A BIM Power Engineering Collaborative Design Method and Related Devices

Abstract

An embodiment of the present invention provides a BIM power engineering collaborative design method and related devices. By obtaining multiple professional design model data, cross-professional feature extraction is performed on the multiple professional design model data to generate a set of feature information associated with each professional design model. Based on a preset set of power engineering constraint rules, conflict coordination processing is performed on the cross-professional feature information in the set of feature information to determine collaborative constraint parameters associated with the multiple professional design models. According to the collaborative constraint parameters, parameter synchronization update is performed on the multiple professional design model data to generate a unified power engineering collaborative design model. Finally, three-dimensional spatial coordinate data and device interface parameter data corresponding to the power engineering collaborative design model are output, and a data docking protocol with an external construction system is triggered.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a BIM power engineering collaborative design method and related devices. Background Art

[0002] BIM power engineering collaborative design aims to achieve global coordination and conflict pre-resolution of design schemes by integrating multi-professional model data such as electrical equipment, structural supports, and pipeline distributions. Existing technologies usually adopt the method of independent modeling by different specialties followed by manual comparison. After each professional team separately completes the positioning of electrical equipment, the layout of structural supports, and the planning of pipeline paths, they rely on manual experience to perform spatial overlap detection and parameter coordination on multi-professional models, and achieve conflict resolution by manually adjusting model parameters. Finally, the design results are integrated and output. In the existing method, due to the lack of a dynamic association mechanism for multi-professional model data, cross-professional features are fragmented. It is difficult for manual inspection to capture in real time the spatial interference between the equipment installation area and the structural support distribution, and the cross conflicts between the pipeline routes and the equipment interfaces. Moreover, manual adjustment is prone to cause inconsistent parameter versions. During the construction stage, secondary format conversion and data reconstruction of the design model are required, resulting in a long design iteration cycle, low coordination efficiency, and a significant increase in the risk of construction rework caused by missed cross-professional conflicts, seriously restricting the accuracy and implementation efficiency of power engineering design. Summary of the Invention

[0003] The present invention provides a BIM power engineering collaborative design method and related devices.

[0004] In a first aspect, an embodiment of the present invention provides a BIM power engineering collaborative design method, the method including: obtaining a plurality of professional design model data, where the plurality of professional design model data includes electrical equipment model data, structural support model data, and pipeline distribution model data; performing cross-professional feature extraction on the plurality of professional design model data to generate a set of feature information associated with each professional design model, the set of feature information including geometric feature information and attribute feature information; based on a preset set of power engineering constraint rules, performing conflict coordination processing on the cross-professional feature information in the set of feature information to determine collaborative constraint parameters associated with the plurality of professional design models; synchronously updating the parameters of the plurality of professional design model data according to the collaborative constraint parameters to generate a unified BIM power engineering collaborative design model; outputting three-dimensional spatial coordinate data and equipment interface parameter data corresponding to the BIM power engineering collaborative design model.

[0005] In a second aspect, an embodiment of the present invention provides a BIM power engineering collaborative design device, including: a memory in which a computer program is stored; a processor configured to load the computer program to implement the BIM power engineering collaborative design method as described above.

[0006] The BIM power engineering collaborative design method provided by the present invention obtains electrical equipment model data, structural support model data, and pipeline distribution model data, extracts cross-professional features, generates a feature information set including geometric feature information and attribute feature information, performs conflict coordination processing on the cross-professional feature information based on a preset power engineering constraint rule set, determines collaborative constraint parameters, and then synchronously updates the multi-professional model data to generate a unified power engineering collaborative design model, and outputs standardized three-dimensional space coordinate data and equipment interface parameter data to achieve seamless docking with an external construction system. By integrating the geometric features and attribute features of multi-professional design data, using preset rules to dynamically detect spatial overlap conflicts between equipment installation positions and structural support distributions, and cross-interference problems between pipeline routes and equipment layouts, automatically generating coordination parameters and synchronously updating each professional model, effectively solving problems such as version inconsistency, low efficiency of manual coordination, and difficult construction docking caused by the fragmentation of multi-professional data in traditional designs. Through cross-professional feature association and rule-driven dynamic adjustment, it can significantly improve the overall understanding ability of complex engineering scenarios during the design process, strengthen the equipment positioning accuracy, optimize the structural load transfer path, and the rationality of pipeline avoidance logic. At the same time, the direct compatibility of the standardized output data with the construction system reduces the secondary data processing link, thus ensuring the feasibility of the design results and the efficient collaboration in the construction stage, and comprehensively improving the accuracy of power engineering design and the reliability of project implementation. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a flowchart of a BIM power engineering collaborative design method provided by an embodiment of the present invention.

[0008] Figure 2 is a schematic diagram of the composition of a BIM power engineering collaborative design device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] Please refer to Figure 1 , Figure 1 which is a flowchart of a BIM power engineering collaborative design method provided by an embodiment of the present invention. This BIM power engineering collaborative design method can be executed by a BIM power engineering collaborative design device. The BIM power engineering collaborative design method may include the following steps:

[0010] Step S100: Obtain multiple professional design model data, where the multiple professional design model data includes electrical equipment model data, structural support model data, and pipeline distribution model data.

[0011] In this step, the electrical equipment model data describes the detailed information of various electrical equipment in a power project. This information includes the type, size, installation location, rated parameters, etc. of the equipment. For example, the specific specifications and spatial location information of equipment such as transformers, switchgear, and motors. The structural support model data is the relevant data of the structural members that support electrical equipment and pipelines, covering the type, size, location, and load-bearing capacity of the members. For example, the detailed parameters of support structures such as steel beams and concrete columns. The pipeline distribution model data records the information such as the routing, pipe diameter, and flow rate of various pipelines in the power project. For example, the specific layout and parameters of pipelines such as cable trays, water pipes, and air ducts. The ways to obtain these data are, for example, to export the existing model data from design software or to obtain the actual physical parameter information through on-site measurement and data collection equipment. For example, for the electrical equipment model data, the 3D model and attribute information of the equipment can be extracted from electrical design software; for the structural support model data, the detailed data of the structural members can be exported using Building Information Modeling (BIM) software; for the pipeline distribution model data, the spatial location and size information of the pipelines can be obtained through laser scanning equipment.

[0012] Step S200: Extract cross-professional features from multiple professional design model data to generate a set of feature information associated with each professional design model. The set of feature information includes geometric feature information and attribute feature information.

[0013] The cross-professional feature extraction in the present invention refers to mining the feature information related to other professions from the design model data of different professions to achieve collaborative design among various professions. The geometric feature information mainly describes the geometric attributes such as the spatial location, shape, and size of the model. For example, the installation location of the equipment, the distribution of the support members, and the routing path of the pipelines. The attribute feature information is the attribute parameters in terms of physics, electricity, mechanics, etc. of the model. For example, the rated parameters of the equipment, the load-bearing capacity of the support members, and the pipe diameter and flow rate parameters of the pipelines. The purpose of generating the set of feature information is to integrate these geometric and attribute feature information together for subsequent conflict coordination and collaborative design. In the specific implementation process, technologies such as machine learning and data mining can be used to analyze and process the model data. For example, a deep learning model is used to analyze the electrical equipment model data to extract feature information such as the installation location and rated parameters of the equipment.

[0014] As an implementation manner, step S200, extracting cross-professional features from multiple professional design model data to generate a set of feature information associated with each professional design model, may specifically include the following steps S210 to step S260:

[0015] Step S210: Input the electrical equipment model data into the pre-trained feature recognition model to extract the first geometric feature information associated with the installation location of the electrical equipment and the first attribute feature information associated with the rated parameters of the equipment.

[0016] The pre-trained feature recognition model is a model trained with a large amount of historical power engineering design data, which can automatically identify and extract key feature information from the electrical equipment model data. The first geometric feature information mainly relates to the installation location of the electrical equipment in three-dimensional space, such as the positioning reference point of the equipment, the scope of the installation area, etc. The first attribute feature information is related to the rated parameters of the equipment, such as rated voltage, rated current, interface specifications, etc. In actual operation, after inputting the electrical equipment model data into the pre-trained feature recognition model, the data is processed and analyzed according to the internal algorithms and rules. For example, the model can use a convolutional neural network (CNN) to extract features from the three-dimensional model of the electrical equipment and identify the installation location and rated parameter information of the equipment.

[0017] As an implementation, in step S210, inputting the electrical equipment model data into the pre-trained feature recognition model to extract the first geometric feature information associated with the installation location of the electrical equipment and the first attribute feature information associated with the rated parameters of the equipment may specifically include:

[0018] Step S211: Analyze the three-dimensional space coordinate points set and the equipment attribute labels in the electrical equipment model data to generate intermediate analysis data including the equipment installation base point coordinates and the hierarchical relationship topology diagram.

[0019] In this step, the three-dimensional space coordinate points set refers to the specific position information of the electrical equipment in three-dimensional space, such as represented by a series of coordinate points. The equipment attribute labels are identifiers used to describe various attributes of the equipment, such as equipment type, rated parameters, etc. The analysis process is to extract and organize this information in the electrical equipment model data to generate intermediate analysis data. Specifically, data analysis algorithms can be used to process the model data. For example, regular expressions are used to match and extract the data to separate the three-dimensional space coordinate points set and the equipment attribute labels. The equipment installation base point coordinates in the generated intermediate analysis data are the key information to determine the installation location of the equipment, and the hierarchical relationship topology diagram describes the hierarchical structure and connection relationship between the equipment, which helps to analyze the layout and association of the equipment in the subsequent process.

[0020] Step S212: Perform spatial clustering processing on the equipment installation base point coordinates in the intermediate analysis data to identify the dense coordinate regions associated with the same electrical equipment, and extract the geometric center coordinates of the dense coordinate regions as the equipment positioning reference point in the first geometric feature information.

[0021] Spatial clustering processing is a method of grouping data points in space according to their spatial positions, aiming to cluster the coordinate points belonging to the same electrical equipment together. In this step, by performing cluster analysis on the equipment installation base point coordinates in the intermediate parsed data, areas where the coordinate points are relatively dense can be identified. These areas usually represent the installation positions of the same electrical equipment. Then, calculate the geometric center coordinates of these dense coordinate areas and use them as the equipment positioning reference points. Specific clustering algorithms can be DBSCAN (Density-Based Spatial Clustering of Applications with Noise) or K-Means algorithm, etc. For example, using the DBSCAN algorithm, set appropriate neighborhood radius and minimum point number parameters, cluster the equipment installation base point coordinates, find the dense areas and calculate their geometric center coordinates.

[0022] Step S213: Determine the topological weight coefficient of the electrical equipment in the overall layout according to the connection path length and the number of branches between the equipment nodes in the hierarchical relationship topology graph, and perform spatial superposition of the topological weight coefficient and the equipment positioning reference point to generate a geometric distribution map with weight annotations.

[0023] The hierarchical relationship topology graph describes the connection relationship and hierarchical structure between electrical equipment. The connection path length between equipment nodes reflects the distance and association degree between equipment, and the number of branches represents the connection complexity of the equipment. By analyzing this information, the topological weight coefficient of each electrical equipment in the overall layout can be determined, and this coefficient is used to measure the importance and influence of the equipment in the layout. Performing spatial superposition of the topological weight coefficient and the equipment positioning reference point means combining the weight information with the spatial position information of the equipment to generate a geometric distribution map with weight annotations. In specific implementation, graph theory algorithms can be used to analyze the hierarchical relationship topology graph and calculate the topological weight coefficient of the equipment. For example, use the Dijkstra algorithm to calculate the shortest path length between equipment nodes, and determine the topological weight coefficient according to the path length and the number of branches. Then, associate the weight coefficient with the coordinate information of the equipment positioning reference point to generate a geometric distribution map with weight annotations.

[0024] Step S214: Synchronously parse the rated voltage parameter, rated current parameter and interface specification parameter in the equipment attribute label, and convert the parameter descriptions in different formats into an attribute parameter vector in a unified dimension through semantic relationship mapping rules.

[0025] The rated voltage parameter, rated current parameter, and interface specification parameter in the device property label are important information for describing the performance and characteristics of electrical equipment. However, these parameters may have different formats and representations. The semantic relationship mapping rule is a rule used to uniformly convert parameter descriptions in different formats. Through this rule, these parameters can be converted into an attribute parameter vector in a unified dimension. When specifically implemented, a semantic mapping table can be established to map parameter descriptions in different formats to a unified standard representation. For example, for the rated voltage parameter, there may be different representations such as "220V" and "0.22kV". Through the semantic mapping table, they are uniformly converted into values in volts (V). Then, these unified parameter values are combined into an attribute parameter vector.

[0026] Step S215: Verify the data consistency between the attribute parameter vector and the geometric distribution atlas with weighted annotations, and eliminate abnormal device nodes with spatial position conflicts or parameter logical contradictions.

[0027] Data consistency verification is a process to ensure that the information between the attribute parameter vector and the geometric distribution atlas with weighted annotations matches and coordinates with each other. Spatial position conflicts may be manifested as the installation position of the device overlapping with other devices or structural supports, and parameter logical contradictions may refer to the rated parameters of the device not matching the actual situation or having unreasonable combinations. During the verification process, it is necessary to compare and analyze the attribute parameter vector and the geometric distribution atlas with weighted annotations to find abnormal device nodes with conflicts or contradictions. When specifically implemented, methods such as rule matching and logical reasoning can be used for verification. For example, check whether the rated current parameter of the device matches the installation position and connection relationship of the device. If there is a mismatch, it is considered that the device node is abnormal. For abnormal device nodes, they can be removed from the dataset to ensure the accuracy of subsequent analysis and design.

[0028] Step S216: Classify and integrate the verified attribute parameter vectors by device type into the first attribute feature information, and dynamically associate them with the device positioning reference points in the geometric distribution atlas with weighted annotations to generate a feature information set containing a geometric-attribute bidirectional indexing relationship; among them, the geometric distribution atlas with weighted annotations is used as the input data for spatial overlap relationship analysis in subsequent steps, and the bidirectional indexing relationship in the feature information set is used for conflict coordination processing of cross-professional feature information.

