building mechanical and electrical system device connection relationship in low-quality BIM models.

[0004] To solve the above technical problems, the technical solution provided by the present application is: a building mechanical and electrical system device connection relationship integrity extraction method based on graph machine learning, comprising: Step 1: based on the graph theory method, constructing the vertex set V in the mechanical and electrical equipment connection relationship graph G=(V, E) from the low-quality BIM model, and extracting the geometric information and attribute information of all components represented by the vertex V i ; wherein the geometric information at least includes three-dimensional coordinates, the floor to which it belongs, the minimum bounding box size, the number of port positions and the normal, and the attribute information at least includes the mechanical and electrical system to which it belongs, the material, the medium, the specification and the port connection information; Step 2: Traverse the vertices Vi in the vertex set V obtained in Step 1. Using the port connection information in the attribute information of vertex Vi, obtain the set of vertices {Vj} directly connected to it. Check if vertex V exists in the electromechanical equipment connection graph G. i With vertex V j The edge (V) i V j If )∈E, and does not exist, then generate the corresponding edge (V). i V j The edge is generated and updated in the electromechanical equipment connection graph G=(V, E). If the edge already exists, it is skipped and the corresponding edge is not generated again. Step 3: Traverse the vertices Vi in the vertex set V mentioned in Step 1. For a vertex Vi that has the characteristics of port number, position and normal information, check whether each port of the component it represents has an edge connection. If a port does not have an edge connection, it is determined that the port connection is missing or false. Wherein, missing connection means that the minimum bounding boxes of two components are connected and the port positions and normals are consistent, but the port connection information attribute is missing; false connection means that the minimum bounding boxes of two components have a small gap, or slightly intersect, or the port normals have a small deviation. Step 4: For ports in the component represented by vertex Vi that are found to have missing or false connections in Step 3, based on the preset distance threshold [d] and normal angle threshold [δ], search for neighboring ports that are not in the same component, generate several first candidate edges, and calculate the matching degree score of each first candidate edge: When the first candidate edge with the highest score satisfies the first matching degree score threshold [S1], the first candidate edge with the highest score is used as the only valid edge connecting the missing or spurious component ports and updated to the edge set E in the electromechanical equipment connection graph G=(V,E); the connectivity analysis of the electromechanical equipment connection graph G=(V,E) is performed, and the vertex set V is merged based on the valid edge connection to form several independent connected subsets, so as to extract the electromechanical system equipment connection subgraph {Gi} in the low-quality BIM model; When the first candidate edge with the highest score does not meet the first matching degree score threshold [S1], the connection relationship of the component port with missing or false connection is repaired by the electromechanical system equipment connection relationship prediction model, so as to completely extract the undirected graph G' of the connection relationship of the building electromechanical system equipment in the low-quality BIM model.

[0005] Furthermore, the method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning provided by the present invention also includes: Step 5: The types of mechanical and electrical equipment in the undirected graph G' of the connection relationship of the mechanical and electrical equipment of the building mechanical and electrical system are identified by using the graph theory method combined with the operation mechanism rules of the building mechanical and electrical system, and the top equipment and the end equipment of the mechanical and electrical system are determined, the shortest path algorithm is used to search the path from each top equipment of the mechanical and electrical system to the corresponding end equipment, so as to determine the one-way flow direction of the medium, and the redundant loops and unnecessary connected edges introduced due to redundant prediction or topological errors are removed in the path analysis process, and the directed graph G'' of the connection relationship of the mechanical and electrical equipment of the building mechanical and electrical system in accordance with the operation mechanism is obtained.

[0006] Further, the building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the present application calculates the matching degree score according to formula (1) in step 4: , (1); In formula (1), S(i, j) is the matching degree score of the first candidate edge, k is each matching degree score index, ω k is the weight of each matching degree score index, wherein 0≤ω k ≤1 and S k (i, j) is the matching degree score of each matching degree score index, sys is the consistency of the mechanical and electrical system, mat is the material consistency, med is the medium consistency, spec is the specification and model consistency, dist is the geometric proximity, ang is the port normal consistency, and floor is the spatial continuity.

