GIM equipment data stripping method and system based on three-dimensional model semantic retrieval

Abstract

The invention relates to the technical field of transformer substation equipment data stripping, and discloses a GIM equipment data stripping method and system based on three-dimensional model semantic retrieval, and the method comprises the steps: obtaining target transformer substation equipment information, and building a first information structure tree set based on the target transformer substation equipment; establishing a three-dimensional model based on the target substation equipment, and performing first preprocessing on the three-dimensional model; performing first matching operation on the first preprocessing result and the first information structure tree set; and performing retrieval according to a result of the first matching operation to obtain a result after equipment data stripping. According to the method, the standard information structure tree is constructed by taking the equipment as a core, the hierarchical architecture and attribute logic of the equipment are deeply analyzed, the equipment set, physical and engineering parameters and key parameters are accurately positioned and extracted by taking the equipment as a foundation and combining a semantic retrieval technology, a traditional data stripping mode is innovated, intelligent and accurate extraction is realized, and the efficiency is improved. And the problems of complexity and low efficiency of manual stripping are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of substation equipment data stripping, and in particular to a GIM equipment data stripping method and system based on three-dimensional model semantic retrieval. Background Art

[0002] The accuracy of power equipment data is crucial for the stable operation and management of substations today. Key data, such as geometric information, physical properties, and engineering parameters, plays an important role in supporting routine substation maintenance, equipment optimization, condition monitoring, and fault diagnosis. As modern technologies continue to integrate into power systems, intelligent processing of substation equipment data is becoming a growing trend. Leveraging intelligent technology to improve equipment data quality and ensure compliance with industry standards is crucial for substation equipment data processing.

[0003] Traditionally, data stripping from substation GIM equipment relies on manual labor. This process is complex and time-consuming, significantly increasing the time and labor costs of data processing. Furthermore, due to the inevitable subjectivity of human operators, manual data stripping lacks the ability to deeply analyze data, resulting in poor sensitivity to potential underlying equipment faults. This can easily lead to data errors caused by fatigue and misoperation, seriously threatening the stability of the power grid system. Furthermore, with the increasing penetration of intelligent technology into our daily lives, traditional manual methods are no longer adaptable to the data processing needs of the intelligent grid, hindering the further development of intelligent power grid systems.

[0004] In the development of intelligent power grid systems, 3D modeling technology has been widely used in substations in recent years. This technology can intuitively and accurately present the structural and spatial relationships between substation equipment through 3D models, automating the extraction and matching of large amounts of data in a short period of time. It is a major trend in the development of GIM data extraction today. However, the application of 3D modeling technology in substations still faces several problems and challenges. In the complex and diverse substation environment, how to improve the consistency of data extracted from different devices, overcome data loss caused by compatibility issues, and ensure that the stripped data complies with industry specifications and standards are urgent issues that need to be addressed by 3D technology. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a GIM equipment data stripping method and system based on three-dimensional model semantic retrieval, which can solve the problems of data inconsistency, data missing, and high cost and time consumption caused by manual operation in traditional methods.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for stripping GIM device data based on three-dimensional model semantic retrieval, comprising:

[0009] Acquire target substation equipment information, and establish a first information structure tree set based on the target substation equipment;

[0010] The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation;

[0011] Establishing a three-dimensional model based on the target substation equipment, and performing a first preprocessing on the three-dimensional model;

[0012] performing a first matching operation on the first preprocessing result and the first information structure tree set;

[0013] A search is performed based on the result of the first matching operation to obtain a result after device data stripping.

[0014] As a preferred solution of the GIM device data stripping method based on three-dimensional model semantic retrieval according to the present invention, the first information structure tree set includes:

[0015] The first information structure tree set is a plurality of standard information structure trees for target substation equipment. The establishment of the standard information structure tree includes:

[0016] The equipment in the target substation is regarded as the basic unit;

[0017] Establishing different standard information structure trees for the basic units;

[0018] The standard information structure tree includes the hierarchical relationship of the components within the basic unit and the attribute parameters of several components.