[0029] Classifying and integrating the verified attribute parameter vectors by device type means merging and organizing the attribute parameters of devices of the same type to form the first attribute feature information. This facilitates the unified management and analysis of different types of devices. Then, the first attribute feature information is dynamically associated with the device positioning reference points in the geometric distribution atlas with weighted annotations to establish a geometric-attribute two-way indexing relationship. This two-way indexing relationship enables quick query of the attribute feature information through the geometric position information of the device and also query of the corresponding geometric position information through the attribute feature information. In specific implementation, database technology can be used to store and associate the attribute parameter vectors and the device positioning reference points. For example, a relational database can be established, storing the device type, attribute parameter vectors, and device positioning reference points as fields of a table, and establishing a two-way index through the relationship between the primary key and the foreign key. The generated set of feature information will provide important basic data for subsequent analysis of spatial overlap relationships and conflict coordination processing of cross-professional feature information.

[0030] Step S220: Input the structural support model data into the feature recognition model to extract the second geometric feature information associated with the distribution of support members and the second attribute feature information associated with the load-bearing parameters.

[0031] The feature recognition model is also pre-trained and can analyze and process the structural support model data. The second geometric feature information mainly describes the distribution of support members in space, such as the position, shape, and distribution density of support members. The second attribute feature information involves the load-bearing capacity of support members, such as static load values, dynamic load peaks, and seismic resistance grades. After inputting the structural support model data into the feature recognition model, the model will extract the relevant geometric and attribute feature information according to its internal algorithms and rules. For example, the model can use machine learning algorithms to analyze the three-dimensional model of support members to identify the distribution and load-bearing parameters of support members.

[0032] As an implementation method, in step S220, inputting the structural support model data into the feature recognition model to extract the second geometric feature information associated with the distribution of support members and the second attribute feature information associated with the load-bearing parameters may specifically include:

[0033] Step S221: Analyze the component node coordinate set and load parameter labels in the structural support model data to generate intermediate analysis data containing the connection point coordinates of support members and the load distribution levels.

[0034] The component node coordinate set is the node position information of the structural support components in three-dimensional space, and the load parameter label is the relevant identifier describing the loads borne by the support components. The parsing process is to extract and organize this information in the structural support model data to generate intermediate parsed data. In specific implementation, a data parsing algorithm can be used to process the model data. For example, an XML parser can be used to parse the data to separate the component node coordinate set and the load parameter label. The connection point coordinates of the support components in the generated intermediate parsed data are the key information for determining the connection relationship and spatial position of the support components, and the load distribution level describes the transfer and distribution of loads between the support components, which helps to analyze the mechanical properties of the support components subsequently.

[0035] Step S222: Perform spatial density clustering on the component node coordinate set in the intermediate parsed data, identify the demarcation threshold between the dense area and the sparse area of the support component distribution, and extract the boundary coordinates of the dense area as the support component distribution density map in the second geometric feature information.

[0036] Spatial density clustering is a method of grouping the component node coordinate set according to its spatial density, aiming to find the dense and sparse areas of the support component distribution. By setting an appropriate demarcation threshold, the coordinate set can be divided into different areas. Extract the boundary coordinates of the dense area to form the support component distribution density map, which can visually display the distribution of the support components. Specific clustering algorithms can choose the DBSCAN algorithm or the OPTICS algorithm, etc. For example, using the DBSCAN algorithm, set appropriate neighborhood radius and minimum point number parameters, cluster the component node coordinate set, find the dense area and extract its boundary coordinates.

[0037] Step S223: Determine the load sharing ratio of each support component in the overall structure according to the load transfer path direction of different components in the load distribution level, and perform type mapping and superposition on the load sharing ratio and the support component distribution density map to generate a geometric distribution map with type identifiers.

[0038] The load distribution hierarchy describes the transfer path and distribution of loads among supporting members. By analyzing the load transfer path directions of different members, the load sharing ratio of each supporting member in the overall structure can be determined. Mapping and overlaying the load sharing ratio with the supporting member distribution density map means combining the load sharing ratio information with the spatial distribution information of the supporting members to generate a geometric distribution map with type identifiers. In specific implementation, graph theory algorithms can be used to analyze the load distribution hierarchy and calculate the load sharing ratios of each supporting member. For example, the topological sorting algorithm can be used to sort the load transfer paths, and the load sharing ratios can be determined according to the sorting results. Then, the load sharing ratios are associated with the boundary coordinates of the supporting member distribution density map to generate a geometric distribution map with type identifiers.

[0039] Step S224: Synchronously parse the static load value, dynamic load peak value, and seismic grade parameter in the load parameter tag, and convert the discrete load description fields into a load parameter vector with a unified dimension through the parameter normalization rule.

[0040] The static load value, dynamic load peak value, and seismic grade parameter in the load parameter tag are important information for describing the load-bearing capacity of the supporting members, but these parameters may have different units and representations. The parameter normalization rule is a rule used to uniformly convert load description fields with different dimensions. Through this rule, these parameters can be converted into a load parameter vector with a unified dimension. In specific implementation, a normalization function can be established to convert different load description fields into a unified standard representation. For example, for the static load value and dynamic load peak value, they can be converted into values in Newtons (N); for the seismic grade parameter, it can be converted into the corresponding seismic acceleration value. Then, these unified parameter values are combined into a load parameter vector for subsequent analysis and processing.

[0041] Step S225: Verify the consistency of the load direction between the load parameter vector and the geometric distribution map with type identifiers, and filter out abnormal supporting nodes where the load transfer path does not match the member distribution direction.

[0042] The verification of load direction consistency is a process to ensure the mutual matching and coordination of the load transfer direction information between the load parameter vector and the geometric distribution diagram with type identifiers. The mismatch between the load transfer path and the component distribution direction may lead to unstable mechanical properties of the support structure or potential safety hazards. During the verification process, it is necessary to compare and analyze the load parameter vector and the geometric distribution diagram with type identifiers to identify abnormal support nodes with mismatches. Specifically, when implementing, methods of rule matching and logical reasoning can be used for verification. For example, check whether the load transfer path of the support component is consistent with the component distribution direction. If there is an inconsistency, it is considered that the support node is abnormal. For abnormal support nodes, they can be screened out from the dataset for further processing and optimization.

[0043] Step S226: Classify and integrate the verified load parameter vector according to the support component type into the second attribute feature information, and perform direction association with the support component distribution density map in the geometric distribution diagram with type identifiers to generate a feature information set containing the load-distribution two-way binding relationship; among them, the geometric distribution diagram with type identifiers is used as the input data for the spatial overlap relationship analysis in the subsequent steps, and the two-way binding relationship in the feature information set is used for the conflict coordination processing of cross-professional feature information.

[0044] Classifying and integrating the verified load parameter vector according to the support component type means merging and sorting the load parameters of the support components of the same type to form the second attribute feature information. This can facilitate the unified management and analysis of different types of support components. Then, perform direction association between the second attribute feature information and the support component distribution density map in the geometric distribution diagram with type identifiers to establish a load-distribution two-way binding relationship. This two-way binding relationship enables quick query of the distribution situation through the load parameter information of the support component, and also enables query of the corresponding load parameter information through the distribution situation. Specifically, when implementing, database technology can be used to store and associate the load parameter vector and the support component distribution density map. For example, establish a relational database, store the support component type, the load parameter vector, and the boundary coordinates of the support component distribution density map as the fields of the table, and establish a two-way binding through the relationship between the primary key and the foreign key. The generated feature information set will provide important basic data for the subsequent spatial overlap relationship analysis and the conflict coordination processing of cross-professional feature information.

[0045] Step S230: Input the pipeline distribution model data into the feature recognition model to extract the third geometric feature information associated with the pipeline routing path and the third attribute feature information associated with the pipe diameter flow parameters.

[0046] The feature recognition model can analyze and process the pipeline distribution model data, and extract relevant geometric and attribute feature information. The third geometric feature information mainly describes the routing path of the pipeline in space, such as the turning points and extension directions of the pipeline. The third attribute feature information involves parameters such as the pipe diameter and flow rate of the pipeline, such as pipe diameter size, maximum flow threshold, pressure loss coefficient, etc. After inputting the pipeline distribution model data into the feature recognition model, the model will extract this feature information according to its internal algorithms and rules. For example, the model can use a path planning algorithm to analyze the 3D model of the pipeline and identify the routing path and pipe diameter flow parameters of the pipeline.

[0047] As an implementation manner, in step S230, input the pipeline distribution model data into the feature recognition model, and extract the third geometric feature information associated with the pipeline routing path and the third attribute feature information associated with the pipe diameter flow parameters. Specifically, it may include:

[0048] Step S231: Analyze the pipeline node coordinate set and flow parameter tags in the pipeline distribution model data, and generate intermediate analysis data including the pipeline turning point coordinates and the connection relationship topology graph.

[0049] The pipeline node coordinate set refers to the node position information of the pipeline in 3D space, and the flow parameter tags are the identifiers describing the pipeline flow. The analysis process is to extract and organize this information in the pipeline distribution model data to generate intermediate analysis data. Specifically in implementation, a data analysis algorithm can be used to process the model data. For example, use a JSON parser to parse the data and separate the pipeline node coordinate set and flow parameter tags. The pipeline turning point coordinates in the generated intermediate analysis data are the key information for determining the pipeline routing path, and the connection relationship topology graph describes the connection relationship and hierarchical structure between pipelines, which helps to analyze the layout and association of pipelines subsequently.

[0050] Step S232: Perform a spatial continuity analysis on the pipeline node coordinate set in the intermediate analysis data, identify the path extension direction between adjacent pipeline nodes, and extract the continuously changing heading angle sequence in the path extension direction as the pipeline routing path segment direction vector in the third geometric feature information.

[0051] Spatial continuity analysis is a method for analyzing the continuity and relevance between data points in space. In this step, by analyzing the pipeline node coordinate set in the intermediate parsed data, the path extension directions between adjacent pipeline nodes are found. Then, the sequence of trend angles with continuous changes in these path extension directions is extracted and used as the direction vector of the pipeline trend path segment. This vector can accurately describe the pipeline trend path. In specific implementation, a differential algorithm can be used to calculate the angle changes between adjacent pipeline nodes and extract the sequence of trend angles with continuous changes. For example, the method of vector cross product is used to calculate the included angles between adjacent pipeline nodes, and these included angles are arranged in sequence to form the sequence of trend angles.

[0052] Step S233: Determine the fluid transmission priority of each pipeline path segment in the overall distribution according to the intersection type and connection depth of the pipeline branch nodes in the connection relationship topology diagram, and perform a flow direction association mapping between the fluid transmission priority and the direction vector of the pipeline trend path segment to generate a geometric distribution network diagram with flow direction labels.

[0053] The connection relationship topology diagram describes the connection relationship and hierarchical structure between pipelines. The intersection type and connection depth of pipeline branch nodes reflect the complexity and importance of pipelines. By analyzing this information, the fluid transmission priority of each pipeline path segment in the overall distribution can be determined. Performing a flow direction association mapping between the fluid transmission priority and the direction vector of the pipeline trend path segment means combining the priority information with the pipeline trend path information to generate a geometric distribution network diagram with flow direction labels. In specific implementation, graph theory algorithms can be used to analyze the connection relationship topology diagram and calculate the fluid transmission priority of each pipeline path segment. For example, the breadth-first search algorithm is used to traverse the connection relationship topology diagram, and the fluid transmission priority is determined according to the traversal result. Then, the priority information is associated with the direction information of the pipeline trend path segment direction vector to generate a geometric distribution network diagram with flow direction labels.

[0054] Step S234: Synchronously parse the pipe diameter size parameter, maximum flow threshold, and pressure loss coefficient in the flow parameter label, and convert the heterogeneous flow description information into a pipe diameter flow parameter vector with a unified dimension through parameter standardization rules.

[0055] The pipe diameter size parameter, maximum flow threshold, and pressure loss coefficient in the flow parameter label are important information for describing the flow characteristics of pipelines. However, these parameters may have different formats and representations. The parameter standardization rule is a rule used to uniformly convert different formats of flow description information. Through this rule, these parameters can be converted into a pipe diameter flow parameter vector of a unified dimension. When specifically implemented, a standardization function can be established to convert different flow description information into a unified standard representation. For example, for the pipe diameter size parameter, it can be converted into a value in millimeters (mm); for the maximum flow threshold and pressure loss coefficient, they can be converted into corresponding dimensionless values. Then, these unified parameter values are combined into a pipe diameter flow parameter vector for subsequent analysis and processing.

[0056] Step S235: Verify the hydrodynamic consistency between the pipe diameter flow parameter vector and the geometric distribution network diagram with flow direction markings, and screen out abnormal pipeline nodes where the flow direction marking conflicts with the direction vector of the pipeline routing path segment.

[0057] Hydrodynamic consistency verification is a process to ensure that the fluid flow information between the pipe diameter flow parameter vector and the geometric distribution network diagram with flow direction markings is mutually matched and coordinated. A reverse conflict between the flow direction marking and the direction vector of the pipeline routing path segment may lead to a reduction in the fluid transmission efficiency of the pipeline or safety problems. During the verification process, it is necessary to compare and analyze the pipe diameter flow parameter vector and the geometric distribution network diagram with flow direction markings to find abnormal pipeline nodes with conflicts. When specifically implemented, methods of rule matching and logical reasoning can be used for verification. For example, check whether the flow direction marking of the pipeline is consistent with the direction of the direction vector of the pipeline routing path segment. If there is an inconsistent situation, it is considered that there is an abnormality in this pipeline node. For abnormal pipeline nodes, they can be screened out from the dataset to ensure the accuracy of subsequent analysis and design.

[0058] Step S236: Classify and integrate the verified pipe diameter flow parameter vector according to the pipeline transmission medium type into the third attribute feature information, and perform dynamic matching with the direction vector of the pipeline routing path segment in the geometric distribution network diagram with flow direction markings to generate a feature information set containing a two-way mapping relationship between path and flow; among them, the geometric distribution network diagram with flow direction markings is used as the input data for spatial intersection relationship analysis in subsequent steps, and the two-way mapping relationship in the feature information set is used for conflict coordination processing of cross-professional feature information.