[0007] Further, the building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the present application, in step 4, the method for establishing the mechanical and electrical system equipment connection relationship link prediction model comprises: Step 4.1: A plurality of high-quality BIM models of existing engineering projects are used as basic data to extract the mechanical and electrical equipment, pipelines and nodes and their geometric information and attribute information in each BIM model according to the method of steps 1 to 2, so as to convert each high-quality BIM model into a mechanical and electrical system equipment connection relationship graph {G init} with complete structure and accurate mechanical and electrical connection relationship; Step 4.2: The node and edge attributes of the mechanical and electrical system equipment connection relationship graph {G init} of step 4.1 are standardized in a unified coding space, including the geometric information, attribute information and local topological features of the nodes, and the parts with missing or inconsistent attributes are filled according to a preset filling strategy, to obtain a standardized mechanical and electrical system equipment connection relationship graph {G std}; Step 4.3: A preset probability and perturbation parameter set {ε trans , θ rot, δ normal}applying random translation and small angle rotation to the node space coordinates of the normalized mechanical and electrical system equipment connection relationship graph {G std} of step 4.2, while applying small angle perturbation to the port normal, to form several times of geometric enhancement sample set {G geo}; Step 4.4: Controlled random perturbation is applied to the attribute information of the nodes and edges of the geometric enhancement sample set {G std} of step 4.3, including random fine-tuning within a pre-set relative range for numerical attributes or truncation within an engineering allowed range, in-class replacement or approximate class replacement for category attributes according to a set probability, and mask processing for part of the attributes according to a missing simulation rate to generate missing samples, to generate an enhanced graph set {G attr} containing attribute perturbation; Step 4.5: The enhanced graph set {G attr} containing attribute perturbation generated in step 4.4 is taken as positive samples, multiple types of negative samples are constructed according to a set negative sample construction strategy, and the positive and negative samples are labeled to generate a negative sample enhanced graph set {G neg}; Step 4.6: For the negative sample enhanced graph set {G neg} of step 4.5, the f-hop neighborhood subgraph centered on each candidate node is extracted as a local structure sample, and the subgraphs corresponding to different regions and mechanical and electrical systems are spatially translated or combined, and the positive and negative samples, node / edge attribute features, subgraph representations and label information are integrated to generate a link prediction dataset G D with balanced positive and negative samples, complete structure specification and context information, where f is the hop number, an integer; Step 4.7: A small-scale subgraph-level or node representation-based splicing graph neural network model is used as a link prediction model, and the link prediction dataset G D of step 4.6 is used as training sample data to train the link prediction model, and a mechanical and electrical system equipment connection relationship link prediction model M is obtained, which satisfies the requirement of edge prediction accuracy.

[0008] Further, the building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the present application, in step 4, the method for repairing the connection relationship of the components ports with missing or false connections in the mechanical and electrical system equipment connection relationship subgraph {G i} includes: Step 4.8: The mechanical and electrical system equipment connection relationship subgraph {G iThe input is connected to the mechanical and electrical system device connection relationship chain link prediction model M, the probability score of the node pair forming the edge in each subgraph and between the subgraphs is inferred and calculated, and the node pair with the link prediction probability greater than the preset threshold [τ] is selected to generate a second candidate edge set ; wherein the node is a component represented by a vertex with missing port number, position or normal attribute characteristics, and a component represented by a vertex with an existing port not connected by an edge and a first candidate edge not meeting the matching degree score threshold; Step 4.9, according to the matching degree score calculation method, calculate the matching degree score of each second candidate edge in the second candidate edge set in step 4.8, filter the effective prediction second candidate edge set greater than the second matching degree score threshold [S2], and remove the second candidate edge repeatedly predicted between the same node pairs in the effective prediction second candidate edge set , and retain one second candidate edge to update to the mechanical and electrical system device connection relationship subgraph {G i} in step 4, generate the building mechanical and electrical system device connection relationship undirected graph G'.

