Method and equipment for automatically constructing circuit of building electromechanical system

Abstract

The invention provides an automatic construction method and equipment for a building electromechanical system circuit, and the method achieves the quick construction of a building electromechanical system and the efficient retrieval of key paths of equipment through abstracting the equipment attributes and the connection relation into a directed graph and automatically generating the connection relation between the equipment through a link prediction graph neural network model. The method can be used for automatically generating the mutual connection relation between the devices according to given device attributes, so that rapid construction of a building electromechanical system and efficient retrieval of key paths of the devices are achieved, and basic data are provided for the functions of device fault positioning, abnormal energy consumption analysis and the like in the building operation and maintenance stage. According to the method, the efficiency and accuracy of electromechanical system design are improved, reliable basic data support is provided for the functions of equipment fault positioning, abnormal energy consumption analysis and the like in the building operation and maintenance stage, meanwhile, a data link of electromechanical system design, construction and operation and maintenance is broken through, and technical support is provided for digital and intelligent transformation of the building industry.

Description

Technical Field

[0001] The invention relates to a method and equipment for automatically constructing lines of a building electromechanical system. Background Art

[0002] As modern buildings grow in size and expand in functionality, their electromechanical systems become increasingly complex. The number of specialized equipment, such as HVAC, electrical equipment, and plumbing equipment, has skyrocketed, and their interconnections exhibit high-dimensional heterogeneity. Large-scale complex projects (such as hospitals and cultural venues) often involve thousands of electromechanical equipment nodes. These equipment attributes (such as power, flow, interface type, and spatial location) are strongly coupled with connection logic (such as fluid flow direction and voltage level matching). Traditional manual point-by-point wiring within building information models is inefficient and error-prone, and can easily miss connection constraints under specific operating conditions, making it difficult to achieve a globally optimal solution under multi-dimensional constraints.

[0003] Furthermore, existing modeling software or tools lack the ability to automatically extract the implicit topological rules between devices. This leads to a disconnect between as-built models and operational maintenance requirements, making it impossible to quickly locate critical equipment paths and, consequently, support operational maintenance scenarios such as equipment fault tracing and energy consumption analysis. Although some research has attempted to achieve automated wiring through rule engines, their architecture, based on hard-coded logic, struggles to capture the complex nonlinear relationships between device interactions and is unable to learn underlying connection patterns from historical data. Summary of the Invention

[0004] The object of the present invention is to provide a method and device for automatically constructing circuits of a building electromechanical system.

[0005] To solve the above problems, the present invention provides a method for automatically constructing a building electromechanical system circuit, comprising:

[0006] Step 1: Extract the directed graph of the building mechanical and electrical system and construct a link prediction graph neural network dataset based on the directed graph of the building mechanical and electrical system;

[0007] Step 2: Based on the enhanced building electromechanical system link prediction dataset, the building electromechanical system connection relationship is automatically designed through directed graph link prediction to obtain the building electromechanical system line connection diagram S1;

[0008] Step 3: Based on the building electromechanical system line connection diagram S1, the building electromechanical system model is automatically constructed and checked.

[0009] Furthermore, in the above method, a directed graph of the building electromechanical system is extracted, and a link prediction graph neural network dataset is constructed based on the directed graph of the building electromechanical system, including:

[0010] Step 1.1: Obtain the historical building operation and maintenance BIM model, and extract the equipment entities in the electromechanical system of the historical building operation and maintenance BIM model {E i}、Pipeline entity{P i} and the intermediate connector entity set {C i}, and its entity attributes and connection attributes, constitute the building mechanical and electrical system circuit connection diagram S;

[0011] Step 1.2: According to the intermediate connector entity {C i}Connection properties {AL i}, directly build the connection relationship between the upstream and downstream device entities, delete the intermediate connection entity {C i}, obtain the building electromechanical system circuit connection diagram S';

[0012] Step 1.3: According to the equipment entity {E i}、Original pipeline entity{P i} and the merged single pipeline entity {P i _new} entity attributes and connection attributes {AL i}, construct a directed graph G(V,E), where the device entity {E i} as the node set V, the original pipeline entity {P i} and the merged single pipeline entity {P i _new} as the edge set E, the entity attributes of the equipment entity as the node attributes; the entity attributes of the pipeline entity as the edge attributes, and verify the graph structure connectivity and attribute integrity;

[0013] Step 1.4: Perform data enhancement on the directed graph G(V,E) after the graph structure connectivity and attribute integrity verification in step 1.3 to generate an enhanced building electromechanical system link prediction dataset.