[0059] Classifying and integrating the verified pipe diameter flow parameter vectors according to the pipeline transmission medium type means merging and sorting the pipe diameter flow parameters of pipelines of the same type to form the third attribute feature information. This can facilitate the unified management and analysis of different types of pipelines. Then, dynamically match the third attribute feature information with the pipeline routing path segment direction vectors in the geometric distribution network diagram with flow direction identifiers to establish a two-way mapping relationship between the path and the flow. This two-way mapping relationship enables the quick query of the pipe diameter flow parameter information through the pipeline routing path information and also enables the query of the corresponding routing path information through the pipe diameter flow parameter information. In specific implementation, database technology can be used to store and associate the pipe diameter flow parameter vectors and the pipeline routing path segment direction vectors. For example, establish a relational database, store the pipeline transmission medium type, the pipe diameter flow parameter vectors, and the direction information of the pipeline routing path segment direction vectors as fields of the table, and establish a two-way mapping through the relationship between the primary key and the foreign key. The generated set of feature information will provide important basic data for subsequent spatial intersection relationship analysis and conflict coordination processing of cross-professional feature information.

[0060] Step S240: Determine the first association feature between the electrical equipment and the structural support according to the spatial overlap relationship between the first geometric feature information and the second geometric feature information.

[0061] The first geometric feature information describes geometric attributes such as the installation location of the electrical equipment, and the second geometric feature information describes geometric attributes such as the distribution of the structural support members. The spatial overlap relationship refers to the coincidence situation in space between the installation location of the electrical equipment and the distribution area of the structural support members. By analyzing this spatial overlap relationship, the first association feature between the electrical equipment and the structural support can be determined. These association features can reflect the mutual influence and constraint relationship between the electrical equipment and the structural support, which is helpful for collaborative design and conflict coordination. In specific implementation, spatial analysis algorithms can be used to process and analyze the first geometric feature information and the second geometric feature information. For example, use Boolean operations to perform an intersection operation on the installation area of the electrical equipment and the distribution area of the structural support members to find the overlapping area.

[0062] As an implementation method, step S240, determining the first association feature between the electrical equipment and the structural support according to the spatial overlap relationship between the first geometric feature information and the second geometric feature information, may specifically include:

[0063] Step S241: Extract the three-dimensional coordinate range of the equipment positioning reference point from the geometric distribution atlas with weight annotations, and extract the spatial coverage area corresponding to the support member distribution density map from the geometric distribution map with type identifiers.

[0064] The geometric distribution atlas with weight annotations contains the positioning reference points and topological weight information of electrical equipment. By extracting the three-dimensional coordinate range of the equipment positioning reference points, the installation position of the electrical equipment can be determined. The geometric distribution map with type identification contains the distribution density map of the support members and the load sharing ratio information. By extracting the spatial coverage area corresponding to the distribution density map of the support members, the distribution range of the structural support members can be determined. In specific implementation, the required information can be extracted from the corresponding atlas and distribution map through database query operations. For example, use SQL statements to query the three-dimensional coordinate range of the equipment positioning reference points from the database table storing the geometric distribution atlas with weight annotations.

[0065] Step S242: Perform a spatial boundary overlay analysis on the three-dimensional coordinate range and the spatial coverage area to identify the overlapping area between the equipment positioning reference points and the distribution area of the support members, and generate overlapping area identification data containing the overlapping boundary coordinates.

[0066] Spatial boundary overlay analysis is to compare and analyze the boundaries of two spatial regions to find their overlapping parts. In this step, perform an overlay analysis on the three-dimensional coordinate range of the equipment positioning reference points and the spatial coverage area corresponding to the distribution density map of the support members to identify the overlapping area. The generated overlapping area identification data contains the boundary coordinates of the overlapping area, and this coordinate information can be used for subsequent analysis and processing. In specific implementation, a spatial analysis algorithm can be used to process the boundaries of the two regions. For example, use the polygon overlay algorithm to overlay the boundary polygons of the three-dimensional coordinate range and the spatial coverage area to find the boundary coordinates of the overlapping area.

[0067] Step S243: According to the overlapping area identification data, determine the set of support member nodes that have spatial conflicts with the equipment positioning reference points, and calculate the adjustment direction parameters of the set of support member nodes based on the load sharing ratio in the geometric distribution map with type identification.

[0068] The overlapping area identification data provides the overlapping information between the equipment positioning reference points and the distribution area of the support members. By analyzing this information, the set of support member nodes that have spatial conflicts with the equipment positioning reference points can be determined. The load sharing ratio in the geometric distribution map with type identification reflects the force conditions of each support member in the overall structure. Based on these ratios, the adjustment direction parameters of the set of support member nodes can be calculated. This parameter is used to guide the adjustment and optimization of the support members to solve the spatial conflict problem. In specific implementation, methods of rule matching and mechanical analysis can be used for calculation. For example, according to the position and size of the overlapping area, determine which support member nodes conflict with the equipment positioning reference points; then, use the principle of mechanical equilibrium to calculate the adjustment direction parameters of the set of support member nodes based on the load sharing ratio in the geometric distribution map with type identification.

[0069] Step S244: Perform displacement compensation processing on the coordinates of the support member node set based on the adjustment direction parameter, generate coordinate data for the support avoidance area, and synchronously update the spatial coverage area boundary in the geometric distribution map with type identifiers.

[0070] The displacement compensation processing adjusts the coordinates of the support member node set according to the adjustment direction parameter to avoid spatial conflicts with the equipment positioning reference points. The generated coordinate data for the support avoidance area describes the distribution range of the adjusted support members. At the same time, it is necessary to synchronously update the spatial coverage area boundary in the geometric distribution map with type identifiers to reflect the new distribution of the support members. In specific implementation, a coordinate transformation algorithm can be used to adjust the coordinates of the support member node set. For example, according to the adjustment direction parameter, a translation transformation is used to displace the coordinates of the support member nodes to generate coordinate data for the support avoidance area; then, the spatial coverage area boundary polygon in the geometric distribution map with type identifiers is updated.

[0071] Step S245: Dynamically analyze the spatial relative position between the updated spatial coverage area boundary and the equipment positioning reference points, and extract the safety distance parameter and spatial mapping relationship between the support member node set after displacement compensation processing and the equipment positioning reference points.

[0072] The dynamic analysis performs real-time analysis and calculation on the spatial relative position between the updated spatial coverage area boundary and the equipment positioning reference points. Through the analysis, the safety distance parameter and spatial mapping relationship between the support member node set after displacement compensation processing and the equipment positioning reference points can be extracted. The safety distance parameter is used to ensure the safety distance between electrical equipment and structural supports, and the spatial mapping relationship describes the spatial association and constraint relationship between the two. In specific implementation, a spatial analysis algorithm can be used to process the updated spatial coverage area boundary and the equipment positioning reference points. For example, a distance calculation algorithm is used to calculate the shortest distance between the support member node set and the equipment positioning reference points as the safety distance parameter; a spatial mapping function is used to establish the spatial mapping relationship between the two.

[0073] Step S246: Logically associate the safety distance parameter with the spatial mapping relationship to generate a first association feature containing equipment-support spatial avoidance rules and conflict coordination paths; among them, the conflict coordination path in the first association feature is used as the direct input for generating subsequent collaborative constraint parameters, and the equipment-support spatial avoidance rules are used for parameter synchronization update of cross-professional feature information.

[0074] Logically associating the safety distance parameter with the space mapping relationship is to integrate and correlate the information of both, forming a complete associated feature. The generated first associated feature includes the equipment-support space avoidance rule and the conflict coordination path. The equipment-support space avoidance rule stipulates the space avoidance requirements between electrical equipment and structural supports, and is used for parameter synchronization update of cross-professional feature information; the conflict coordination path provides specific steps and methods for resolving space conflicts and serves as the direct input for generating subsequent collaborative constraint parameters. When specifically implemented, methods of logical reasoning and rule formulation can be used for association and generation. For example, based on the safety distance parameter and the space mapping relationship, the equipment-support space avoidance rule is formulated; based on the process and methods for conflict resolution, the conflict coordination path is generated.

[0075] Step S250: Determine the second associated feature between the pipeline distribution and the electrical equipment according to the spatial intersection relationship between the third geometric feature information and the first geometric feature information.

[0076] The third geometric feature information describes geometric attributes such as the routing path of the pipeline, and the first geometric feature information describes geometric attributes such as the installation position of the electrical equipment. The spatial intersection relationship refers to the intersection situation in space between the routing path of the pipeline and the installation position of the electrical equipment. By analyzing this spatial intersection relationship, the second associated feature between the pipeline distribution and the electrical equipment can be determined. These associated features can reflect the mutual influence and constraint relationship between the pipeline and the electrical equipment, which is helpful for collaborative design and conflict coordination. When specifically implemented, spatial analysis algorithms can be used to process and analyze the third geometric feature information and the first geometric feature information. For example, the line segment intersection algorithm is used to detect the intersection of the routing path of the pipeline and the installation area of the electrical equipment to find the intersection area.

[0077] As an implementation manner, in step S250, to determine the second associated feature between the pipeline distribution and the electrical equipment according to the spatial intersection relationship between the third geometric feature information and the first geometric feature information, it may specifically include:

[0078] Step S251: Extract the three-dimensional extension range of the direction vector of the pipeline routing path segment from the geometric distribution network diagram with flow direction markings, and obtain the coordinate distribution area of the equipment positioning reference point from the geometric distribution atlas with weight markings.

[0079] The geometric distribution network diagram with flow direction identification contains the direction vectors of the pipeline routing path segments and the fluid transmission priority information. By extracting the three-dimensional extension range of the direction vectors of the pipeline routing path segments, the pipeline routing path can be determined. The geometric distribution atlas with weight annotation contains the positioning reference points of electrical equipment and the topological weight information. By obtaining the coordinate distribution area of the equipment positioning reference points, the installation position of the electrical equipment can be determined. During specific implementation, the required information can be extracted from the corresponding atlas and network diagram through database query operations. For example, use SQL statements to query the three-dimensional extension range of the direction vectors of the pipeline routing path segments from the database table storing the geometric distribution network diagram with flow direction identification.

[0080] Step S252: Conduct a spatial trajectory intersection analysis on the three-dimensional extension range and the coordinate distribution area to identify the intersection area between the direction vectors of the pipeline routing path segments and the equipment positioning reference points, and generate intersection area identification data including the intersection point coordinates and the direction conflict types.

[0081] Spatial trajectory intersection analysis is to compare and analyze two spatial trajectories to find out their intersection parts. In this step, conduct an intersection analysis on the three-dimensional extension range of the direction vectors of the pipeline routing path segments and the coordinate distribution area of the equipment positioning reference points to identify the intersection area. The generated intersection area identification data contains the coordinates of the intersection points and the direction conflict types, and this information can be used for subsequent analysis and processing. During specific implementation, spatial analysis algorithms can be used to process the two trajectories. For example, use the ray method to detect the intersection of the three-dimensional extension range and the coordinate distribution area to find the coordinates of the intersection points; judge the direction conflict types according to the vector directions at the intersection points.

[0082] Step S253: Based on the intersection area identification data, determine the set of electrical equipment nodes with spatial interference with the pipeline path, and calculate the displacement priority parameters of the set of electrical equipment nodes according to the topological weight coefficients in the geometric distribution atlas with weight annotation.

[0083] The intersection area identification data provides the intersection information between the direction vectors of the pipeline routing path segments and the equipment positioning reference points. By analyzing this information, the set of electrical equipment nodes with spatial interference with the pipeline path can be determined. The topological weight coefficients in the geometric distribution atlas with weight annotation reflect the importance and influence of each electrical equipment in the overall layout. Based on these coefficients, the displacement priority parameters of the set of electrical equipment nodes can be calculated. This parameter is used to guide the adjustment and optimization of electrical equipment to solve the spatial interference problem. During specific implementation, rule matching and sorting algorithms can be used for calculation. For example, according to the position and size of the intersection area, determine which electrical equipment nodes interfere with the pipeline path; then, according to the topological weight coefficients in the geometric distribution atlas with weight annotation, use the sorting algorithm to calculate the displacement priority parameters of the set of electrical equipment nodes.

[0084] Step S254: Perform position offset processing on the coordinates of the electrical equipment node set based on the displacement priority parameter to generate pipeline avoidance path coordinate data, and synchronously update the device positioning reference points in the geometric distribution map with weight annotations.

[0085] The position offset processing adjusts the coordinates of the electrical equipment node set according to the displacement priority parameter to avoid spatial interference with the pipeline path. The generated pipeline avoidance path coordinate data describes the avoidance range of the adjusted pipeline path. At the same time, it is necessary to synchronously update the device positioning reference points in the geometric distribution map with weight annotations to reflect the new positions of the electrical equipment. When specifically implemented, a coordinate transformation algorithm can be used to adjust the coordinates of the electrical equipment node set. For example, according to the displacement priority parameter, a translation transformation is used to displace the coordinates of the electrical equipment nodes to generate pipeline avoidance path coordinate data; then, the device positioning reference points in the geometric distribution map with weight annotations are updated.

[0086] Step S255: Dynamically analyze the spatial relative relationship between the updated device positioning reference points and the direction vectors of the pipeline routing path segments, and extract the safety distance parameters and flow direction mapping relationship between the electrical equipment node set after position offset processing and the pipeline path.

[0087] The dynamic analysis is to perform real-time analysis and calculation on the spatial relative positions between the updated device positioning reference points and the direction vectors of the pipeline routing path segments. Through the analysis, the safety distance parameters and flow direction mapping relationship between the electrical equipment node set after position offset processing and the pipeline path can be extracted. The safety distance parameters are used to ensure the safety distance between the electrical equipment and the pipeline, and the flow direction mapping relationship describes the fluid flow association and constraint relationship between the two. When specifically implemented, a spatial analysis algorithm can be used to process the updated device positioning reference points and the direction vectors of the pipeline routing path segments. For example, a distance calculation algorithm is used to calculate the shortest distance between the electrical equipment node set and the pipeline path as the safety distance parameter; a flow direction mapping function is used to establish the flow direction mapping relationship between the two.

[0088] Step S256: Logically associate the safety distance parameters and the flow direction mapping relationship to generate a second associated feature including pipeline-equipment spatial avoidance rules and flow direction coordination paths; among them, the flow direction coordination path in the second associated feature is used as the basic input for generating subsequent collaborative constraint parameters, and the pipeline-equipment spatial avoidance rules are used for parameter synchronization update of cross-professional feature information.