[0009] Compared with the prior art, the beneficial effects of the present application are as follows: The building mechanical and electrical system device connection relationship integrity extraction method based on graph machine learning provided by the present application is used to extract the building mechanical and electrical system device connection relationship in a low-quality BIM model. When the connection of the component port in the low-quality BIM model is missing or false, and the building mechanical and electrical system device connection relationship cannot be extracted completely, the missing or false connected port is found, then the near neighbor port of the non-same component of the missing or false connected component port is searched based on the preset distance threshold [d] and the normal angle threshold [δ], a plurality of first candidate edges are generated, the matching degree score of each first candidate edge is calculated, and when the first candidate edge with the highest score meets the first matching degree score threshold [S1], the first candidate edge with the highest score is taken as the only effective edge of the missing or false connected component port and is updated to the edge set E in the mechanical and electrical device connection relationship graph G=(V,E). The connectivity of the mechanical and electrical device connection relationship graph G=(V,E) is analyzed, the vertex set V is merged based on the effective edge connection, and a plurality of independent connected subsets are formed, so as to extract the mechanical and electrical system device connection relationship subgraph {G iThis method achieves robust extraction of the connection relationships of effectively connected MEP (Mechanical, Electrical, and Plumbing) system equipment in low-quality BIM models. When the first candidate edge with the highest score does not meet the first matching degree score threshold [S1], the connection relationships of missing or spurious component ports are repaired through the MEP system equipment connection relationship link prediction model. This allows for the complete extraction of the undirected graph G' of the connection relationships of the building's MEP system equipment in the low-quality BIM model, thus achieving the repair processing of missing or spurious connections at the ports of the MEP system equipment in the low-quality BIM model and ensuring the extraction and repair of the connection relationships of missing or spurious component ports. It avoids the problems of incomplete and inaccurate extraction of MEP system equipment connection relationships in low-quality BIM models, and has the advantages of good extraction completeness and high accuracy. It can robustly extract building MEP system equipment connection relationships and achieve intelligent repair even when BIM modeling quality is uneven, attributes are missing or logical errors exist. Compared with manual repair, it has the effect of high repair efficiency and avoids human omissions. It reduces the dependence on high-quality BIM models. Through the complete extraction of building MEP system equipment connection relationships, it can provide reliable data support for fault diagnosis, energy path analysis and abnormal energy consumption location in the building operation and maintenance phase. Attached Figure Description

[0010] Figure 1 This is a flowchart of a method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning. Figure 2 This is a schematic diagram showing a case where there is a gap between the minimum bounding boxes of two components, resulting in a dummy connection at the component port. Figure 3 This is a schematic diagram showing a case where the component ports are spuriously connected due to a slight intersection of the minimum bounding boxes of two components. Figure 4 This is a schematic diagram illustrating a case where the normals of the ports of two components are inconsistent, resulting in a false connection at the port of a component. Figure 5 This is a diagram showing the repaired port dummy connection. Detailed Implementation

[0011] The present invention will now be described in detail with reference to the accompanying drawings. The advantages and features of the present invention will become clearer from the following description. It should be noted that the drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0012] Please refer to Figure 1 This invention provides a method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning, including: Step 1: Construct vertex set V in mechanical and electrical equipment connection relationship graph G=(V, E) from low-quality BIM model based on graph theory method, and extract geometric information and attribute information of components represented by vertex V i ; wherein the geometric information at least includes three-dimensional coordinates, the floor to which it belongs, the minimum bounding box size, the number of port positions and the normal, and the attribute information at least includes the mechanical and electrical system to which it belongs, the material, the medium, the specification and model, and the port connection information. Before constructing the mechanical and electrical equipment connection relationship graph G=(V, E) from the low-quality BIM model based on the graph theory method, the mechanical and electrical equipment, pipes and pipelines, and pipe fittings such as tees, elbows, and valves in the BIM can be uniformly abstracted.

[0013] Step 2: Traverse the vertex V i in the vertex set V in step 1, and obtain the vertex set {V j} directly connected to it through the port connection information in the attribute information of the vertex V i ; check whether there is an edge (V i , V j )∈E between the vertex V i and the vertex V j in the mechanical and electrical equipment connection relationship graph G, if not, generate the corresponding edge (V i , V j ) and update it to the mechanical and electrical equipment connection relationship graph G=(V, E), if it already exists, skip and do not generate the corresponding edge.

[0014] Step 3: Traverse the vertex V i in the vertex set V in step 1, and check whether each port of the component represented by the vertex V i has an edge connection, if a port does not have an edge connection, it is determined that the port connection is missing or false; wherein the connection missing means that the minimum bounding boxes of two components are connected and the port position and normal are consistent, but the attribute information of the port connection is missing; the false connection means that there is a small gap between the minimum bounding boxes of two components, or the minimum bounding boxes slightly intersect, or the normal of the port slightly deflects. Figures 2 to 4 Three examples of false port connections are illustrated.