[0014] Furthermore, in the above method, the facility entity includes: equipment entity, pipeline entity and intermediate connection entity, wherein the equipment entity and pipeline entity both have entity attributes and connection attributes; the intermediate connection entity only has connection attributes;

[0015] The entity attributes of the equipment entity include at least: equipment type, rated power / flow and spatial location;

[0016] The entity attributes of the pipeline entity include at least: pipeline inner diameter, current carrying capacity;

[0017] The connection attributes of equipment entities, pipeline entities and intermediate connection entities represent the starting and ending facility entities and their connection directions.

[0018] Furthermore, in the above method, step 1.2 includes:

[0019] Step 1.2.1, according to the intermediate connector entity {C i} connection attribute AL i , get the intermediate connector entity {C i} connected to the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end};

[0020] Step 1.2.2, through the starting pipeline entity {P i _start} and terminate the pipeline entity {P i _end}, tracing the starting pipeline entity {P i _start} Directly connected starting device entity {E i _start}, tracing back to the end of the pipeline entity {P i _end} directly connected terminating device entity {E i _end};

[0021] Step 1.2.3, remove the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} between the intermediate connector C i , the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} merged into a single pipeline entity {P i _new}, through a single pipeline entity {P i _new} directly creates the starting device entity {E i _start} and terminate the device entity {E i _end}, and update the starting device entity {E i _start} entity attributes and the termination device entity {E i _end} of the entity connection attribute {AL i}; and create the connection attributes of a single pipeline entity;

[0022] Step 1.2.4: Based on the updated starting device entity {E i _start} and terminate the device entity {E i _end}, calculate the merged single pipeline entity {P i _new}, including the pipe inner diameter and current carrying capacity, to obtain the building mechanical and electrical system line connection diagram S'.

[0023] Furthermore, in the above method, the data enhancement method at least includes: taking the existing edge E as a positive sample, randomly sampling node pairs without edges as negative samples, and generating virtual edge attributes for the negative samples; normalizing or standardizing the node attributes and edge attributes, and extracting high-order graph structure features as supplementary features.

[0024] Furthermore, in the above method, step 2 includes:

[0025] Step 2.1: Select a graph neural network model suitable for directed graph link prediction, and train the graph neural network model based on the enhanced building electromechanical system link prediction dataset to obtain a building electromechanical equipment connection prediction model M with a link prediction accuracy that meets preset requirements;

[0026] Step 2.2: Extract the equipment entities of the building mechanical and electrical system from the BIM model to be designed {E 0i}, construct the initial directed graph G0(V0,E0) of the building electromechanical system; where the node set V0 is composed of the equipment entity {E 0i} mapping, the node attribute is the device entity {E 0i}Entity attribute {AE 0i}, the edge set E0 is initially set to empty and is used for subsequent link prediction tasks;

[0027] Step 2.3: Input the initial directed graph G0 constructed in step 2.2 into the building mechanical and electrical equipment connection prediction model M trained in step 2.1, predict the connection probability between nodes, and generate the building mechanical and electrical system directed graph G1(V1, E1); where the node set V1 is the same as V0, and the edge set E1 consists of node pairs whose predicted connection probability between nodes is higher than a preset threshold, and the corresponding edge attributes are assigned; the node pairs are the starting and ending points of the edges;

[0028] Step 2.4: Extract the circuit connection diagram S0 of the building electromechanical system from the BIM model to be designed, and map the directed graph G1 back to the equipment entity {E 1i} and pipeline entities {P 1i}, and according to the entity attributes and connection attributes of the equipment entity or pipeline entity, merge the pipeline entity according to the preset rules and add intermediate connectors, and update all equipment entities {E 1i}、Pipeline entity{P 1i} and intermediate connector entity {C 1i}, and obtain the building electromechanical system line connection diagram S1 that meets the preset actual engineering requirements.