[0089] Logically associating the safety distance parameter with the flow direction mapping relationship integrates and correlates the information of both to form a complete associated feature. The generated second associated feature includes the pipeline-equipment spatial avoidance rule and the flow direction coordination path. The pipeline-equipment spatial avoidance rule stipulates the spatial avoidance requirements between pipelines and electrical equipment and is used for the parameter synchronization update of cross-professional feature information; the flow direction coordination path provides the specific steps and methods for solving fluid flow direction conflicts and serves as the basic input for generating subsequent collaborative constraint parameters. When specifically implemented, logical reasoning and rule-making methods can be used for association and generation. For example, based on the safety distance parameter and the flow direction mapping relationship, the pipeline-equipment spatial avoidance rule is formulated; based on the process and methods for resolving flow direction conflicts, the flow direction coordination path is generated.

[0090] Step S260: Integrate the first associated feature, the second associated feature, and all attribute feature information into a feature information set.

[0091] Integrate the first associated feature, the second associated feature, and all the previously extracted attribute feature information to form a complete feature information set. This set includes the associated features and their attribute feature information among electrical equipment, structural supports, and pipelines, providing comprehensive data support for subsequent conflict coordination and collaborative design. When specifically implemented, data fusion technology can be used to integrate this information. For example, use the merge operation of the database to store the first associated feature, the second associated feature, and the attribute feature information in the same database table to form the feature information set.

[0092] Step S300: Based on a preset set of power engineering constraint rules, perform conflict coordination processing on the cross-professional feature information in the feature information set to determine the collaborative constraint parameters associated with multiple professional design models.

[0093] The preset set of power engineering constraint rules is a series of predefined rules used to regulate various parameters and relationships in power engineering design, such as spatial safety rules, pipeline avoidance rules, load transfer rules, etc. The cross-professional feature information in the feature information set includes the associated features and their attribute feature information among electrical equipment, structural supports, and pipelines. By performing conflict coordination processing on this cross-professional feature information, existing conflicts can be identified and resolved, thereby determining the collaborative constraint parameters associated with multiple professional design models. These collaborative constraint parameters are used to guide subsequent model updates and collaborative design. When specifically implemented, rule matching and optimization algorithms can be used to process the feature information set. For example, use the constraint satisfaction algorithm to match and optimize the cross-professional feature information in the feature information set to find the collaborative constraint parameters that satisfy the set of power engineering constraint rules.

[0094] As an implementation manner, in step S300, based on a preset set of power engineering constraint rules, conflict coordination processing is performed on the cross-professional feature information in the feature information set to determine collaborative constraint parameters associated with multiple professional design models, which may specifically include:

[0095] Step S310: Extract the device positioning reference points in the geometric distribution atlas with weight annotations, the distribution density map of support members in the geometric distribution map with type identifiers, and the direction vectors of the pipeline routing path segments in the geometric distribution network diagram with flow direction identifiers from the feature information set.

[0096] Extracting these key information from the feature information set is to provide basic data for subsequent conflict coordination processing. The device positioning reference points in the geometric distribution atlas with weight annotations describe the installation positions of electrical devices, the distribution density map of support members in the geometric distribution map with type identifiers describes the distribution of structural support members, and the direction vectors of the pipeline routing path segments in the geometric distribution network diagram with flow direction identifiers describe the routing paths of pipelines. Specifically in implementation, these information can be extracted from the feature information set through database query operations. For example, use SQL statements to query the device positioning reference points, the distribution density map of support members, and the direction vectors of the pipeline routing path segments from the database table storing the feature information set.

[0097] Step S320: Based on the space safety rules in the set of power engineering constraint rules, detect the first spatial overlap area between the device positioning reference points and the distribution density map of support members, and generate support member displacement compensation parameters according to the device-support space avoidance rule in the first associated feature.

[0098] The space safety rules in the set of power engineering constraint rules stipulate the safety distance requirements between electrical devices and structural supports. By detecting the first spatial overlap area between the device positioning reference points and the distribution density map of support members, the parts with spatial conflicts can be found. The device-support space avoidance rule in the first associated feature provides a method to solve this conflict. According to this rule, support member displacement compensation parameters can be generated to adjust the positions of support members to meet the space safety rules. Specifically in implementation, a spatial analysis algorithm can be used to process the device positioning reference points and the distribution density map of support members to find the first spatial overlap area; then, generate support member displacement compensation parameters according to the device-support space avoidance rule. For example, use Boolean operations to perform an intersection operation on the three-dimensional coordinate range of the device positioning reference points and the spatial coverage area corresponding to the distribution density map of support members to find the overlap area; generate support member displacement compensation parameters according to the safety spacing parameters and adjustment direction parameters in the device-support space avoidance rule.

[0099] Step S330: Based on the pipeline avoidance rules in the power engineering constraint rule set, detect the second spatial intersection area between the equipment positioning reference point and the direction vector of the pipeline routing path segment, and generate equipment positioning offset parameters according to the pipeline-equipment spatial avoidance rules in the second association feature.

[0100] The pipeline avoidance rules in the power engineering constraint rule set stipulate the avoidance requirements between electrical equipment and pipelines. By detecting the second spatial intersection area between the equipment positioning reference point and the direction vector of the pipeline routing path segment, the parts with spatial interference can be found. The pipeline-equipment spatial avoidance rules in the second association feature provide a method to solve this interference. According to this rule, equipment positioning offset parameters can be generated to adjust the position of electrical equipment to meet the pipeline avoidance rules. In specific implementation, spatial analysis algorithms can be used to process the equipment positioning reference point and the direction vector of the pipeline routing path segment to find the second spatial intersection area; then, equipment positioning offset parameters can be generated according to the pipeline-equipment spatial avoidance rules. For example, use the line segment intersection algorithm to detect the intersection of the coordinate distribution area of the equipment positioning reference point and the three-dimensional extension range of the direction vector of the pipeline routing path segment to find the intersection area; generate equipment positioning offset parameters according to the safety distance parameter and displacement priority parameter in the pipeline-equipment spatial avoidance rules.

[0101] Step S340: Based on the load transfer rules in the power engineering constraint rule set, detect the third spatial interference area between the support member distribution density map and the direction vector of the pipeline routing path segment, and generate pipeline path adjustment parameters according to the load sharing ratio in the geometric distribution map with type identification.

[0102] The load transfer rules in the power engineering constraint rule set stipulate the load transfer requirements between structural supports and pipelines. By detecting the third spatial interference area between the support member distribution density map and the direction vector of the pipeline routing path segment, the parts with spatial conflicts can be found. The load sharing ratio in the geometric distribution map with type identification reflects the force condition of each support member in the overall structure. According to this ratio, pipeline path adjustment parameters can be generated to adjust the pipeline path to meet the load transfer rules. In specific implementation, spatial analysis algorithms can be used to process the support member distribution density map and the direction vector of the pipeline routing path segment to find the third spatial interference area; then, pipeline path adjustment parameters can be generated according to the load sharing ratio in the geometric distribution map with type identification. For example, use Boolean operations to perform an intersection operation on the spatial coverage area corresponding to the support member distribution density map and the three-dimensional extension range of the direction vector of the pipeline routing path segment to find the interference area; generate pipeline path adjustment parameters according to the load sharing ratio in the geometric distribution map with type identification and the principle of mechanical balance.

[0103] Step S350: Classify and integrate the support member displacement compensation parameters, equipment positioning offset parameters, and pipeline path adjustment parameters according to professional types to generate collaborative constraint parameters including spatial avoidance rules, load transfer priorities, and flow coordination paths. Among them, the support member displacement compensation parameters in the collaborative constraint parameters are used to update the structural support model data, the equipment positioning offset parameters are used to synchronize the electrical equipment model data, and the pipeline path adjustment parameters are used to correct the pipeline distribution model data.

[0104] Classify and integrate the generated support member displacement compensation parameters, equipment positioning offset parameters, and pipeline path adjustment parameters according to professional types to form collaborative constraint parameters. These collaborative constraint parameters contain information such as spatial avoidance rules, load transfer priorities, and flow coordination paths, and are used to guide the data update and correction of multiple professional design models. When specifically implemented, data classification and integration techniques can be used to process these parameters. For example, use the grouping and merging operations of the database to store the support member displacement compensation parameters, equipment positioning offset parameters, and pipeline path adjustment parameters in different database tables according to professional types, and then merge these tables to generate collaborative constraint parameters. The support member displacement compensation parameters are used to update the component connection point coordinate set in the structural support model data, the equipment positioning offset parameters are used to synchronize the equipment installation base point coordinates in the electrical equipment model data, and the pipeline path adjustment parameters are used to correct the pipeline node coordinate set in the pipeline distribution model data.

[0105] Step S400: Synchronously update the parameters of multiple professional design model data according to the collaborative constraint parameters to generate a unified collaborative design model for the power project.

[0106] The collaborative constraint parameters contain information such as support member displacement compensation parameters, equipment positioning offset parameters, and pipeline path adjustment parameters, and these parameters are used to guide the data update of multiple professional design models. By reversely mapping these parameters to the corresponding model data, synchronous update of the parameters can be achieved. The generated unified collaborative design model for the power project contains the updated electrical equipment model data, structural support model data, and pipeline distribution model data, ensuring the consistency and coordination among various professional design models. When specifically implemented, data mapping and update techniques can be used to process the data of multiple professional design models. For example, use the update operation of the database to reversely map the support member displacement compensation parameters in the collaborative constraint parameters to the component connection point coordinate set in the structural support model data, map the equipment positioning offset parameters to the equipment installation base point coordinates in the electrical equipment model data, and map the pipeline path adjustment parameters to the pipeline node coordinate set in the pipeline distribution model data.

[0107] As an implementation manner, in step S400, parameter synchronization update is performed on multiple professional design model data according to the collaborative constraint parameters to generate a unified power engineering collaborative design model, which may specifically include:

[0108] Step S410: Reverse map the support member displacement compensation parameter in the collaborative constraint parameters to the set of component connection point coordinates in the structural support model data to generate an updated support member distribution density map and load-bearing parameters.

[0109] Reversing the mapping of the support member displacement compensation parameter in the collaborative constraint parameters to the set of component connection point coordinates in the structural support model data means applying the displacement compensation parameter to the coordinates of the component connection points to update the positions of the support members. By updating the coordinates of the component connection points, an updated support member distribution density map can be generated to reflect the new distribution of the support members. At the same time, since the position change of the support members can affect their load-bearing capacity, it is necessary to recalculate and update the load-bearing parameters. In specific implementation, a coordinate transformation algorithm can be used to apply the support member displacement compensation parameter to the coordinates of the component connection points to generate an updated set of component connection point coordinates; then, the distribution density map and load-bearing parameters of the support members are recalculated according to the updated set of component connection point coordinates. For example, a translation transformation is used to apply the support member displacement compensation parameter to the coordinates of the component connection points to update the coordinates of the component connection points; according to the updated set of component connection point coordinates, the finite element analysis method is used to recalculate the load-bearing parameters of the support members.

[0110] Step S420: Reverse map the equipment positioning offset parameter in the collaborative constraint parameters to the equipment installation base point coordinates in the electrical equipment model data to generate an updated equipment positioning reference point and equipment attribute parameters.

[0111] Reversing the mapping of the equipment positioning offset parameter in the collaborative constraint parameters to the equipment installation base point coordinates in the electrical equipment model data means applying the offset parameter to the coordinates of the equipment installation base point to update the position of the electrical equipment. By updating the coordinates of the equipment installation base point, an updated equipment positioning reference point can be generated to reflect the new installation position of the electrical equipment. At the same time, since the position change of the electrical equipment can affect its attribute parameters, it is necessary to recalculate and update the equipment attribute parameters. In specific implementation, a coordinate transformation algorithm can be used to apply the equipment positioning offset parameter to the coordinates of the equipment installation base point to generate an updated set of equipment installation base point coordinates; then, the equipment positioning reference point and equipment attribute parameters are recalculated according to the updated set of equipment installation base point coordinates. For example, a translation transformation is used to apply the equipment positioning offset parameter to the coordinates of the equipment installation base point to update the coordinates of the equipment installation base point; according to the updated set of equipment installation base point coordinates, the topological weight coefficient and rated parameters and other attribute parameters of the equipment are recalculated.

[0112] Step S430: Inversely map the pipeline path adjustment parameter in the collaborative constraint parameter to the pipeline node coordinate set in the pipeline distribution model data to generate an updated pipeline routing path segment direction vector and pipe diameter flow parameters.

[0113] Inversely mapping the pipeline path adjustment parameter in the collaborative constraint parameter to the pipeline node coordinate set in the pipeline distribution model data means applying the adjustment parameter to the coordinates of the pipeline nodes to update the pipeline routing path. By updating the coordinates of the pipeline nodes, an updated pipeline routing path segment direction vector can be generated to reflect the new routing path of the pipeline. At the same time, since the change in the pipeline routing path can affect its pipe diameter flow parameters, it is necessary to recalculate and update the pipe diameter flow parameters. In specific implementation, a coordinate transformation algorithm can be used to apply the pipeline path adjustment parameter to the coordinates of the pipeline nodes to generate an updated pipeline node coordinate set; then, based on the updated pipeline node coordinate set, recalculate the pipeline routing path segment direction vector and pipe diameter flow parameters. For example, use a translation transformation to apply the pipeline path adjustment parameter to the coordinates of the pipeline nodes to update the coordinates of the pipeline nodes; based on the updated pipeline node coordinate set, use a fluid mechanics analysis method to recalculate the pipe diameter flow parameters of the pipeline.

[0114] Step S440: Based on the spatial overlap relationship between the updated support member distribution density map and the equipment positioning reference point, verify whether the spatial avoidance rule in the collaborative constraint parameter meets the preset safety distance threshold.

[0115] By analyzing the spatial overlap relationship between the updated support member distribution density map and the equipment positioning reference point, it can be verified whether the spatial avoidance rule in the collaborative constraint parameter is effective. The preset safety distance threshold is a predefined safety distance requirement. If the spatial overlap relationship meets this threshold, it means that the spatial avoidance rule is satisfied; otherwise, the collaborative constraint parameter needs to be further adjusted. In specific implementation, a spatial analysis algorithm can be used to process the updated support member distribution density map and the equipment positioning reference point to calculate the shortest distance between them; then, compare this distance with the preset safety distance threshold. For example, use a distance calculation algorithm to calculate the shortest distance between the spatial coverage area corresponding to the updated support member distribution density map and the three-dimensional coordinate range of the equipment positioning reference point, and compare this distance with the preset safety distance threshold. If the distance is greater than or equal to the threshold, it means that the spatial avoidance rule meets the requirements; otherwise, the support member displacement compensation parameter or the equipment positioning offset parameter needs to be readjusted.