[0019] As a preferred solution of the GIM device data stripping method based on three-dimensional model semantic retrieval according to the present invention, the first information structure tree set further includes:

[0020] Compare the tree structure of the standard information structure tree of the same type of equipment in the target substation;

[0021] If there is a first standard information structure tree that can fully cover the standard information structure trees of other devices of the same type, the first standard information structure tree is used as the universal standard information structure tree for devices of this type;

[0022] If it does not exist, the standard information structure tree of the same type of equipment is recorded as a different standard information structure tree and stored in the first information structure tree set.

[0023] As a preferred solution of the GIM equipment data stripping method based on three-dimensional model semantic retrieval according to the present invention, the step of establishing a three-dimensional model based on the target substation equipment includes:

[0024] Obtaining a geographic information model data file of the target substation;

[0025] Performing a first data analysis on the geographic information model data file, wherein the first data analysis is used to separate the geographic information model data file into original hierarchical structure information, spatial geometric shape information, and attribute information;

[0026] Performing format conversion on the geographic information model data file after parsing the first data, and converting the geographic information model data into three-dimensional grid data;

[0027] The three-dimensional model is established according to the three-dimensional mesh data.

[0028] As a preferred solution of the GIM device data stripping method based on three-dimensional model semantic retrieval according to the present invention, the first preprocessing of the three-dimensional model includes:

[0029] Storing the original hierarchical structure information, spatial geometric shape information and attribute information in an object representation file;

[0030] Write the attribute information corresponding to all levels in the geographic information model file into the database structured query language format file.

[0031] As a preferred solution of the GIM device data stripping method based on three-dimensional model semantic retrieval according to the present invention, the first matching operation on the first preprocessing result and the first information structure tree set includes:

[0032] Parsing the ontology file of the three-dimensional model according to the first information structure tree set to obtain a second information structure tree for the three-dimensional model;

[0033] Obtain all nodes in the first information structure tree set as a first node set, and obtain all nodes in the second information structure tree as a second node set;

[0034] A matching degree between the first node set and the second node set is calculated.

[0035] As a preferred solution of the GIM device data stripping method based on three-dimensional model semantic retrieval according to the present invention, the first matching operation on the first preprocessing result and the first information structure tree set further includes:

[0036] Preset several matching thresholds;

[0037] The matching degree between the first node set and the second node set is compared with a plurality of matching degree thresholds to obtain a matching result.

[0038] In a second aspect, the present invention provides a GIM device data stripping system based on 3D model semantic retrieval, comprising:

[0039] A data acquisition module, configured to acquire target substation equipment information and establish a first information structure tree set based on the target substation equipment;

[0040] The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation;

[0041] A preprocessing module, configured to establish a three-dimensional model based on the target substation equipment and perform a first preprocessing on the three-dimensional model;

[0042] a matching module, configured to perform a first matching operation on the first preprocessing result and the first information structure tree set;

[0043] The stripping module is used to perform a search based on the result of the first matching operation to obtain a result after the device data is stripped.

[0044] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-described method when executing the computer program.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described above when the computer program is executed by a processor.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes a GIM equipment data stripping method and system based on three-dimensional model semantic retrieval, obtains target substation equipment information, establishes a first information structure tree set based on the target substation equipment; establishes a three-dimensional model based on the target substation equipment, and performs a first preprocessing on the three-dimensional model; performs a first matching operation on the first preprocessing result and the first information structure tree set; performs a search based on the result of the first matching operation to obtain the result after the equipment data stripping. This application constructs a standard information structure tree with the equipment as the core, deeply analyzes the equipment hierarchical architecture and attribute logic, and combines this as the cornerstone with semantic retrieval technology to accurately locate and extract equipment sets, physical and engineering parameters, accurately extract key parameters, innovate the traditional data stripping mode, realize intelligent and precise extraction, and solve the complex and inefficient dilemma of manual stripping. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A method flow chart of a GIM device data stripping method based on 3D model semantic retrieval provided by one embodiment of the present invention.

[0049] Figure 2 A GIM hierarchical structure and reference relationship diagram of a GIM device data stripping method based on three-dimensional model semantic retrieval is provided as an embodiment of the present invention.