[0029] Furthermore, in the above method, the preset merging rules include but are not limited to: merging pipeline entities of the same type in similar areas, adding intermediate connectors at the divergence points of pipeline entities, giving priority to the connection layout with the shortest path and the least elbows, and making the properties of the intermediate connectors compatible with the properties of the connected pipes.

[0030] Furthermore, in the above method, step 3 includes:

[0031] Step 3.1: According to the pipeline entity {P 1i} and the intermediate connector entity {C 1i}, define the BIM family instance of the corresponding entity, set the parameters of the family instance to be consistent with the entity attributes and connection attributes in the building mechanical and electrical system line connection diagram S1, and store the defined family instance in the BIM family library to facilitate subsequent model construction and call;

[0032] Step 3.2: According to the pipeline entity {P 1i}、Intermediate connector entity{C 1i} and its entity attributes and connection attributes, automatically call the family instance defined in step 3.1, generate the pipeline and intermediate connector entity model, and complete the series connection of the building's mechanical and electrical equipment;

[0033] Step 3.3: According to the preset building mechanical and electrical system design specifications, check the pipe and intermediate connector solid models generated in step 3.2, and output a detailed report on design issues such as collisions (such as intersections between pipes and building structures or other professional pipelines) and non-compliance with specifications (such as insufficient pipe bending radius and slope that does not meet requirements) in the model. Mark the location, type, and severity of the problem for manual correction of design problems to obtain a building mechanical and electrical system BIM model that meets engineering requirements.

[0034] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is caused to adopt any one of the methods described above.

[0035] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0036] processor; and

[0037] A memory arranged to store computer executable instructions which, when executed, cause the processor to: employ any of the methods described above.

[0038] Compared with the existing technology, the present invention proposes a method for automatically constructing a building electromechanical system based on graph machine learning. By abstracting the device attributes and connection relationships into a directed graph, the link prediction graph neural network model is used to automatically generate the connection relationships between devices, thereby realizing the rapid construction of the building electromechanical system and the efficient retrieval of the key paths of the equipment. It can be used to automatically generate the mutual connection relationships between devices according to the given device attributes, thereby realizing the rapid construction of the building electromechanical system and the efficient retrieval of the key paths of the equipment, and providing basic data for functions such as equipment fault location and abnormal energy consumption analysis in the building operation and maintenance stage. This method not only improves the efficiency and accuracy of electromechanical system design, but also provides reliable basic data support for functions such as equipment fault location and abnormal energy consumption analysis in the building operation and maintenance stage. At the same time, it opens up the data chain of electromechanical system design, construction and operation and maintenance, and provides technical support for the digital and intelligent transformation of the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of a method for automatically constructing a building electromechanical system circuit according to an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of a building electromechanical system before the intermediate connector is removed according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of a building electromechanical system after removing the intermediate connectors according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention is further described in detail below with reference to the accompanying drawings.

[0043] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces and memories.

[0044] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0045] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0046] like Figure 1 As shown, the present invention provides a method for automatically constructing a building electromechanical system circuit, comprising:

[0047] Step 1: Extract the directed graph of the building mechanical and electrical system and construct a link prediction graph neural network dataset based on the directed graph of the building mechanical and electrical system;

[0048] Step 1.1: Obtain the historical building operation and maintenance BIM model, and extract the equipment entity set in the electromechanical system of the historical building operation and maintenance BIM model {E i}、Pipeline entity collection{P i} and the intermediate connector entity set {C i}, and its entity attributes and connection attributes, constitute the building mechanical and electrical system line connection diagram S.