[0116] Step S450: Based on the spatial intersection relationship between the updated pipeline routing path segment direction vector and the equipment positioning reference point, verify whether the flow direction coordination path in the collaborative constraint parameter meets the preset pipeline avoidance threshold.

[0117] By analyzing the spatial intersection relationship between the direction vector of the updated pipeline routing path segment and the device positioning reference point, it is possible to verify whether the flow coordination path in the collaborative constraint parameters is effective. The preset pipeline avoidance threshold is a predefined avoidance requirement. If the spatial intersection relationship meets this threshold, it indicates that the flow coordination path is satisfied; otherwise, the collaborative constraint parameters need to be further adjusted. Specifically, a spatial analysis algorithm can be used to process the direction vector of the updated pipeline routing path segment and the device positioning reference point to calculate their intersection situation; then, compare the intersection situation with the preset pipeline avoidance threshold. For example, use the line segment intersection algorithm to calculate the number of intersection points and the intersection area between the three-dimensional extension range of the direction vector of the updated pipeline routing path segment and the coordinate distribution area of the device positioning reference point, and compare these results with the preset pipeline avoidance threshold. If the number of intersection points and the intersection area are less than or equal to the threshold, it indicates that the flow coordination path meets the requirements; otherwise, the pipeline path adjustment parameters or the device positioning offset parameters need to be readjusted.

[0118] Step S460: When all verification results meet the power engineering constraint rule set, spatially align the updated structural support model data, electrical equipment model data, and pipeline distribution model data according to a unified coordinate reference to generate a power engineering collaborative design model with consistent versions; among them, the power engineering collaborative design model contains parameter change records corresponding to the collaborative constraint parameters, and the parameter change records are used for version tracing during subsequent construction data docking.

[0119] When all verification results meet the power engineering constraint rule set, it indicates that the adjustment and update of the collaborative constraint parameters are effective, and the updated structural support model data, electrical equipment model data, and pipeline distribution model data can be spatially aligned. Spatially aligning according to a unified coordinate reference is to unify the coordinate systems of these model data to the same reference to ensure their spatial consistency. The generated power engineering collaborative design model with consistent versions contains the updated design model data of each specialty and records the parameter change records corresponding to the collaborative constraint parameters. These parameter change records are used for version tracing during subsequent construction data docking, facilitating construction personnel to understand the change situation and reasons of the model data. Specifically, coordinate transformation and data merging techniques can be used to process the updated model data. For example, use a coordinate transformation matrix to unify the coordinate systems of the updated structural support model data, electrical equipment model data, and pipeline distribution model data to the same reference; merge these model data into a unified database while recording the parameter change records.

[0120] Step S500: Output the 3D spatial coordinate data and equipment interface parameter data corresponding to the collaborative design model of the power project, and trigger the data docking protocol with the external construction system.

[0121] Outputting the 3D spatial coordinate data and equipment interface parameter data corresponding to the collaborative design model of the power project provides the data of the design model to the external construction system for construction personnel to perform construction operations. The 3D spatial coordinate data describes the position information of electrical equipment, structural supports, and pipelines in the 3D space, and the equipment interface parameter data describes the interface specifications and connection requirements of electrical equipment. Triggering the data docking protocol with the external construction system establishes a data transmission channel with the external construction system to ensure the accurate transmission and docking of data. In specific implementation, data output and communication technologies can be used to process the collaborative design model of the power project. For example, the file export function can be used to output the 3D spatial coordinate data and equipment interface parameter data in a set file format; the network communication protocol can be used to establish a data docking channel with the external construction system and transmit the output data to the external construction system.

[0122] As an implementation method, in step S500, outputting the 3D spatial coordinate data and equipment interface parameter data corresponding to the collaborative design model of the power project, and triggering the data docking protocol with the external construction system can specifically include:

[0123] Step S510: Extract the 3D coordinate data corresponding to the updated equipment positioning reference points, the node coordinate set corresponding to the support member distribution density map, and the spatial trajectory data corresponding to the pipeline routing path segment direction vectors from the collaborative design model of the power project.

[0124] Extracting these key data from the collaborative design model of the power project provides a basis for subsequent data output and docking. The 3D coordinate data corresponding to the updated equipment positioning reference points describes the new installation positions of electrical equipment, the node coordinate set corresponding to the support member distribution density map describes the new distribution of structural support members, and the spatial trajectory data corresponding to the pipeline routing path segment direction vectors describes the new routing paths of pipelines. In specific implementation, these data can be extracted from the collaborative design model of the power project through database query operations. For example, SQL statements can be used to query the 3D coordinate data corresponding to the equipment positioning reference points, the node coordinate set corresponding to the support member distribution density map, and the spatial trajectory data corresponding to the pipeline routing path segment direction vectors from the database table storing the collaborative design model of the power project.

[0125] Step S520: Convert the 3D coordinate data into the reference coordinate system format supported by the construction positioning system, where the conversion process includes planar projection correction of elevation data and coordinate offset compensation.

[0126] The construction positioning system usually has its own reference coordinate system format. To ensure that the extracted three-dimensional coordinate data can be correctly recognized and used by the construction positioning system, it is necessary to convert the extracted three-dimensional coordinate data into this format. The conversion process includes plane projection correction of elevation data and compensation for coordinate offset. Plane projection correction is to project the elevation data in three-dimensional space onto a two-dimensional plane to meet the requirements of the construction positioning system; coordinate offset compensation is to adjust the coordinate data to eliminate the deviation between different coordinate systems. When specifically implemented, coordinate transformation algorithms can be used to process the three-dimensional coordinate data. For example, use projection transformation to project the elevation data onto a two-dimensional plane; calculate the coordinate offset according to the requirements of the construction positioning system and compensate the coordinate data.

[0127] Step S530: Divide the node coordinate set and the spatial trajectory data into segmented construction units according to the requirements of the construction process, and add an avoidance rule identifier corresponding to the collaborative constraint parameters to each construction unit.

[0128] Dividing the node coordinate set and the spatial trajectory data into segmented construction units according to the requirements of the construction process is to facilitate the construction operations of construction personnel. Each construction unit corresponds to a specific construction task, and through segmentation, the entire construction process can be divided into multiple subtasks. Adding an avoidance rule identifier corresponding to the collaborative constraint parameters to each construction unit is to ensure that the avoidance rules in the collaborative constraint parameters are followed during the construction process. When specifically implemented, the node coordinate set and the spatial trajectory data can be segmented according to the arrangement and requirements of the construction process; then, an avoidance rule identifier corresponding to the collaborative constraint parameters is assigned to each construction unit. For example, according to the construction progress and sequence, divide the node coordinate set corresponding to the distribution density map of support members and the spatial trajectory data corresponding to the direction vector of the pipeline routing path segment into multiple segmented construction units; add a unique avoidance rule identifier to each construction unit, and this identifier corresponds to the spatial avoidance rule or the flow coordination path in the collaborative constraint parameters.

[0129] Step S540: Parse the interface position change data associated with the equipment positioning offset parameter in the collaborative constraint parameters from the equipment interface parameter data, and repackage the terminal numbers and connection sequences according to the construction interface standard.

[0130] Parsing the interface position change data associated with the device positioning offset parameter in the device interface parameter data is to understand the change situation of the device interface position. Since the device positioning offset parameter may cause the position of the device to change, which may affect the position of the device interface. Re-encapsulating the terminal numbers and connection sequences according to the construction interface standard is to ensure that the connection of the device interface meets the construction requirements. Specifically, during implementation, the device interface parameter data can be processed through data parsing and processing algorithms to extract the interface position change data associated with the device positioning offset parameter. For example, a string matching algorithm can be used to search for fields related to the device positioning offset parameter in the device interface parameter data, and the specific information of the interface position change can be extracted. Then, according to the construction interface standard, the terminal numbers and connection sequences are rearranged to ensure the accuracy and standardization of the device interface connection during the construction process. A construction interface standard template can be established, and the parsed interface position change data is matched with the template, and the terminal numbers and connection sequences are re-encapsulated according to the requirements of the template.

[0131] Step S550: Send the segmented construction unit data, the avoidance rule identifier, and the re-encapsulated interface position change data to the external construction system through an encrypted transmission channel, and receive the data integrity verification result returned by the construction system.

[0132] To ensure the security and reliability of data transmission, an encrypted transmission channel is used to send the segmented construction unit data, the avoidance rule identifier, and the re-encapsulated interface position change data to the external construction system. The encrypted transmission channel can use a symmetric encryption algorithm (such as the AES algorithm) or an asymmetric encryption algorithm (such as the RSA algorithm) to encrypt the data, preventing the data from being stolen or tampered with during transmission. After sending the data, it is necessary to receive the data integrity verification result returned by the external construction system. Data integrity verification can use a hash algorithm (such as MD5, SHA-256, etc.) to perform a hash calculation on the transmitted data. The construction system also performs the same hash calculation after receiving the data, and then compares the two hash values. If they are the same, it means that the data has not been lost or damaged during transmission. For example, before sending the data, use the SHA-256 algorithm to perform a hash calculation on the segmented construction unit data, the avoidance rule identifier, and the re-encapsulated interface position change data to obtain a hash value; send the data and the hash value to the external construction system. After receiving the data, the construction system also uses the SHA-256 algorithm to perform a hash calculation on the data and compares the calculated hash value with the received hash value, and returns the comparison result as the data integrity verification result.

[0133] Step S560: Based on the error flags in the data integrity verification result, locate the parameter change records in the collaborative design model of the power project that do not meet the construction specifications, and trigger the secondary correction process based on the collaborative constraint parameters.

[0134] If the data integrity verification result contains error flags, it indicates that there may be problems with the transmitted data, and it is necessary to further locate the parameter change records in the collaborative design model of the power project that do not meet the construction specifications. By analyzing the specific content of the error flags and combining with the parameter change records in the collaborative design model of the power project, the parameters that may cause problems can be found. For example, if the error flag indicates that the avoidance rule of a certain construction unit does not meet the requirements, the parameter change records corresponding to this construction unit can be checked to see if there are incorrect parameter settings related to the avoidance rule. Once the parameter change records that do not meet the construction specifications are located, the secondary correction process based on the collaborative constraint parameters is triggered. In the secondary correction process, the collaborative constraint parameters are adjusted according to the specific situation of the error. If the problem is caused by unreasonable setting of the displacement compensation parameter of the support member, the displacement compensation parameter of the support member can be recalculated to ensure that it meets the construction specifications; if the device positioning offset parameter affects the correctness of the interface position, the device positioning offset parameter can be readjusted. After adjusting the collaborative constraint parameters, the parameter synchronization and update of the data of multiple professional design models are carried out again according to the previous steps to generate a new collaborative design model of the power project, and then the data output and transmission are carried out again until the data integrity verification result passes.

[0135] Step S570: When the data integrity verification result passes, generate a status identification signal for successful docking with the external construction system, and lock the data of the current version of the collaborative design model of the power project.

[0136] When the data integrity verification result passes, it indicates that the data of the segmented construction units, the avoidance rule identifiers, and the re-encapsulated interface position change data have been successfully and completely transmitted to the external construction system. At this time, a status identification signal for successful docking with the external construction system is generated. This signal can be a message in a preset format, containing relevant information about the successful docking, such as the docking time, the content of the docked data, etc. At the same time, to ensure the stability and consistency of the data, the data of the current version of the collaborative design model of the power project is locked. The locking operation can be achieved by setting the access rights of the data. For example, the read and write rights of the data are set to read-only to prohibit further modification of the data. This can prevent errors and conflicts caused by accidental modification of the data during the construction process and ensure that the construction process is carried out according to the design requirements. In addition, the locked data of the collaborative design model of the power project can be backed up so that it can be restored to the current version when needed later.

[0137] As an implementation manner, the generation process of the pre-trained feature recognition model may specifically include the following steps S10 to S70:

[0138] Step S10: Obtain the electrical equipment installation position data in the historical power engineering design dataset, parse the device base point coordinates and adjacent device spacing parameters in the electrical equipment installation position data, and generate a device space distribution topology graph.

[0139] The historical power engineering design dataset contains a large amount of past power engineering design information. The electrical equipment installation position data therein records the specific installation positions of various electrical equipment in three-dimensional space. The device base point coordinates refer to the reference point positions of electrical equipment in space, usually the coordinates of the center point of the device or the key installation point; the adjacent device spacing parameters describe the distance relationship between adjacent electrical equipment. Parsing these data can be achieved through data extraction and processing algorithms. For example, regular expressions are used to extract the device base point coordinates and adjacent device spacing parameters from the electrical equipment installation position data. Generating a device space distribution topology graph is to represent the installation positions and spacing relationships of these devices in a graphical manner. The method of graph theory can be adopted, regarding each electrical equipment as a node and the spacing between adjacent devices as the weight of the edge to construct a graph structure. Such a device space distribution topology graph can intuitively display the distribution and mutual relationships of electrical equipment in space, providing important basic data for subsequent model training.

[0140] Step S20: Obtain the structure support node data in the historical power engineering design dataset, extract the support member connection point coordinates and load transfer direction parameters in the node data, and generate a support load distribution topology graph.

[0141] The structure support node data records the relevant information of the structure support members in the power engineering. The support member connection point coordinates represent the connection positions between support members, and the load transfer direction parameters describe the load transfer direction between support members. Extracting this information from the structure support node data can use data parsing techniques. For example, an XML parser or a JSON parser is used to parse the data to extract the support member connection point coordinates and load transfer direction parameters. Generating a support load distribution topology graph is to present the connection relationship of support members and the load transfer situation in a graphical manner. Similarly, the method of graph theory is adopted, regarding the support member connection points as nodes and the load transfer direction as the direction attribute of the edge to construct a directed graph. Such a support load distribution topology graph can clearly display the load transfer path and distribution in the structure support system, helping to analyze the relationship between the structure support and other specialties subsequently.