[0015] Step 4: For the port with missing or false connection in the component represented by the vertex V i in step 3, based on the preset distance threshold [d] and the normal angle threshold [δ], search for the near neighbor port of the non-same component, generate a plurality of first candidate edges, and calculate the matching degree score of each first candidate edge: The matching degree score of each first candidate edge can be calculated according to formula (1): , (1) In formula (1), S(i, j) is the matching degree score of the first candidate edge, k is each matching degree score index, ω k is the weight of each matching degree score index, wherein 0≤ω k ≤1 and S k (i, j) is the matching degree score of each matching degree score index, sys is the electronic system consistency, mat is the material consistency, med is the medium consistency, spec is the specification conformity, dist is the geometric proximity, ang is the port normal consistency, and floor is the spatial continuity.

[0016] The matching degree score of the first candidate edge is calculated through seven indexes of the electronic system consistency, the material consistency, the medium consistency, the specification conformity, the geometric proximity, the port normal consistency, and the port normal consistency in formula (1).

[0017] The electronic system consistency score S sys (i, j) is as follows: (2) The material consistency score S mat (i, j) is as follows: (3) In formula (3), α mat is the value of the inconsistent material; The medium consistency score S med (i, j) is as follows: (4) The specification conformity score S spec (i, j) is as follows: (5) In formula (5), β1, β2, and β3 are the weights of the caliber, the wall thickness, and the interface standard similarity in the specification, respectively, wherein: The caliber similarity score S d (i, j) is as follows: (5.1) In formula (5.1), d i and d j are the calibers of the port i and the port j; The wall thickness similarity score S t (i, j) is as follows: (5.2) The interface standard similarity score S iface (i, j) is as follows: (5.3) wherein the geometric neighborhood score S dist (i, j) is: (6) In formula (6), d is the distance of the two ports; wherein the port normal consistency score S (7) In formula (7), δ is the port normal angle; wherein the spatial continuity score S (8) In formula (8), α floor is the value of the spatial continuity of adjacent layers in the same well.

[0018] When the first candidate edge with the highest score meets the first matching degree score threshold [S1], the first candidate edge with the highest score is taken as the only valid edge of the connected missing or false connected component port, and is updated to the edge set E in the mechanical and electrical equipment connection relationship graph G=(V, E); the connectivity of the mechanical and electrical equipment connection relationship graph G=(V, E) is analyzed, the vertex set V is connected and merged based on the valid edge, and a plurality of independent connected subsets are formed, so as to extract the mechanical and electrical system equipment connection relationship subgraph {G i} in the low-quality BIM model.

[0019] When the first candidate edge with the highest score does not meet the first matching degree score threshold [S1], the connection relationship of the connected missing or false connected component port is repaired by the mechanical and electrical system equipment connection relationship link prediction model, so as to completely extract the connection relationship undirected graph G' of the building mechanical and electrical system equipment in the low-quality BIM model. Figure 5 An example after port false connection repair is shown in Table 1.

[0020] The building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the embodiment of the application is used for integrity extraction of building mechanical and electrical system equipment connection relationship in a low-quality BIM model. When the building mechanical and electrical system equipment connection relationship cannot be extracted integrally due to the connection loss or false connection of component ports in the low-quality BIM model, the lost or false connected component ports are found out, then the near neighbor ports of the non-same components of the lost or false connected component ports are searched based on the preset distance threshold [d] and normal angle threshold [delta], a plurality of first candidate edges are generated, the matching degree score of each first candidate edge is calculated, when the first candidate edge with the highest score meets the first matching degree score threshold [S1], the first candidate edge with the highest score is taken as the only valid edge of the lost or false connected component port and is updated to the edge set E in the mechanical and electrical equipment connection relationship graph G=(V, E), and the connectivity of the mechanical and electrical equipment connection relationship graph G=(V, E) is analyzed, the effective edge connection is used to merge the vertex set V, and a plurality of independent connected subsets are formed, so that the mechanical and electrical system equipment connection relationship subgraph {G i} is extracted in the low-quality BIM model, and the robust extraction of the effective connection mechanical and electrical system equipment connection relationship in the low-quality BIM model is realized. When the first candidate edge with the highest score does not meet the first matching degree score threshold [S1], the connection relationship of the lost or false connected component port is repaired by using the mechanical and electrical system equipment connection relationship link prediction model, so that the connection relationship undirected graph G' of the building mechanical and electrical system equipment is extracted integrally in the low-quality BIM model, the repair processing of the lost or false connected component port in the low-quality BIM model is realized, the extraction and repair of the connection relationship of the lost or false connected component port are ensured, the problem that the mechanical and electrical system equipment connection relationship is not complete and not accurate in the low-quality modeling BIM is avoided, and the method has the advantages of good extraction integrity and high accuracy. The building mechanical and electrical system equipment connection relationship can be robustly extracted and intelligently repaired in the case that the BIM modeling quality is uneven and there is attribute loss or logical error. Compared with manual repair, the method has the effects of high repair efficiency and avoidance of human omission. The dependence on high-quality modeling BIM is reduced, and the complete building mechanical and electrical system equipment connection relationship can provide reliable data support for fault diagnosis, energy path analysis, and abnormal energy consumption positioning in the building operation and maintenance stage.