[0049] Preferably, the device entity set {E i}, including but not limited to: power distribution cabinets, transformers, chillers, water pumps, fans, etc.;

[0050] Pipeline entity collection {P i}, including but not limited to: cables, water pipes, air ducts, etc.;

[0051] Intermediate connector entity {C i}, including but not limited to cable intermediate connectors, three-way valves, angle valves, etc.;

[0052] Facility entities include: equipment entities, pipeline entities and intermediate connection entities. Among them, equipment entities and pipeline entities have entity attributes and connection attributes; intermediate connection entities only have connection attributes;

[0053] Equipment entity collection {Ei}Entity attribute AE i At least include: equipment type, rated power / flow, spatial location, etc.;

[0054] Pipeline entity collection {P i}Entity attribute AP i At least include: pipeline inner diameter, current carrying capacity, etc.;

[0055] Equipment entities, pipeline entities, and intermediate connection entities {C i} connection attribute AL i Indicates the starting and ending facility entities and their connection directions.

[0056] Step 1.2: According to the intermediate connector entity {C i}Connection properties {AL i}, directly build the connection relationship between the upstream and downstream device entities, delete the intermediate connection entity {C i}, obtain the building mechanical and electrical system line connection diagram S'.

[0057] Step 1.2.1, according to the intermediate connector entity {C i} connection attribute AL i , get the intermediate connector entity {C i} connected to the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end};

[0058] Step 1.2.2, through the starting pipeline entity {P i _start} and terminate the pipeline entity {P i _end}, tracing the starting pipeline entity {P i _start} Directly connected starting device entity {E i _start}, tracing back to the end of the pipeline entity {P i _end} directly connected terminating device entity {E i _end};

[0059] Step 1.2.3, as Figure 2 and 3 As shown, remove the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} between the intermediate connector C i , the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} merged into a single pipeline entity {P i _new}, through a single pipeline entity {Pi _new} directly creates the starting device entity {E i _start} and terminate the device entity {E i _end}, and update the starting device entity {E i _start} entity attributes and the termination device entity {E i _end} of the entity connection attribute {AL i}; and create the connection attributes of a single pipeline entity;

[0060] Step 1.2.4: Based on the updated starting device entity {E i _start} and terminate the device entity {E i _end}, calculate the merged single pipeline entity {P i _new}, including but not limited to: pipe inner diameter, current carrying capacity, etc., to obtain the building mechanical and electrical system line connection diagram S'.

[0061] Step 1.3: According to the equipment entity {E i}、Original pipeline entity{P i} and the merged single pipeline entity {P i _new} entity attributes and connection attributes {AL i}, construct a directed graph G(V,E), where the device entity {E i} as the node set V, the original pipeline entity {P i} and the merged single pipeline entity {P i _new} as the edge set E, the entity attributes of the equipment entity as the node attributes; the entity attributes of the pipeline entity as the edge attributes, and verify the graph structure connectivity and attribute integrity.

[0062] Step 1.4: Perform data enhancement (data amplification) on the directed graph G(V, E) after the graph structure connectivity and attribute integrity verification in step 1.3 to generate an enhanced building electromechanical system link prediction dataset; the data enhancement method at least includes: using existing edges E as positive samples, randomly sampling node pairs without edges as negative samples, and generating virtual edge attributes for negative samples; normalizing or standardizing node attributes and edge attributes, and extracting high-order graph structure features (such as node degree and shortest path) as supplementary features.

[0063] Step 2: Based on the enhanced building electromechanical system link prediction dataset, the building electromechanical system connection relationship is automatically designed through directed graph link prediction to obtain the building electromechanical system line connection diagram S1;

[0064] Step 2.1: Select a graph neural network model suitable for directed graph link prediction, and train the graph neural network model based on the enhanced building electromechanical system link prediction dataset described in step 1.4 to obtain a building electromechanical equipment connection prediction model M whose link prediction accuracy meets the preset requirements.

[0065] Preferably, the graph neural network model can be GAT (Graph Attention Network), GCN (Graph Convolutional Network) or GraphSAGE; the training process includes hyperparameter adjustment, model performance evaluation and model structure fine-tuning, etc.