[0142] Step S30: Obtain the pipeline path data in the historical power engineering design dataset, parse the pipeline turning point coordinates and fluid direction identification parameters in the path data, and generate a pipeline flow topology diagram.

[0143] The pipeline path data records the routing information of various pipelines in the power engineering. The pipeline turning point coordinates refer to the coordinates of the points where the direction of the pipeline changes in space, and the fluid direction identification parameter indicates the flow direction of the fluid in the pipeline. Data mining and analysis algorithms can be used to parse the pipeline path data. For example, the curve fitting algorithm is used to process the pipeline path data to find the pipeline turning point coordinates; by identifying the identification fields in the data, the fluid direction identification parameters are extracted. Generating a pipeline flow topology diagram is to represent the routing of the pipeline and the fluid flow direction in a graphical way. Using the pipeline turning points as nodes and the fluid direction as the edge direction attribute, a directed graph is constructed. Such a pipeline flow topology diagram can intuitively display the layout of the pipeline and the fluid flow path, providing an important reference for subsequent collaborative design.

[0144] Step S40: Align the device space distribution topology diagram, the support load distribution topology diagram, and the pipeline flow topology diagram in the space coordinate system to generate a global topology connection diagram including devices - supports - pipelines.

[0145] The space coordinate system alignment is to ensure that the device space distribution topology diagram, the support load distribution topology diagram, and the pipeline flow topology diagram are uniformly represented in the same space coordinate system. Since these topology diagrams may be generated based on different measurement or design standards, their coordinate systems may be different. Therefore, coordinate system conversion and alignment operations are required. The coordinates of each topology diagram can be converted by finding a common reference point or reference coordinate system. For example, a landmark location in the power engineering is selected as the reference point, and the coordinates of the device space distribution topology diagram, the support load distribution topology diagram, and the pipeline flow topology diagram are all converted to the coordinate system with this reference point as the origin. Generating a global topology connection diagram including devices - supports - pipelines is to integrate these three topology diagrams and construct a unified graph structure. In this global topology connection diagram, not only the topology information of electrical equipment, structural supports, and pipelines is included, but also the mutual connection and association relationships between them are reflected.

[0146] As an implementation manner, in step S40, aligning the device space distribution topology diagram, the support load distribution topology diagram, and the pipeline flow topology diagram in the space coordinate system to generate a global topology connection diagram including devices - supports - pipelines may specifically include:

[0147] Step S41: Extract the device base point coordinate set from the device space distribution topology diagram, and generate virtual connection edges between devices based on the adjacent device spacing parameters.

[0148] The set of equipment base point coordinates is the coordinate set of all electrical equipment base points in the topological map of the equipment spatial distribution. By traversing the node information in the topological map of the equipment spatial distribution, the set of equipment base point coordinates can be extracted. Generating virtual connection edges between equipment based on the adjacent equipment spacing parameter is to establish an association relationship between equipment. The adjacent equipment spacing parameter describes the distance between adjacent equipment. According to this distance information, virtual edges can be added between equipment base points, and the weight of the edge can be set as the adjacent equipment spacing. Such virtual connection edges can reflect the spatial distance and association degree between equipment, providing more information for subsequent analysis and processing. For example, for equipment A and equipment B, the adjacent equipment spacing is d, then a virtual connection edge with a weight of d is added between the base points of equipment A and equipment B.

[0149] Step S42: Extract the coordinate set of the support member connection points from the topological map of the support load distribution, and generate the support member load flow edges according to the load transfer direction parameter.

[0150] The coordinate set of the support member connection points is the coordinate set of all support member connection points in the topological map of the support load distribution. By performing data extraction operations on the topological map of the support load distribution, the coordinate set of the support member connection points can be obtained. Generating the support member load flow edges according to the load transfer direction parameter is to clarify the load transfer path between support members. The load transfer direction parameter specifies the direction in which the load is transferred from one support member to another. According to this direction information, directed edges are added between the support member connection points, and the direction of the edge represents the load transfer direction. Such support member load flow edges can clearly show the load transfer process in the structural support system, helping to analyze the mechanical properties of the structure. For example, if support member A transfers the load to support member B, then a directed edge pointing from A to B is added between the connection points of support member A and support member B.

[0151] Step S43: Extract the coordinate set of the pipeline turning points from the topological map of the pipeline flow direction, and generate the pipeline fluid direction edges according to the fluid direction identification parameter.

[0152] The pipeline turning point coordinate set is the coordinate set of all pipeline turning points in the pipeline flow topology graph. By parsing the data of the pipeline flow topology graph, the pipeline turning point coordinate set can be extracted. Generating the pipeline fluid direction edges according to the fluid direction identification parameters is to represent the flow path of the fluid in the pipeline. The fluid direction identification parameters specify the flow direction of the fluid in the pipeline. According to this direction information, directed edges are added between the pipeline turning points, and the direction of the edge represents the fluid flow direction. Such pipeline fluid direction edges can intuitively display the fluid flow situation in the pipeline, which is of great significance for analyzing the transmission performance of the pipeline and collaborative design. For example, if the fluid flows from turning point A to turning point B in the pipeline, a directed edge pointing from A to B is added between turning point A and turning point B.

[0153] Step S44: Superimpose the equipment base point coordinate set, the support member connection point coordinate set, and the pipeline turning point coordinate set in a unified coordinate system to generate a global node coordinate pool.

[0154] Since the equipment base point coordinate set, the support member connection point coordinate set, and the pipeline turning point coordinate set may come from different topology graphs, their coordinate systems may not be consistent. Therefore, it is necessary to superimpose them in a unified coordinate system. Coordinate system conversion can be carried out first to convert each coordinate set to the same coordinate system, and then these coordinate sets are merged together to generate a global node coordinate pool. The global node coordinate pool contains the coordinate information of all key nodes of electrical equipment, structural supports, and pipelines, providing a basis for constructing the global topology connection graph in the follow-up. For example, the equipment base point coordinate set, the support member connection point coordinate set, and the pipeline turning point coordinate set are all converted to a coordinate system with a certain landmark position in the power project as the origin, and then the coordinates in these coordinate sets are merged into a set to form a global node coordinate pool.

[0155] Step S45: According to the direction attributes of the virtual connection edges between equipment, the load flow direction edges of support members, and the pipeline fluid direction edges, establish composite connection edges between cross-professional nodes in the global node coordinate pool.

[0156] The virtual connection edges between equipment rooms, the load flow edges of support members, and the fluid direction edges of pipelines respectively describe the correlation relationships within electrical equipment, structural supports, and pipelines. Based on the direction attributes of these edges, establishing composite connection edges between cross-professional nodes in the global node coordinate pool is to reflect the mutual influences and correlations between different professions. For example, if the installation location of an electrical equipment is close to a certain structural support member, and the load transfer path of this structural support member can affect the stability of the electrical equipment, then a composite connection edge can be established between the base point of the electrical equipment and the connection point of the structural support member. The direction and attributes of the composite connection edge can be set according to specific correlation situations. For example, the weight of the edge can be set to represent the strength of the correlation, and the direction of the edge can represent the direction of influence. Such composite connection edges can comprehensively reflect the complex relationships between different professions in a power project.

[0157] Step S46: Based on the direction attributes and spatial density of the composite connection edges, calculate the weight coefficients of each global node in the cross-professional topology, and generate a global topology connection graph with weight annotations. Among them, the composite connection edges in the global topology connection graph are used to train the node embedding parameters of the graph neural network model, and the weight coefficients are used for the priority determination of conflict coordination processing.

[0158] The direction attributes and spatial density of the composite connection edges reflect the correlation strength and spatial distribution between nodes. Calculating the weight coefficients of each global node in the cross-professional topology based on this information can adopt centrality analysis methods in graph theory, such as degree centrality, betweenness centrality, etc. For example, degree centrality measures the number of connections between a node and other nodes. The more connections, the higher the importance of the node in the topological structure; betweenness centrality measures the frequency of a node's appearance on the shortest paths between other nodes. The higher the frequency, the greater the role of the node in information transmission and correlation. The weight coefficients calculated according to these centrality indicators can reflect the importance of each global node in the cross-professional topology. Generating a global topology connection graph with weight annotations is to label the calculated weight coefficients on the nodes of the global topology connection graph while retaining the information of the composite connection edges. Such a global topology connection graph with weight annotations provides an important data basis for subsequent graph neural network model training and conflict coordination processing. The graph neural network model can generate node embedding parameters by learning the information of the composite connection edges, and the weight coefficients can be used to determine the priorities of each node in conflict coordination processing, giving priority to processing nodes with high weight coefficients to improve the efficiency and effect of conflict coordination.

[0159] Step S50: Based on the node connection density in the global topology connection graph, identify the equipment cluster areas in the electrical equipment installation location data where the occurrence frequency is greater than the preset frequency, and extract the equipment base point coordinates of the equipment cluster areas as training sample labels.

[0160] The node connection density reflects the connection tightness between nodes in the global topological connection graph. By analyzing the node connection density in the global topological connection graph, areas with a high frequency of occurrence in the electrical equipment installation location data can be found, that is, the equipment cluster areas. The preset frequency is a preset threshold used to determine whether a certain area is an equipment cluster area. By traversing the nodes in the global topological connection graph and counting the number of connections of nodes in each area, when the number of connections exceeds the preset frequency, the area is defined as an equipment cluster area. Extracting the equipment base point coordinates of the equipment cluster area as the training sample labels is to provide clear targets for subsequent model training. These equipment base point coordinates can accurately identify the location of the equipment cluster area, and the graph neural network model can improve its recognition ability of the equipment cluster area by learning these labels. For example, the equipment base point coordinates of the equipment cluster area can be stored in a dataset as the labels of the training samples for training the graph neural network model.

[0161] Step S60: Based on the edge connection directions in the global topological connection graph, identify the consistency relationship between the load transfer path in the support load distribution topological graph and the fluid direction in the pipeline flow direction topological graph, and generate cross-professional feature association rules.

[0162] The edge connection directions in the global topological connection graph contain the information of the load transfer path in the support load distribution topological graph and the fluid direction in the pipeline flow direction topological graph. By analyzing these edge connection directions, the consistency relationship between the load transfer path and the fluid direction can be identified. The consistency relationship can be manifested as the load transfer direction being the same as, opposite to, or having an included angle with the fluid flow direction, etc. According to these consistency relationships, cross-professional feature association rules can be generated. For example, if it is found that the load transfer direction of the support components in a certain area is the same as the fluid flow direction in the pipeline, and this situation occurs frequently, then an association rule can be generated: in this area, the load transfer of the support components is associated with the fluid flow in the pipeline in the same direction. Such cross-professional feature association rules can help better coordinate the relationships between different professions in collaborative design and avoid conflicts and contradictions.

[0163] Step S70: Input the equipment base point coordinates and the cross-professional feature association rules into the graph neural network model for iterative training until the error rate between the equipment location prediction coordinates output by the graph neural network model and the historical annotation data is lower than the preset threshold. Among them, after the graph neural network model is trained, it is stored as a pre-trained feature recognition model, and the cross-professional feature association rules are used for conflict detection in subsequent collaborative design.

[0164] A graph neural network model is a neural network model specifically designed to process graph-structured data, which can effectively learn the feature information of nodes and edges in the graph. The device base point coordinates are used as the input node features, and the cross-professional feature association rules are used as the edge features, and are input into the graph neural network model for iterative training. In each iteration, the graph neural network model performs forward propagation according to the input information and outputs the predicted coordinates of device positioning. These predicted coordinates are compared with the historical annotation data to calculate the error rate. The error rate can be measured by metrics such as Euclidean distance error. If the error rate is higher than the preset threshold, the parameters of the graph neural network model need to be adjusted, and the node embedding weights and edge attention parameters are updated through the backpropagation algorithm to reduce the error rate. This iterative process is continuously repeated until the error rate between the predicted coordinates of device positioning output by the graph neural network model and the historical annotation data is lower than the preset threshold. At this time, the training of the graph neural network model is completed, and it is stored as a pre-trained feature recognition model. In subsequent collaborative design, the cross-professional feature association rules can be used for conflict detection. When the design data of different professions violate these association rules, it indicates that there may be conflicts and further processing and coordination are required.

[0165] As an implementation manner, in step S70, the device base point coordinates and the cross-professional feature association rules are input into the graph neural network model for iterative training until the error rate between the predicted coordinates of device positioning output by the graph neural network model and the historical annotation data is lower than the preset threshold, which may specifically include:

[0166] Step S71: Divide the global topological connection graph into a training subgraph and a validation subgraph. The training subgraph contains a preset percentage of global nodes and associated composite connection edges.

[0167] To evaluate the performance of the graph neural network model and avoid overfitting problems, the global topological connection graph is divided into a training subgraph and a validation subgraph. The preset percentage is a pre-set ratio used to determine the number of global nodes and composite connection edges included in the training subgraph. For example, 80% of the nodes and associated composite connection edges in the global topological connection graph can be divided into the training subgraph, and the remaining 20% is used as the validation subgraph. Such a division method can enable the graph neural network model to learn most of the data features during the training process, and at the same time use the validation subgraph to evaluate the generalization ability of the model. During the division process, a random sampling method can be adopted to randomly select a preset percentage of global nodes and associated composite connection edges to form the training subgraph, and the remaining nodes and edges form the validation subgraph.

[0168] Step S72: Use the device base point coordinates in the training subgraph as the input node features, and use the cross-professional feature association rules as the edge features, and input them into the graph neural network model for forward propagation.

[0169] The input of the graph neural network model includes node features and edge features. Taking the device base point coordinates in the training subgraph as the input node features is because the device base point coordinates can reflect the location information of electrical equipment and are an important basis for the model to learn. Taking the cross-professional feature association rules as the edge features is because these rules describe the association relationships between different professions and can help the model better understand the information in the graph structure. After being input into the graph neural network model, the model performs forward propagation, processes and transforms the input information through a series of neural network layers, and finally outputs the device location prediction coordinates. During the forward propagation process, the graph neural network model performs operations such as weighted summation and non-linear transformation on the input information according to its internal weights and parameters, and gradually extracts and learns the feature information in the graph.

[0170] Step S73: Calculate the Euclidean distance error between the device location prediction coordinates output by the graph neural network model and the historical annotated device base point coordinates in the training subgraph.