[0021] In order to construct the mechanical and electrical system equipment connection relationship link prediction model for predicting the connection edge of the lost or false connected component port in the low-quality BIM model, the building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the embodiment of the application comprises the following steps in step 4: Step 4.1: Using high-quality BIM models from several existing engineering projects as base data, extract the mechanical and electrical equipment, pipelines, and nodes, along with their geometric and attribute information, from each BIM model according to the methods in Steps 1 and 2. This process converts each high-quality BIM model into a structurally complete mechanical and electrical system equipment connection diagram {G} with accurate mechanical and electrical connections. init}

[0022] Step 4.2: For the electromechanical system equipment connection diagram from Step 4.1 {G} init The node and edge attributes of {G} are standardized within a unified coding space, including the node's geometric information, attribute information, and local topological features. Simultaneously, missing or inconsistent attribute descriptions are filled in according to a preset filling strategy, resulting in the standardized electromechanical system equipment connection diagram {G}. std The filling strategies include, but are not limited to, filling unknown classes, mean / median interpolation, and retaining missing masks.

[0023] Step 4.3: According to the preset probability and disturbance parameter set {ε} trans , θ rot , δ normal} For the standardized electromechanical system equipment connection diagram of step 4.2 {G std Random translations and small-angle rotations are applied to the node spatial coordinates of {G}, while a small angular perturbation is applied to the port normal to form a geometrically enhanced sample set {G} several times larger. geo}

[0024] Step 4.4: Apply the geometric augmentation sample set {G} from Step 4.3 std The node and edge attribute information of} is subjected to controlled random perturbation, including random fine-tuning of numerical attributes (such as pipe diameter, wall thickness, rated power, etc.) within a preset relative range or truncation within the engineering allowable range, performing intra-class replacement or near-class substitution of categorical attributes (such as material, interface standard, to which the electromechanical system belongs, etc.) according to a set probability, masking some attributes according to the missing simulation rate to generate missing samples, and generating an enhanced atlas {G} containing attribute perturbation. attr}

[0025] Step 4.5: The enhanced atlas {G} generated in Step 4.4, containing attribute perturbations... attr As positive samples, multiple types of negative samples are constructed according to the set negative sample construction strategy, and positive and negative samples are labeled to generate a negative sample enhancement atlas {G}. negThe negative sample construction strategy includes randomly sampling node pairs in the graph that do not have a direct connection relationship, screening node pairs that are geometrically adjacent or have similar topological structures but should not be connected according to the design specifications of the mechatronic system, and the like, to simulate confusing non-connection relationships and improve the counterexample for the mechatronic system device connection relationship link prediction model to be established.

[0026] Step 4.6: Enhancing the negative sample graph set {G neg} of step 4.5, extracting f-hop neighborhood subgraphs centered on each candidate node as local structure samples, and performing spatial translation or structure combination on subgraphs corresponding to different regions and mechatronic systems, integrating positive and negative samples, node / edge attribute features, subgraph representations, and label information, to generate a link prediction dataset G D where f is the number of hops, which is an integer.