[0066] Step 2.2: Extract the equipment entities of the building mechanical and electrical system from the BIM model to be designed {E 0i}, construct the initial directed graph G0(V0,E0) of the building electromechanical system; where the node set V0 is composed of the equipment entity {E 0i} mapping, the node attribute is the device entity {E 0i}Entity attribute {AE 0i} (such as device type, rated power / flow, spatial location, etc.), the edge set E0 is initially set to empty and is used for subsequent link prediction tasks;

[0067] Step 2.3: Input the initial directed graph G0 constructed in step 2.2 into the building mechanical and electrical equipment connection prediction model M trained in step 2.1, predict the connection probability between nodes, and generate the building mechanical and electrical system directed graph G1 (V1, E1); wherein, the node set V1 is the same as V0, and the edge set E1 consists of node pairs whose predicted connection probability between nodes is higher than the preset threshold, and is assigned corresponding edge attributes; the node pairs are the starting and ending points of the edges.

[0068] Step 2.4: Extract the circuit connection diagram S0 of the building electromechanical system from the BIM model to be designed, and map the directed graph G1 back to the equipment entity {E 1i} and pipeline entities {P 1i}, and according to the entity attributes (such as spatial position, pipe inner diameter, current carrying capacity) and connection attributes (such as starting and ending facility entities and connection direction) of the equipment entity or pipeline entity, merge the pipeline entity according to the preset rules and add intermediate connectors (such as three-way valves, angle valves, etc.), and update all equipment entities {E 1i}、Pipeline entity{P 1i} and intermediate connector entity {C 1i}, and obtain the building electromechanical system circuit connection diagram S1 that meets the preset actual engineering requirements;

[0069] Preferably, the preset merging rules include, but are not limited to: merging pipeline entities of the same type in similar areas, adding intermediate connectors at the divergence points of pipeline entities, giving priority to the connection layout with the shortest path and the least elbows, and making the properties of the intermediate connectors compatible with the properties of the connected pipes.

[0070] Specifically, the intermediate connector entity {C i} entity attributes can include: connection inside diameter, current carrying capacity and type;

[0071] Step 3: Based on the building electromechanical system line connection diagram S1, automatically construct and check the building electromechanical system model;

[0072] Step 3.1: According to the pipeline entity {P 1i} and the intermediate connector entity {C 1i}, define the BIM family instance of the corresponding entity, set the parameters of the family instance (such as pipe inner diameter, current carrying capacity, etc.) to be consistent with the entity attributes and connection attributes in the building mechanical and electrical system line connection diagram S1, and store the defined family instance in the BIM family library to facilitate subsequent model construction and call.

[0073] Step 3.2: According to the pipeline entity {P 1i}、Intermediate connector entity{C 1i} and its entity properties and connection properties (such as pipeline inner diameter, current carrying capacity, starting and ending facility entities and connection direction, etc.), automatically call the family instance defined in step 3.1, generate pipeline and intermediate connector entity models, and complete the series connection of building mechanical and electrical equipment.

[0074] Step 3.3: Check the solid models of the pipes and intermediate connectors generated in step 3.2 according to the preset building mechanical and electrical system design specifications. Output a report on collisions and non-compliant design issues in the model, marking the location, type, and severity of the problems.

[0075] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is caused to adopt any one of the methods described above.

[0076] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0077] processor; and

[0078] A memory arranged to store computer executable instructions which, when executed, cause the processor to: employ any of the methods described above.

[0079] In summary, the present invention proposes a method for automatically constructing a building electromechanical system based on graph machine learning, which abstracts the device attributes and connection relationships into a directed graph, and uses a link prediction graph neural network model to automatically generate the connection relationships between devices, thereby realizing the rapid construction of the building electromechanical system and the efficient retrieval of the key paths of the equipment. It can be used to automatically generate the mutual connection relationships between devices according to the given device attributes, thereby realizing the rapid construction of the building electromechanical system and the efficient retrieval of the key paths of the equipment, and providing basic data for functions such as equipment fault location and abnormal energy consumption analysis in the building operation and maintenance stage. This method not only improves the efficiency and accuracy of electromechanical system design, but also provides reliable basic data support for functions such as equipment fault location and abnormal energy consumption analysis in the building operation and maintenance stage, and at the same time opens up the data chain of electromechanical system design, construction and operation and maintenance, providing technical support for the digital and intelligent transformation of the construction industry.