[0171] The Euclidean distance error is an index to measure the distance between two coordinate points. Calculate the Euclidean distance error between the device location prediction coordinates output by the graph neural network model and the historical annotated device base point coordinates in the training subgraph. For each device node, calculate the Euclidean distance between its predicted coordinates and the historical annotated coordinates in the three-dimensional space respectively, and then average the Euclidean distances of all device nodes to obtain the overall Euclidean distance error. The Euclidean distance error can intuitively reflect the deviation degree between the device location prediction coordinates output by the graph neural network model and the actual historical annotated coordinates, providing a basis for subsequent model parameter adjustment. For example, for device node i, its predicted coordinates are , and the historical annotated coordinates are , then the Euclidean distance error , and the overall Euclidean distance error is the average of all .

[0172] Step S74: Based on the Euclidean distance error, reversely adjust the node embedding weights and edge attention parameters of the graph neural network model.

[0173] The node embedding weights and edge attention parameters of the graph neural network model are adjusted in reverse to reduce the Euclidean distance error and improve the prediction accuracy of the model. According to the Euclidean distance error, the parameters of the graph neural network model are updated using the backpropagation algorithm. The backpropagation algorithm is an optimization algorithm based on gradient descent. It calculates the gradient of the error with respect to the model parameters and then adjusts the parameters in the opposite direction of the gradient to gradually reduce the error. During this process, the node embedding weights and edge attention parameters are adjusted accordingly based on the magnitude and direction of the error. For example, if the Euclidean distance error between the predicted coordinates of a certain node and the historical annotation coordinates is large, it indicates that the node embedding weight of this node may need to be adjusted significantly; similarly, if the association rule of a certain edge has a large impact on the error, then the edge attention parameter of this edge also needs to be adjusted accordingly. By continuously adjusting the parameters in reverse, the graph neural network model can gradually learn more accurate feature representations and improve the accuracy of device location prediction.

[0174] Step S75: Repeat the forward propagation process on the validation subgraph, calculate the validation error rate, and determine whether the decrease amplitude of the validation error rate in three consecutive iterations is lower than the set threshold.

[0175] While the model is being trained on the training subgraph, it is necessary to perform validation on the validation subgraph to evaluate the generalization ability of the model. Repeat the forward propagation process on the validation subgraph, use the device base point coordinates in the validation subgraph as input node features, and the cross-professional feature association rules as edge features, and input them into the graph neural network model to obtain the device location prediction coordinates on the validation subgraph. Calculate the error rate between these prediction coordinates and the historical annotation device base point coordinates in the validation subgraph as the validation error rate. The calculation method of the validation error rate is the same as that of the Euclidean distance error on the training subgraph. Then, determine whether the decrease amplitude of the validation error rate in three consecutive iterations is lower than the set threshold. The set threshold is a pre-set small value used to determine whether the decrease of the validation error rate is tending to be flat. If the decrease amplitude of the validation error rate in three consecutive iterations is lower than the set threshold, it indicates that the performance of the model has tended to be stable and may have achieved a good training effect, and the training can be considered terminated.

[0176] Step S76: When the judgment condition is met, terminate the training and store the final parameters of the graph neural network model. Among them, the final parameters include the node embedding matrix and the cross-professional edge attention coefficient, which are used for real-time feature extraction of the feature recognition model in collaborative design.

[0177] When the decrease in the validation error rate for three consecutive iterations is lower than the set threshold, the judgment condition for terminating training is met. At this time, the training process of the graph neural network model is terminated, and the final parameters of the model are stored. The final parameters include the node embedding matrix and the cross-professional edge attention coefficients. The node embedding matrix is a matrix that maps the nodes in the graph to a low-dimensional vector space, which can represent the feature information of the nodes; the cross-professional edge attention coefficients reflect the importance and association strength of the edges in the graph neural network model. These final parameters play an important role in the real-time feature extraction process of the feature recognition model in collaborative design. During real-time feature extraction, the feature recognition model can process and analyze the input design data according to these parameters, extract the feature information related to electrical equipment, structural supports, and pipelines, and provide support for subsequent collaborative design and conflict resolution.

[0178] As an implementation manner, in step S70, after the graph neural network model is trained, it is stored as a pre-trained feature recognition model, and the cross-professional feature association rules are used for conflict detection in subsequent collaborative design, specifically including:

[0179] Step S77: Convert the node embedding matrix into a mapping relationship table between device types and spatial coordinates, and the mapping relationship table records the typical coordinate distribution ranges of each device type.

[0180] The node embedding matrix is an important parameter obtained by training the graph neural network model, which maps the nodes in the graph to a low-dimensional vector space. Converting the node embedding matrix into a mapping relationship table between device types and spatial coordinates is to connect the feature information of the nodes with the actual types and spatial coordinates of the devices. By performing clustering analysis on the node embedding matrix, nodes with similar features can be grouped into the same category, and then according to the device types and spatial coordinates corresponding to the nodes, the typical coordinate distribution ranges of each device type can be determined. For example, use the K-Means clustering algorithm to cluster the node embedding matrix, divide the nodes into different clusters, and each cluster represents a device type. Then, count the spatial coordinates of the nodes in each cluster, calculate their average values and standard deviations, and obtain the typical coordinate distribution range of the device type. Store this information in the mapping relationship table for easy query and use in subsequent collaborative design.

[0181] Step S78: Extract the composite connection edges with cross-professional edge attention coefficients higher than the importance threshold to generate key cross-professional connection rules.

[0182] The cross - professional edge attention coefficient reflects the importance and correlation strength of edges in the graph neural network model. By setting an importance threshold, composite connection edges with cross - professional edge attention coefficients higher than this threshold are extracted. These edges represent the key correlation relationships between different professions. Based on these composite connection edges, key cross - professional connection rules are generated. For example, if a composite connection edge connects an electrical equipment node and a structural support node, and the cross - professional edge attention coefficient of this edge is higher than the importance threshold, it indicates that there is an important correlation between this electrical equipment and this structural support. A key cross - professional connection rule can be generated: the installation of this electrical equipment needs to consider the bearing capacity of this structural support. Such key cross - professional connection rules can help focus on the key correlations between different professions in collaborative design, and timely discover and solve potential conflicts.

[0183] Step S79: Associate and store the key cross - professional connection rules with the equipment type mapping relationship table to form the interpretable metadata of the feature recognition model.

[0184] Associating and storing the key cross - professional connection rules with the equipment type mapping relationship table is to combine the key correlation relationships between different professions with the type and spatial coordinate information of the equipment to form the interpretable metadata of the feature recognition model. The interpretable metadata can provide explanations and bases for the output results of the feature recognition model, making it easier to understand and apply the analysis results of the model in collaborative design. For example, when the feature recognition model detects a conflict between a certain electrical equipment and a structural support, through the key cross - professional connection rules and the equipment type mapping relationship table in the interpretable metadata, the reasons for the conflict and possible solutions can be understood. Storing this information together facilitates querying and using in subsequent conflict detection and collaborative design processes.

[0185] Step S710: Configure a version identifier and a training data fingerprint in the feature recognition model. The version identifier is associated with the source information of the historical power engineering design data set;

[0186] Configuring a version identifier and training data fingerprint in the feature recognition model is for managing and tracing the model's version and training data. The version identifier is a unique identifier used to distinguish different versions of the feature recognition model. It associates the source information of the historical power engineering design dataset, such as the collection time, collection location, and scale of the data. Through the version identifier, it is convenient to know which version of the historical data the model is trained on and the source situation of the data. The training data fingerprint is a unique value obtained by calculating the hash of the training data, which can ensure the integrity and consistency of the training data. If the training data changes, the training data fingerprint will also change accordingly. When using the feature recognition model, the training data fingerprint can be compared to verify whether the training data used by the model is consistent with the current data environment. For example, when performing model updates or data migrations, the training data fingerprint can be checked to ensure that the model's training data has not been tampered with or damaged.

[0187] Step S711: Package the feature recognition model into a callable collaborative design service module. The service module receives real-time design data and outputs cross-professional feature information. Among them, the interpretability metadata is used for rule tracing during conflict detection, and the training data fingerprint ensures the compatibility between the model version and the construction specifications.

[0188] Packaging the feature recognition model into a callable collaborative design service module is to facilitate the use of the model in the collaborative design process. The service module can adopt a modular design concept, encapsulating the functions of the feature recognition model into an independent service unit and providing unified input and output interfaces. The service module receives real-time design data, which can be electrical equipment model data, structural support model data, pipeline distribution model data, etc. By calling the feature recognition model to process and analyze this real-time design data, cross-professional feature information is output, such as the installation location of equipment, the distribution of support members, and the routing of pipelines. During the conflict detection process, the interpretability metadata is used for rule tracing. When a conflict is detected, the key cross-professional connection rules and equipment type mapping relationship table in the interpretability metadata can be used to find the cause of the conflict and the corresponding solution rules. The training data fingerprint ensures the compatibility between the model version and the construction specifications. By comparing the training data fingerprint with the standard data fingerprint corresponding to the current construction specifications, it can be determined whether the model is suitable for the current construction environment. If they do not match, the model may need to be retrained or adjusted to ensure that the output results of the model meet the requirements of the construction specifications.

[0189] As an implementation method, in step S711, packaging the feature recognition model into a callable collaborative design service module, where the service module receives real-time design data and outputs cross-professional feature information, may specifically include:

[0190] Step S7111: Define the input interface format of the collaborative design service module, which includes the three-dimensional coordinate set of the electrical equipment model data, the component node set of the structural support model data, and the path node set of the pipeline distribution model data.

[0191] To ensure that the collaborative design service module can correctly receive and process real-time design data, it is necessary to define its input interface format. The input interface format includes the three-dimensional coordinate set of the electrical equipment model data, the component node set of the structural support model data, and the path node set of the pipeline distribution model data. The three-dimensional coordinate set of the electrical equipment model data records the position information of the electrical equipment in the three-dimensional space. The component node set of the structural support model data describes the node positions of the structural support components. The path node set of the pipeline distribution model data represents the path nodes of the pipeline routing. The input interface can be defined in data formats such as JSON or XML. Such an input interface format clearly specifies the organization method of the real-time design data, facilitating the service module to parse and process the data.

[0192] Step S7112: Define the output interface format of the collaborative design service module, which includes the device geometric distribution atlas with weight annotations, the support distribution map with type identifiers, and the pipeline network map with flow direction identifiers.

[0193] Defining the output interface format of the collaborative design service module is to standardize the organization method of the cross-professional characteristic information output by the service module. The output interface format includes the device geometric distribution atlas with weight annotations, the support distribution map with type identifiers, and the pipeline network map with flow direction identifiers. The device geometric distribution atlas with weight annotations describes the installation positions and importance weights of the electrical equipment. The support distribution map with type identifiers shows the distribution and type information of the structural support components. The pipeline network map with flow direction identifiers reflects the pipeline routing and fluid flow direction. Similarly, the output interface can be defined in data formats such as JSON or XML. Such an output interface format can accurately convey the cross-professional characteristic information output by the service module, facilitating subsequent collaborative design and conflict detection.

[0194] Step S7113: Deploy the service module to the distributed computing nodes and configure the dynamic resource allocation strategy to respond to high-concurrency design requests.

[0195] To improve the processing capacity and response speed of the collaborative design service module, it is deployed to distributed computing nodes. The distributed computing nodes can be a cluster composed of multiple servers, which parallelly process design requests through the distributed computing method. During the deployment process, it is necessary to consider the communication and data synchronization issues between nodes to ensure that the service module can operate normally in the distributed environment. At the same time, configure a dynamic resource allocation strategy to respond to high-concurrency design requests. The dynamic resource allocation strategy can dynamically adjust the resource allocation of computing nodes according to the quantity and complexity of design requests. For example, when the number of design requests is large, the number of computing nodes can be increased or more computing resources can be allocated; when the number of design requests is small, the number of computing nodes can be reduced or some computing resources can be released. A load balancing algorithm can be used to achieve dynamic resource allocation, such as the round-robin algorithm, weighted round-robin algorithm, etc. Such a dynamic resource allocation strategy can improve the resource utilization rate and response performance of the service module, ensuring that design requests can be processed in a timely manner even under high concurrency.

[0196] Step S7114: Integrate a real-time monitoring component in the service module, and the component collects the computing latency and memory occupancy metrics during the feature extraction process.

[0197] Integrating a real-time monitoring component in the service module is to monitor the running status and performance metrics of the service module in real time. The real-time monitoring component can collect the computing latency and memory occupancy metrics during the feature extraction process. Computing latency refers to the time taken by the service module to process a design request, which reflects the processing speed of the service module. The memory occupancy metric refers to the size of the memory space occupied by the service module during operation, which reflects the resource usage of the service module. By collecting these metrics in real time, problems existing in the operation of the service module, such as too high computing latency and too large memory occupancy, can be discovered in a timely manner. For example, performance monitoring tools (such as Prometheus, Grafana, etc.) can be used to implement the real-time monitoring component, regularly collect the computing latency and memory occupancy metrics, and display these metrics in a visual way to facilitate the monitoring and analysis by operation and maintenance personnel.

[0198] Step S7115: Establish a two-way authentication channel between the service module and the collaborative design platform to ensure the encrypted transmission of input design data and output feature information; among them, the dynamic resource allocation strategy is dynamically adjusted based on the computing latency metric, and the encrypted transmission channel complies with the power engineering data security standard.

[0199] The establishment of a two-way authentication channel between the service module and the collaborative design platform is to ensure the security and integrity of the input design data and output feature information. The two-way authentication channel can be implemented using digital certificates and encryption algorithms, such as using the SSL / TLS protocol for encrypted communication. During the communication process, the service module and the collaborative design platform verify each other's identities to ensure that only legitimate users and systems can perform data transmission. At the same time, the input design data and output feature information are encrypted to prevent the data from being stolen or tampered with during transmission. The encrypted transmission channel needs to comply with the power engineering data security standard to ensure the security and compliance of the data. The dynamic resource allocation strategy is adjusted dynamically based on the calculation delay index. When the calculation delay index is too high, it indicates that the processing capacity of the service module may be insufficient, and it is necessary to increase the computing resources or adjust the resource allocation strategy; when the calculation delay index is low, the computing resources can be appropriately reduced to improve the resource utilization rate. In this way, the performance and response speed of the service module can be improved while ensuring data security.