[0027] Step 4.7: Using a small-scale subgraph-level or node representation-based splicing graph neural network model as the link prediction model, and using the link prediction dataset G D of step 4.6 as training sample data to train the link prediction model, obtaining a mechatronic system device connection relationship link prediction model M with a satisfactory edge prediction accuracy. The small-scale subgraph-level or node representation-based splicing graph neural network model can be selected from SEAL (Subgraph Embedding Approach for Link prediction), NBFNet (Neural Bellman-Ford Network), GraphSAGE (Graph SAmple and aggreGatE), etc. The model training can use a cross-entropy loss function or a positive and negative sample weighted loss function to iteratively optimize the model parameters, and simultaneously use a pre-set proportion of the validation set and the test set to evaluate the performance of the model. The selection of the above graph neural network model can be based on the data size and the structural characteristics of the building mechatronic system to select an adaptive model.

[0028] To realize intelligent repair of the connection relationship of the component port with missing or false connections, the building mechatronic system device connection relationship integrity extraction method based on graph machine learning provided by the embodiments of the present application includes the following steps: i Step 4.8: Repairing the connection relationship of the component port with missing or false connections in the mechatronic system device connection relationship subgraph {G i ​The input is connected to the mechanical and electrical system device connection relationship chain link prediction model M, the inference calculates the probability score of the node pairs in each subgraph and between subgraphs forming an edge, and selects the node pairs with a link prediction probability greater than a preset threshold [tau] to generate a second candidate edge set ; wherein the node is a component represented by a vertex with missing port number, position or normal attribute characteristics, and a component represented by a vertex with an unestablished edge connection between the ports and a first candidate edge that does not satisfy the matching degree score threshold.

[0029] Step 4.9: According to the matching degree score calculation method, calculate the matching degree score of each second candidate edge in the second candidate edge set in step 4.8, filter the effective predicted second candidate edge set with a second matching degree score greater than a second matching degree score threshold [S2], and remove the duplicate predicted second candidate edges between the same node pairs in the effective predicted second candidate edge set , and retain one second candidate edge to update the mechanical and electrical system device connection relationship subgraph {G i} in step 4, to generate the building mechanical and electrical system device connection relationship undirected graph G'.

[0030] In order to extract the media flow direction of each mechanical and electrical system of the building mechanical and electrical system device connection relationship, thereby providing reliable data support for fault diagnosis, energy path analysis, and abnormal energy consumption positioning in the building operation and maintenance stage. The building mechanical and electrical system device connection relationship integrity extraction method based on graph machine learning provided by the embodiment of the application further comprises: Step 5: Identify the mechanical and electrical equipment types in the building mechanical and electrical system device connection relationship undirected graph G' using the graph theory method combined with the operation mechanism rules of the building mechanical and electrical system, and determine the top-end equipment and the end-end equipment of the mechanical and electrical system. The shortest path algorithm is used to search the path from each mechanical and electrical system top-end equipment to its corresponding end-end equipment, thereby determining the one-way flow direction of the medium, and eliminating redundant loops and unnecessary connected edges introduced due to redundant prediction or topological errors in the path analysis process, to obtain the building mechanical and electrical system device connection relationship directed graph G'' that conforms to the operation mechanism.

[0031] Wherein the operation mechanism of the building mechanical and electrical system includes but is not limited to: in the air conditioning and heating system, the top-end equipment is usually a cold and heat source unit, a cooling tower, etc., and the end-end equipment is usually a fan coil, a supply air outlet, etc.; in the fire water system, the top-end equipment is usually a water pump, a water tank or an external water source access point, and the end-end equipment is usually a fire hydrant, a spray head, etc.

[0032] The graph theory algorithm is a common ancestor identification method based on a shortest path, that is, in a tree-shaped mechanical and electrical equipment connection relationship graph, a vertex with only one connection edge is regarded as a vertex representing an end device, then all the connected paths in the graph are traversed from all the end vertices, and the node with the highest frequency is determined as the common ancestor of the plurality of end nodes, that is, the vertex representing the end device.

[0033] The building mechanical and electrical system equipment connection relationship integrity extraction method based on graph machine learning provided by the embodiment of the application is used for robustly extracting an effective connection part in a building mechanical and electrical system equipment connection relationship in a low-quality modeling BIM, generating a credible device connection relationship subgraph set, then combining a historical high-quality modeling BIM to construct a link prediction model, realizing prediction of an error or missing device connection relationship and link completion between connection relationship subgraphs, and outputting a complete building mechanical and electrical system equipment connection relationship directed graph, so as to be applied to intelligent operation and maintenance scenes such as mechanical and electrical model reconstruction, fault tracing, and energy path analysis, and significantly improve the intelligent level of operation and management of the whole life cycle of a building.