[0080] The detailed contents of the various device embodiments of the present invention can be found in the corresponding parts of the various method embodiments, which will not be repeated here.

[0081] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0082] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0083] In addition, a portion of the present invention may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instructions for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that operates according to the program instructions. Here, according to one embodiment of the present invention, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to operate based on the aforementioned methods and / or technical solutions according to multiple embodiments of the present invention.

[0084] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalents of the claims be encompassed within the present invention. Any figure marks in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A method for automatically constructing a building electromechanical system circuit, characterized in that: include: Step 1: Extract the directed graph of the building mechanical and electrical system and construct a link prediction graph neural network dataset based on the directed graph of the building mechanical and electrical system; Step 2: Based on the enhanced building electromechanical system link prediction dataset, the building electromechanical system connection relationship is automatically designed through directed graph link prediction to obtain the building electromechanical system line connection diagram S1; Step 3: Based on the building electromechanical system line connection diagram S1, the building electromechanical system model is automatically constructed and checked.

2. The method for automatically constructing a building electromechanical system circuit according to claim 1, wherein: Extract the directed graph of the building mechanical and electrical system and construct a link prediction graph neural network dataset based on the directed graph of the building mechanical and electrical system, including: Step 1.1: Obtain the historical building operation and maintenance BIM model, and extract the equipment entities in the electromechanical system of the historical building operation and maintenance BIM model {E i }、Pipeline entity{P i } and the intermediate connector entity set {C i }, and its entity attributes and connection attributes, constitute the building mechanical and electrical system circuit connection diagram S; Step 1.2: According to the intermediate connector entity {C i }Connection properties {AL i }, directly build the connection relationship between the upstream and downstream device entities, delete the intermediate connection entity {C i }, obtain the building electromechanical system circuit connection diagram S'; Step 1.3: According to the equipment entity {E i }、Original pipeline entity{P i } and the merged single pipeline entity {P i _new} entity attributes and connection attributes {AL i }, construct a directed graph G(V,E), where the device entity {E i } as the node set V, the original pipeline entity {P i } and the merged single pipeline entity {P i _new} as the edge set E, the entity attributes of the equipment entity as the node attributes; the entity attributes of the pipeline entity as the edge attributes, and verify the graph structure connectivity and attribute integrity; Step 1.4: Perform data enhancement on the directed graph G(V,E) after the graph structure connectivity and attribute integrity verification in step 1.3 to generate an enhanced building electromechanical system link prediction dataset.

3. The automatic construction method of the building electromechanical system circuit according to claim 2, characterized in that: Facility entities include: equipment entities, pipeline entities and intermediate connection entities. Among them, equipment entities and pipeline entities have entity attributes and connection attributes; intermediate connection entities only have connection attributes; The entity attributes of the equipment entity include at least: equipment type, rated power / flow and spatial location; The entity attributes of the pipeline entity include at least: pipeline inner diameter, current carrying capacity; The connection attributes of equipment entities, pipeline entities and intermediate connection entities represent the starting and ending facility entities and their connection directions.

4. The method for automatically constructing a building electromechanical system circuit according to claim 2, wherein: Step 1.2 includes: Step 1.2.1, according to the intermediate connector entity {C i } connection attribute AL i , get the intermediate connector entity {C i } connected to the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end}; Step 1.2.2, through the starting pipeline entity {P i _start} and terminate the pipeline entity {P i _end}, tracing the starting pipeline entity {P i _start} Directly connected starting device entity {E i _start}, tracing back to the end of the pipeline entity {P i _end} directly connected terminating device entity {E i _end}; Step 1.2.3, remove the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} between the intermediate connector C i , the starting pipeline entity {P i _start} and terminate pipeline entities {P i _end} merged into a single pipeline entity {P i _new}, through a single pipeline entity {P i _new} directly creates the starting device entity {E i _start} and terminate the device entity {E i _end}, and update the starting device entity {E i _start} entity attributes and the termination device entity {E i _end} of the entity connection attribute {AL i }; and create the connection attributes of a single pipeline entity; Step 1.2.4: Based on the updated starting device entity {E i _start} and terminate the device entity {E i _end}, calculate the merged single pipeline entity {P i _new}, including the pipe inner diameter and current carrying capacity, to obtain the building mechanical and electrical system line connection diagram S'.