[0200] Please refer to Figure 2 , Figure 2The following is a schematic structural diagram of a BIM power engineering collaborative design device provided by an embodiment of the present invention. The BIM power engineering collaborative design device can be a general computer system, such as an electronic device with data processing capabilities like a server or a personal computer. The BIM power engineering collaborative design device at least includes a processor 101, a communication interface 102, and a memory 103. Among them, the processor 101, the communication interface 102, and the memory 103 can be connected through a bus or other means. Among them, the processor 101 (or the Central Processing Unit (CPU)) is the computing core and control core of the BIM power engineering collaborative design device, which can parse various instructions in the BIM power engineering collaborative design device and process various data of the BIM power engineering collaborative design device. The communication interface 102 can optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.), and can be used to send and receive data under the control of the processor 101; the communication interface 102 can also be used for the transmission and interaction of internal data of the BIM power engineering collaborative design device. The memory 103 (Memory) is a memory device in the BIM power engineering collaborative design device, used to store programs and data. It can be understood that the memory 103 here can include both the built-in memory of the BIM power engineering collaborative design device, and of course, can also include the extended memory supported by the BIM power engineering collaborative design device. The memory 103 provides a storage space, and this storage space stores the operating system of the BIM power engineering collaborative design device, which can include but is not limited to: Android system, iOS system, Windows Phone system, etc., and the present invention does not make any limitations in this regard. In one embodiment, the processor 101 executes the BIM power engineering collaborative design method provided above in the embodiments of the present invention by running the computer program in the memory 103.

Claims

1. A BIM collaborative design method for power engineering, characterized in that, The method includes: Obtaining a plurality of professional design model data, where the plurality of professional design model data includes electrical equipment model data, structural support model data, and pipeline distribution model data; Inputting the electrical equipment model data into a pre-trained feature recognition model to extract first geometric feature information associated with the installation position of the electrical equipment and first attribute feature information associated with the rated parameters of the equipment; Inputting the structural support model data into the feature recognition model to extract second geometric feature information associated with the distribution of support members and second attribute feature information associated with the load-bearing parameters; Inputting the pipeline distribution model data into the feature recognition model to extract third geometric feature information associated with the pipeline routing path and third attribute feature information associated with the pipe diameter flow parameters; Determining a first association feature between the electrical equipment and the structural support according to the spatial overlap relationship between the first geometric feature information and the second geometric feature information; Determining a second association feature between the pipeline distribution and the electrical equipment according to the spatial intersection relationship between the third geometric feature information and the first geometric feature information; Integrating the first association feature, the second association feature, and all the attribute feature information into a feature information set; Based on a preset set of power engineering constraint rules, performing conflict coordination processing on the cross-professional feature information in the feature information set to determine coordination constraint parameters associated with the plurality of professional design models; Performing parameter synchronization update on the plurality of professional design model data according to the coordination constraint parameters to generate a unified power engineering collaborative design model; Outputting three-dimensional space coordinate data and device interface parameter data corresponding to the power engineering collaborative design model.

2. The method according to claim 1, wherein The step of inputting the electrical equipment model data into a pre-trained feature recognition model to extract first geometric feature information associated with the installation position of the electrical equipment and first attribute feature information associated with the rated parameters of the equipment includes: Analyzing the three-dimensional space coordinate point set and device attribute tags in the electrical equipment model data to generate intermediate analysis data including the installation base point coordinates of the device and the hierarchical relationship topology diagram; Performing spatial clustering processing on the installation base point coordinates in the intermediate analysis data to identify a dense coordinate area associated with the same electrical equipment, and extracting the geometric center coordinate of the dense coordinate area as the device positioning reference point in the first geometric feature information; Determining the topological weight coefficient of the electrical equipment in the overall layout according to the connection path length and the number of branches between device nodes in the hierarchical relationship topology diagram, and performing spatial superposition of the topological weight coefficient and the device positioning reference point to generate a geometric distribution map with weight annotation; Synchronously analyzing the rated voltage parameters, rated current parameters, and interface specification parameters in the device attribute tags, and converting parameter descriptions in different formats into attribute parameter vectors in a unified dimension through semantic relationship mapping rules; Verify the data consistency between the attribute parameter vector and the geometric distribution atlas with weighted annotations, and eliminate abnormal device nodes with spatial position conflicts or parameter logic contradictions; Classify and integrate the verified attribute parameter vectors by device type into the first attribute feature information, and dynamically associate them with the device positioning reference points in the geometric distribution atlas with weighted annotations to generate a feature information set containing a geometric-attribute two-way indexing relationship; Among them, the geometric distribution atlas with weighted annotations is used as the input data for spatial overlap relationship analysis in subsequent steps, and the two-way indexing relationship in the feature information set is used for conflict coordination processing of cross-professional feature information.

3. The method according to claim 1, characterized in that, Inputting the structural support model data into the feature recognition model to extract the second geometric feature information associated with the distribution of support members and the second attribute feature information associated with the load-bearing parameters, including: Analyze the component node coordinate set and load parameter labels in the structural support model data to generate intermediate analysis data containing the connection point coordinates of the support members and the load distribution hierarchy; Perform spatial density clustering on the component node coordinate set in the intermediate analysis data, identify the boundary threshold between the dense area and the sparse area of the support member distribution, and extract the boundary coordinates of the dense area as the support member distribution density map in the second geometric feature information; According to the load transfer path directions of different components in the load distribution hierarchy, determine the load sharing ratio of each support member in the overall structure, and perform type mapping and superposition of the load sharing ratio and the support member distribution density map to generate a geometric distribution map with type identifiers; Synchronously analyze the static load value, dynamic load peak value, and seismic grade parameters in the load parameter labels, and convert the discrete load description fields into a load parameter vector with a unified dimension through parameter normalization rules; Verify the load direction consistency between the load parameter vector and the geometric distribution map with type identifiers, and filter out abnormal support nodes with inconsistent load transfer paths and component distribution directions; Classify and integrate the verified load parameter vectors by support member type into the second attribute feature information, and perform direction association with the support member distribution density map in the geometric distribution map with type identifiers to generate a feature information set containing a load-distribution two-way binding relationship; Among them, the geometric distribution map with type identifiers is used as the input data for spatial overlap relationship analysis in subsequent steps, and the two-way binding relationship in the feature information set is used for conflict coordination processing of cross-professional feature information.

4. The method according to claim 1, wherein Inputting the pipeline distribution model data into the feature recognition model to extract the third geometric feature information associated with the pipeline routing path and the third attribute feature information associated with the pipe diameter flow parameters, including: Analyze the pipeline node coordinate set and flow parameter labels in the pipeline distribution model data to generate intermediate analysis data containing the turning point coordinates of the pipeline and the topological graph of the connection relationship; Perform a spatial continuity analysis on the pipeline node coordinate set in the intermediate parsed data, identify the path extension directions between adjacent pipeline nodes, and extract the sequence of continuously changing trend angles in the path extension directions as the pipeline trend path segment direction vector in the third geometric feature information; Determine the fluid transmission priority of each pipeline path segment in the overall distribution according to the intersection type and connection depth of the pipeline branch nodes in the connection relationship topology diagram, and perform a flow direction correlation mapping between the fluid transmission priority and the pipeline trend path segment direction vector to generate a geometric distribution network diagram with flow direction labels; Synchronously parse the pipe diameter size parameter, maximum flow threshold, and pressure loss coefficient in the flow parameter label, and convert the heterogeneous flow description information into a pipe diameter flow parameter vector of a unified dimension through parameter standardization rules; Verify the hydrodynamic consistency between the pipe diameter flow parameter vector and the geometric distribution network diagram with flow direction labels, and screen out abnormal pipeline nodes where the flow direction label conflicts with the pipeline trend path segment direction vector; Classify and integrate the verified pipe diameter flow parameter vectors according to the pipeline transmission medium type into the third attribute feature information, and perform dynamic matching with the pipeline trend path segment direction vector in the geometric distribution network diagram with flow direction labels to generate a feature information set containing a two-way mapping relationship between path and flow; Among them, the geometric distribution network diagram with flow direction labels is used as the input data for spatial intersection relationship analysis in subsequent steps, and the two-way mapping relationship in the feature information set is used for conflict coordination processing of cross-professional feature information.

5. The method according to claim 1, wherein Based on the preset set of power engineering constraint rules, perform conflict coordination processing on the cross-professional feature information in the feature information set to determine the collaborative constraint parameters associated with the multiple professional design models, including: Extract the equipment positioning reference points in the geometric distribution map with weight annotations, the support member distribution density map in the geometric distribution map with type labels, and the pipeline trend path segment direction vector in the geometric distribution network diagram with flow direction labels from the feature information set; Based on the spatial safety rules in the set of power engineering constraint rules, detect the first spatial overlap area between the equipment positioning reference points and the support member distribution density map, and generate support member displacement compensation parameters according to the equipment-support spatial avoidance rules in the first association feature; Based on the pipeline avoidance rules in the set of power engineering constraint rules, detect the second spatial intersection area between the equipment positioning reference points and the pipeline trend path segment direction vector, and generate equipment positioning offset parameters according to the pipeline-equipment spatial avoidance rules in the second association feature; Based on the load transfer rules in the set of power engineering constraint rules, detect the third spatial interference area between the support member distribution density map and the pipeline trend path segment direction vector, and generate pipeline path adjustment parameters according to the load sharing ratio in the geometric distribution map with type labels; Classify and integrate the support member displacement compensation parameters, equipment positioning offset parameters, and pipeline path adjustment parameters according to professional types to generate collaborative constraint parameters including space avoidance rules, load transfer priorities, and flow coordination paths; Among them, the support member displacement compensation parameters in the collaborative constraint parameters are used for updating the structural support model data, the equipment positioning offset parameters are used for synchronizing the electrical equipment model data, and the pipeline path adjustment parameters are used for correcting the pipeline distribution model data.

6. The method according to claim 5, wherein Synchronously update the parameters of the multiple professional design model data according to the collaborative constraint parameters to generate a unified power engineering collaborative design model, including: Inverse map the support member displacement compensation parameters in the collaborative constraint parameters to the component connection point coordinate set in the structural support model data to generate an updated support member distribution density map and load-bearing parameters; Inverse map the equipment positioning offset parameters in the collaborative constraint parameters to the equipment installation base point coordinates in the electrical equipment model data to generate an updated equipment positioning reference point and equipment attribute parameters; Inverse map the pipeline path adjustment parameters in the collaborative constraint parameters to the pipeline node coordinate set in the pipeline distribution model data to generate an updated pipeline routing path segment direction vector and pipe diameter flow parameters; Based on the spatial overlap relationship between the updated support member distribution density map and the equipment positioning reference point, verify whether the space avoidance rules in the collaborative constraint parameters meet the preset safety distance threshold; Based on the spatial intersection relationship between the updated pipeline routing path segment direction vector and the equipment positioning reference point, verify whether the flow coordination path in the collaborative constraint parameters meets the preset pipeline avoidance threshold; When all verification results meet the power engineering constraint rule set, spatially align the updated structural support model data, electrical equipment model data, and pipeline distribution model data according to a unified coordinate reference to generate a power engineering collaborative design model with consistent versions; Among them, the power engineering collaborative design model contains parameter change records corresponding to the collaborative constraint parameters, and the parameter change records are used for version tracing during subsequent construction data docking.

7. The method according to claim 6, wherein Output the three-dimensional space coordinate data and equipment interface parameter data corresponding to the power engineering collaborative design model, including: Extract the three-dimensional coordinate data corresponding to the updated equipment positioning reference point, the node coordinate set corresponding to the support member distribution density map, and the spatial trajectory data corresponding to the pipeline routing path segment direction vector from the power engineering collaborative design model; Convert the three-dimensional coordinate data into the reference coordinate system format supported by the construction positioning system, where the conversion process includes plane projection correction of elevation data and coordinate offset compensation; Divide the node coordinate set and spatial trajectory data into segmented construction units according to the construction process requirements, and add avoidance rule identifiers corresponding to the collaborative constraint parameters to each construction unit; Parse the interface position change data associated with the device positioning offset parameter in the device interface parameter data, and repackage the terminal numbers and connection sequences according to the construction interface standard; Send the segmented construction unit data, avoidance rule identifier, and repackaged interface position change data to the external construction system through an encrypted transmission channel, and receive the data integrity verification result returned by the construction system; Locate the parameter change records that do not meet the construction specifications in the power engineering collaborative design model according to the error flag in the data integrity verification result, and trigger a secondary correction process based on the collaborative constraint parameters; When the data integrity verification result passes, generate a status identification signal indicating the completion of the docking with the external construction system, and lock the data of the current version of the power engineering collaborative design model.

8. The method according to claim 1, characterized in that, The generation process of the pre-trained feature recognition model includes: Obtain the electrical equipment installation position data in the historical power engineering design dataset, parse the device base point coordinates and adjacent device spacing parameters in the electrical equipment installation position data, and generate a device spatial distribution topology map; Obtain the structural support node data in the historical power engineering design dataset, extract the support member connection point coordinates and load transfer direction parameters in the node data, and generate a support load distribution topology map; Obtain the pipeline path data in the historical power engineering design dataset, parse the pipeline turning point coordinates and fluid direction identification parameters in the path data, and generate a pipeline flow topology map; Align the device spatial distribution topology map, support load distribution topology map, and pipeline flow topology map in the spatial coordinate system to generate a global topology connection map; Based on the node connection density in the global topology connection map, identify the device cluster areas in the electrical equipment installation position data where the occurrence frequency is greater than the preset frequency, and extract the device base point coordinates of the device cluster areas as training sample labels; Based on the edge connection direction in the global topology connection map, identify the consistency relationship between the load transfer path in the support load distribution topology map and the fluid direction in the pipeline flow topology map, and generate cross-professional feature association rules; Input the device base point coordinates and cross-professional feature association rules into the graph neural network model for iterative training until the error rate between the device positioning prediction coordinates output by the graph neural network model and the historical annotation data is lower than the preset threshold; Among them, after the graph neural network model is trained, it is stored as a pre-trained feature recognition model, and the cross-professional feature association rules are used for conflict detection in subsequent collaborative design.

9. A BIM power engineering collaborative design device, characterized in that, Including: A memory that stores a computer program; A processor for loading the computer program to implement the BIM power engineering collaborative design method according to any one of claims 1-8.

Images