[0034] The present application is not limited to the above-mentioned specific embodiments, and obviously, the above-described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the present application. Those skilled in the art can make other levels of modifications and changes to the present application. Thus, if these modifications and changes of the present application belong to the scope of the claims of the present application, the present application also intends to include these modifications and changes.

Claims

1. A method for extracting the integrity of equipment connection relationships in a building electromechanical system based on graph machine learning, characterized in that, include: Step 1: Construct a vertex set V in the electromechanical equipment connection graph G=(V, E) from the low-quality BIM model using graph theory methods, and extract all connections between vertices V. i The geometric and attribute information of the component is represented; the geometric information includes at least three-dimensional coordinates, floor, minimum bounding box size, number and location of ports, and normals; the attribute information includes at least the electromechanical system to which it belongs, material, medium, specifications, and port connection information. Step 2: Traverse the vertices V in the vertex set V mentioned in Step 1. i Through vertex V i From the port connection information in the attribute information, obtain the set of vertices directly connected to it {V j Check if vertex V exists in the electromechanical equipment connection diagram G. i With vertex V j The edge (V) i V j If )∈E, and does not exist, then generate the corresponding edge (V). i V j The edge is generated and updated in the electromechanical equipment connection graph G=(V, E). If the edge already exists, it is skipped and the corresponding edge is not generated again. Step 3: Traverse the vertices V in the vertex set V mentioned in Step 1. i For a vertex V that has characteristics of port number, location, and normal information... i Check whether each port of the component it represents has edge connections. If a port does not have edge connections, it is determined that the port connection is missing or false. Among them, missing connection means that the minimum bounding boxes of two components are connected and the port positions and normals are consistent, but the connection information attributes of the port are missing. False connection means that the minimum bounding boxes of two components have small gaps, slight intersections, or slight deviations in the port normals. Step 4: For the determination made in Step 3 by vertex V i For ports in the represented components that are missing or spuriously connected, based on preset distance thresholds [d] and normal angle thresholds [δ], the nearest neighbor ports that are not in the same component are retrieved, generating several first candidate edges, and the matching degree score of each first candidate edge is calculated: When the first candidate edge with the highest score satisfies the first matching degree score threshold [S1], the first candidate edge with the highest score is taken as the only valid edge connecting the missing or spurious component ports and updated to the edge set E in the electromechanical equipment connection graph G=(V,E); connectivity analysis is performed on the electromechanical equipment connection graph G=(V,E), and the vertex set V is merged based on the valid edge connection to form several independent connected subsets, so as to extract the electromechanical system equipment connection subgraph {G} from the low-quality BIM model. i }; When the first candidate edge with the highest score does not meet the first matching degree score threshold [S1], the connection relationship of the component port with missing or false connection is repaired by the electromechanical system equipment connection relationship prediction model, so as to completely extract the undirected graph G' of the connection relationship of the building electromechanical system equipment in the low-quality BIM model.

2. The method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning according to claim 1, characterized in that, Also includes: Step 5: Using graph theory methods combined with the operating mechanism rules of building electromechanical systems, identify the types of electromechanical equipment in the undirected graph G' of the building electromechanical system equipment connection relationship and determine the top and bottom devices of the electromechanical system. Use the shortest path algorithm to search the path from each top device to its corresponding bottom device to determine the unidirectional flow direction of the medium. In the path analysis process, remove redundant loops and unnecessary connected edges introduced by redundant prediction or topology errors to obtain the directed graph G'' of the building electromechanical system equipment connection relationship that conforms to the operating mechanism.

3. The method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning according to claim 1, characterized in that, In step 4, the matching score is calculated according to formula (1): ， （1）； In equation (1), S(i, j) is the matching score of the first candidate edge, k is the matching score index of each item, and ω k ω represents the weights of each matching score indicator, where 0 ≤ ω k ≤1 and S k (i, j) represents the matching score of each matching score index, sys represents the consistency of the electromechanical system, mat represents the consistency of the material, med represents the consistency of the medium, spec represents the conformity of the specification model, dist represents the geometric proximity, ang represents the port normal consistency, and floor represents the spatial continuity.