[0050] Figure 3 A schematic diagram comparing the accuracy of a GIM device data stripping method based on 3D model semantic retrieval provided by an embodiment of the present invention with that of a traditional method.

[0051] Figure 4 An internal structure diagram of a computer device providing a GIM device data stripping method based on 3D model semantic retrieval according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0053] Example 1, with reference to Figures 1-4 , which is the first embodiment of the present invention, provides a GIM device data stripping method based on 3D model semantic retrieval, comprising:

[0054] Before introducing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0055] GIM devices: GIM (Geographic Information Model) devices are those that provide geographic location information. In substation environments, GIM devices typically involve data modeling of power equipment. This data, including geometric information, physical properties, and engineering parameters, is used to support routine substation maintenance, equipment optimization, condition monitoring, and fault diagnosis.

[0056] GIM data: GIM data refers to the collection of geographic location-related information obtained through GIM technology. Specifically in the substation scenario, it contains detailed information about each device in the substation, such as its hierarchical structure, reference relationships, spatial geometry, and attribute information. This data is crucial for intelligent substation processing and can be used to automate data extraction and matching processes.

[0057] GIM Model: A GIM model is a three-dimensional representation built from GIM data. It intuitively and accurately displays the structure and spatial relationships between substation equipment. The GIM model not only helps understand the complex spatial layout within the substation but also provides a foundation for automated data processing, such as using semantic search techniques to quickly extract required information.

[0058] *.ifc and *.stl model files: *.ifc (Industry Foundation Classes) is an open standard file format primarily used in BIM (Building Information Modeling) within the construction industry. In power systems, the IFC format is also used to describe 3D models of power facilities and their properties.

[0059] The *.stl (Stereolithography or Standard Tessellation Language) file format is widely used in 3D printing and other CAD applications to describe the surface geometry of an object. Both formats are designed to facilitate the exchange of 3D model data between different software.

[0060] FBX model file: Developed by Autodesk, BX (Filmbox) is a file format for exchanging 3D data. It supports complex animations, materials, textures, and other rich 3D information, and is widely used in game development, film and television special effects production, and other fields. In the context of substation data processing, the FBX format is used to store assembled and converted 3D mesh data for subsequent rendering and optimization.

[0061] SQL format files: SQL (Structured Query Language) is a programming language specifically designed for managing database systems. SQL format files generally refer to scripts written in SQL that define how to access, query, update, and manage database data. In substation data processing, SQL format files may be used to construct database tables containing attribute information corresponding to all hierarchical levels, facilitating data management and querying.

[0062] Existing technologies face challenges such as incompatible model file formats, inefficient information extraction, and difficulties in data management and retrieval. Traditional methods for processing 3D model data for substation equipment often face complex and time-consuming data conversion and integration due to the diverse model file formats. Furthermore, traditional methods often lack effective means of extracting the rich semantic information contained in the models, such as device attributes and hierarchical relationships. This information is often overlooked or underutilized in subsequent data processing and analysis. Furthermore, with the continuous growth of substation data, efficiently managing and retrieving this data has become a pressing issue.

[0063] This application provides a method that can effectively solve the above-mentioned problems. Next, we will explain in detail how to implement the GIM device data stripping method based on 3D model semantic retrieval with multiple embodiments.

[0064] Figure 1 A method flow chart of a GIM device data stripping method based on 3D model semantic retrieval is shown, including:

[0065] S101, obtaining target substation equipment information and establishing a first information structure tree set based on the target substation equipment;

[0066] In an optional embodiment, the target substation equipment may include key equipment such as transformers, circuit breakers, disconnectors, capacitors, reactors, and mutual inductors. These devices play a vital role in the substation, and their operating status directly impacts the stability and security of the entire power system. To establish an accurate information structure tree, a comprehensive and detailed collection of the hierarchical structure and attribute information of these devices is required.

[0067] In an optional embodiment, for example, the hierarchical structure of a transformer might include its main body, cooling system, insulation system, and other components, while the attribute information might include key parameters such as its rated voltage, rated current, capacity, and loss. Similarly, for other devices, corresponding hierarchical structures and attribute information libraries need to be constructed based on their specific physical structures and functional characteristics.