5. The method for automatically constructing a building electromechanical system circuit according to claim 2, wherein: The data enhancement method at least includes: taking existing edges E as positive samples, randomly sampling node pairs without edges as negative samples, and generating virtual edge attributes for the negative samples; normalizing or standardizing the node attributes and edge attributes, and extracting high-order graph structure features as supplementary features.

6. The method for automatically constructing a building electromechanical system circuit according to claim 4, wherein: Step 2 includes: Step 2.1: Select a graph neural network model suitable for directed graph link prediction, and train the graph neural network model based on the enhanced building electromechanical system link prediction dataset to obtain a building electromechanical equipment connection prediction model M with a link prediction accuracy that meets preset requirements; Step 2.2: Extract the equipment entities of the building mechanical and electrical system from the BIM model to be designed {E 0i }, construct the initial directed graph G0(V0,E0) of the building electromechanical system; where the node set V0 is composed of the equipment entity {E 0i } mapping, the node attribute is the device entity {E 0i }Entity attribute {AE 0i }, the edge set E0 is initially set to empty and is used for subsequent link prediction tasks; Step 2.3: Input the initial directed graph G0 constructed in step 2.2 into the building mechanical and electrical equipment connection prediction model M trained in step 2.1, predict the connection probability between nodes, and generate the building mechanical and electrical system directed graph G1(V1, E1); where the node set V1 is the same as V0, and the edge set E1 consists of node pairs whose predicted connection probability between nodes is higher than a preset threshold, and the corresponding edge attributes are assigned; the node pairs are the starting and ending points of the edges; Step 2.4: Extract the circuit connection diagram S0 of the building electromechanical system from the BIM model to be designed, and map the directed graph G1 back to the equipment entity {E 1i } and pipeline entities {P 1i }, and according to the entity attributes and connection attributes of the equipment entity or pipeline entity, merge the pipeline entity according to the preset rules and add intermediate connectors, and update all equipment entities {E 1i }、Pipeline entity{P 1i } and intermediate connector entity {C 1i }, and obtain the building electromechanical system line connection diagram S1 that meets the preset actual engineering requirements.

7. The method for automatically constructing a building electromechanical system circuit according to claim 6, wherein: The preset merging rules include, but are not limited to: merging pipeline entities of the same type in adjacent areas, adding intermediate connectors at the divergence points of pipeline entities, prioritizing connection layouts with the shortest paths and the fewest elbows, and making the properties of intermediate connectors compatible with the properties of connected pipes.

8. The method for automatically constructing a building electromechanical system circuit according to claim 6, wherein: Step 3 includes: Step 3.1: According to the pipeline entity {P 1i } and the intermediate connector entity {C 1i }, define the BIM family instance of the corresponding entity, set the parameters of the family instance to be consistent with the entity attributes and connection attributes in the building mechanical and electrical system line connection diagram S1, and store the defined family instance in the BIM family library to facilitate subsequent model construction and call; Step 3.2: According to the pipeline entity {P 1i }、Intermediate connector entity{C 1i } and its entity attributes and connection attributes, automatically call the family instance defined in step 3.1, generate the pipeline and intermediate connector entity model, and complete the series connection of the building's mechanical and electrical equipment; Step 3.3: According to the preset building mechanical and electrical system design specifications, check the pipe and intermediate connector solid models generated in step 3.2, and output a detailed report on design issues such as collisions (such as intersections between pipes and building structures or other professional pipelines) and non-compliance with specifications (such as insufficient pipe bending radius and slope that does not meet requirements) in the model. Mark the location, type, and severity of the problem for manual correction of design problems to obtain a building mechanical and electrical system BIM model that meets engineering requirements.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: adopt the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform a method as claimed in any one of claims 1 to 8.

Images