4. The method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning according to claim 1, characterized in that, In step 4, the method for establishing a link prediction model for the connection relationship of electromechanical system equipment includes: Step 4.1: Using high-quality BIM models from several existing engineering projects as base data, extract the mechanical and electrical equipment, pipelines, and nodes, along with their geometric and attribute information, from each BIM model according to the methods in Steps 1 and 2. This process converts each high-quality BIM model into a structurally complete mechanical and electrical system equipment connection diagram {G} with accurate mechanical and electrical connections. init }; Step 4.2: For the electromechanical system equipment connection diagram from Step 4.1 {G} init The node and edge attributes of {G} are standardized within a unified coding space, including the node's geometric information, attribute information, and local topological features. Simultaneously, missing or inconsistent attribute descriptions are filled in according to a preset filling strategy, resulting in the standardized electromechanical system equipment connection diagram {G}. std }; Step 4.3: According to the preset probability and disturbance parameter set {ε} trans , θ rot , δ normal } For the standardized electromechanical system equipment connection diagram of step 4.2 {G std Random translations and small-angle rotations are applied to the node spatial coordinates of {G}, while a small angular perturbation is applied to the port normal to form a geometrically enhanced sample set {G} several times larger. geo }; Step 4.4: Apply the geometric augmentation sample set {G} from Step 4.3 std The nodes and edges of the graph are subjected to controlled random perturbations, including random fine-tuning of numerical attributes within a preset relative range or truncation within the engineering allowable range, performing intra-class replacement or approximate class substitution on categorical attributes according to a set probability, masking some attributes according to the missing simulation rate to generate missing samples, and generating an enhanced graph {G} containing attribute perturbations. attr }; Step 4.5: The enhanced atlas {G} generated in Step 4.4, containing attribute perturbations... attr As positive samples, multiple types of negative samples are constructed according to the set negative sample construction strategy, and positive and negative samples are labeled to generate a negative sample enhancement atlas {G}. neg }; Step 4.6: Enhance the negative sample atlas {G} from Step 4.5 neg The algorithm extracts f-hop neighborhood subgraphs centered on each candidate node as local structure samples. It then performs spatial translation or structural combination on the subgraphs corresponding to different regions and mechatronic systems. By integrating positive and negative samples, node / edge attribute features, subgraph representations, and label information, it generates a link prediction dataset G that is structurally sound, contextually complete, and balanced between positive and negative samples. D Where f is the number of jumps, which is an integer; Step 4.7: Employ a small-scale subgraph-level or node-representation-based graph neural network model as the link prediction model, using the link prediction dataset G from Step 4.

6. D The link prediction model is trained using the training sample data to obtain the electromechanical system equipment connection relationship link prediction model M, which meets the requirements of edge prediction accuracy.

5. The method for extracting the integrity of connection relationships of building electromechanical system equipment based on graph machine learning according to claim 1, characterized in that, In step 4, the electromechanical system equipment connection relationship subgraph {G} is predicted using the electromechanical system equipment connection relationship link prediction model. i Methods for repairing the connection relationships of missing or tampered component ports in a document include: Step 4.8, extract the electromechanical system equipment connection relationship subgraph {G} from the low-quality BIM model in Step 4. i The input is fed into the electromechanical system equipment connection relationship link prediction model M. The model calculates the probability scores of node pairs forming edges within and between subgraphs, and selects node pairs with link prediction probabilities greater than a preset threshold [τ] to generate a second candidate edge set. The nodes are, in particular, components represented by vertices that lack port number, position, or normal attribute features, and components represented by vertices that have ports without established edge connections and whose first candidate edges do not meet the matching degree score threshold. Step 4.9: Calculate the second candidate edge set from Step 4.8 according to the matching score calculation method. The matching score of each second candidate edge is used to filter the set of valid predicted second candidate edges that are greater than the second matching score threshold [S2]. And will effectively predict the second candidate edge set. In the process of deduplicating the second candidate edges predicted repeatedly between the same node pairs, one second candidate edge is retained and updated to the electromechanical system equipment connection relationship subgraph {G} described in step 4. i In the process, an undirected graph G' representing the connection relationships of building electromechanical system equipment is generated.

Images