[0068] In an optional embodiment, for example, a transformer of the same type may include a hierarchical relationship between components such as the core, windings, and oil tank, as well as attributes such as voltage level, capacity, and insulation parameters. The core node can be associated with attribute data such as material information and magnetic permeability, while the winding node is associated with parameters such as the number of winding turns, wire diameter, and insulation level. Analogously analyzing the transformer, the structural components and attribute information of other types of equipment in the substation (busbars, lightning arresters, etc.) provides a framework for further data extraction.

[0069] In an embodiment of the present application, the target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation.

[0070] In an optional embodiment, a hierarchical structure can be used to describe the subordination and assembly relationships between components within a device. This structure is typically presented as a tree, where the root node represents the device itself, and the child nodes represent the various components or parts of the device. This hierarchical structure helps clearly demonstrate the internal structure of the device and the relationships between components.

[0071] In an optional embodiment, attribute information is a detailed description of the device and its components, including its physical characteristics (e.g., size, weight, and material), electrical characteristics (e.g., rated voltage and current), operating status (e.g., temperature, humidity, and pressure), and any other information related to the device's performance, functionality, and safety. Attribute information typically exists in the form of key-value pairs, where the key is the attribute name and the value is the attribute's specific description or numerical value.

[0072] In this embodiment of the present application, the first information structure tree set includes:

[0073] The first information structure tree set is a number of standard information structure trees for target substation equipment. The establishment of the standard information structure tree includes:

[0074] The equipment in the target substation is regarded as the basic unit;

[0075] Establish different standard information structure trees for basic units;

[0076] The standard information structure tree includes the hierarchical relationship of the internal components of the basic unit and the attribute parameters of several components.

[0077] It should be noted that the meaning of taking the equipment in the target substation as the basic unit is to regard the various equipment in the substation as independent entities, and each equipment has its own unique hierarchical structure and attribute information. These devices, as basic units, constitute the basis of the entire substation data model. By conducting detailed analysis and modeling of each device, the present application can construct a standard information structure tree for each device. These tree structures clearly show the hierarchical relationship between the components inside the equipment, as well as the specific attribute parameters of each component. This modeling method not only helps the present application to have a deeper understanding of the structure and function of the equipment, but also provides great convenience for subsequent data processing and analysis. In the process of constructing the standard information structure tree, the present application fully considers the diversity and complexity of the equipment to ensure that each device can be accurately and comprehensively described.

[0078] For example, for a specific transformer device, its standard information structure tree may include the hierarchical relationship of the main components such as the transformer body, windings, cores, and cooling systems. Among them, the transformer body node may be associated with key attributes such as rated voltage, rated current, and capacity; the winding node may record in detail specific parameters such as winding type, number of turns, and insulation level. The core node and the cooling system node also contain a series of attribute information closely related to their functions and characteristics. Through such a hierarchical structure and attribute parameter description, the present application can accurately capture the core characteristics of the transformer equipment and provide a solid foundation for subsequent data stripping and semantic retrieval.

[0079] In this embodiment of the present application, the first information structure tree set also includes:

[0080] Compare the tree structure of the standard information structure tree of the same type of equipment in the target substation;

[0081] If there is a first standard information structure tree that can fully cover the standard information structure trees of other devices of the same type, the first standard information structure tree is used as the universal standard information structure tree for devices of this type;

[0082] If it does not exist, the standard information structure tree of the same type of equipment is recorded as a different standard information structure tree and stored in the first information structure tree set.

[0083] For example, in actual application, assume that there are three different types of transformer equipment in the target substation: T1, T2 and T3. In order to construct a standard information structure tree that can universally and accurately describe these three types of transformers, this application follows the following steps:

[0084] Step 1: For each transformer (T1, T2, T3), a separate standard information structure tree is constructed. For example, the information structure tree for T1 might include components such as the core, windings, and cooling system, along with their corresponding attribute parameters (e.g., core material, number of winding turns, cooling method, etc.). Similarly, each T2 and T3 also have their own hierarchical structure and attribute information library based on their specific physical structure and functional characteristics.

[0085] Step 2: Compare and analyze the three information structure trees constructed for T1, T2, and T3. The goal is to find out whether one of the trees can fully cover the information of the other two trees, that is, to find a "maximum common subtree."

[0086] Suppose that after comparison, it is found that the information structure tree of T1 not only includes the core components and properties shared by T2 and T3 (such as the basic winding and cooling system that all transformers have), but also includes some special but non-conflicting components or parameters (such as special insulation materials).

[0087] In this case, the information structure tree of T1 can be used as the universal standard information structure tree for this type of transformer. This means that for most common data processing tasks, the information structure tree of T1 is sufficient because it already covers the main features of T2 and T3.

[0088] Step 3. If there are certain special types of transformers (such as T2 or T3 here), which have unique components or parameters that cannot be fully covered by the general standard information structure tree (such as T3's unique high-efficiency cooling system), then it is necessary to establish and save their own standard information structure trees for these devices separately in the first information structure tree set.

[0089] It should be noted that this ensures that even devices with unique designs or characteristics are accurately represented and their specific information can be easily accessed when needed.

[0090] It should also be noted that obtaining target substation equipment information and establishing a first information structure tree set based on the target substation equipment provides a solid structured foundation for subsequent data stripping and semantic retrieval. By detailed analysis and modeling of the hierarchical structure and attribute information of the target substation equipment, the present application ensures that this information can be accurately and efficiently extracted and utilized during subsequent processing. This structured data representation not only improves the speed and accuracy of data processing, but also provides strong support for intelligent management and maintenance of substations. Specifically, after establishing the first information structure tree set, the present application can use this tree structure to strip and reorganize the data of substation equipment, thereby achieving rapid identification and classification of different equipment data. At the same time, combined with semantic retrieval technology, the present application can further mine and utilize the rich semantic information in the equipment data, such as the association relationship between devices and the similarity of attribute information, thereby providing more comprehensive and accurate data support for routine maintenance, equipment optimization, status monitoring, and fault diagnosis of substations.

[0091] S102, establishing a three-dimensional model based on target substation equipment, and performing a first preprocessing on the three-dimensional model;

[0092] In an optional embodiment, the 3D model can be created using various 3D modeling software or tools, such as AutoCAD, 3ds Max, Revit, etc. These software provide a wealth of modeling functions and tools, allowing users to accurately construct 3D models of substation equipment based on the actual size, shape, material, and other information of the equipment.

[0093] In an optional embodiment, these 3D models can be generated based on geographic information model data files (such as GIM data files) or detailed design information from other sources. Geographic information model data files typically contain detailed information such as the device's geographic location, spatial layout, size ratio, and material, which are crucial for building accurate 3D models.

[0094] In an embodiment of the present application, establishing a three-dimensional model based on target substation equipment includes:

[0095] Obtain the geographic information model data file of the target substation;

[0096] Performing a first data analysis on the geographic information model data file, the first data analysis being used to separate the geographic information model data file into original hierarchical structure information, spatial geometric shape information, and attribute information;

[0097] Performing format conversion on the geographic information model data file after the first data is parsed, and converting the geographic information model data into three-dimensional grid data;

[0098] Create a 3D model based on 3D mesh data.

[0099] For example, Figure 2 The following is a diagram of the GIM hierarchical structure and reference relationships used in this application. This diagram shows an example of an information structure tree used to describe the information organization of transformer equipment in a substation, where:

[0100] Top-level file (*.gim): This is the top-level file of the entire project, which contains the basic information and configuration of the project.

[0101] Project configuration file (project.cbm): Starting from the top-level file, first point to the project configuration file, which defines the overall architecture and configuration information of the project.

[0102] System level (F1System, F2System, F3System, F4System): The project configuration file is further broken down into multiple system levels, each representing a specific subsystem or functional module. For example, F1System, F2System, and so on correspond to different transformer types or functional modules.

[0103] Each system level has its corresponding configuration file (*.cbm), which describes the specific configuration and parameters of the system in detail.

[0104] Component level (*.dev): Below the system level, it is further divided into specific component levels. Each component level represents a specific physical component or assembly, such as a winding, core, etc.

[0105] The component level also has its corresponding configuration files (*.dev), which describe the specific properties and parameters of the component in detail.

[0106] Other file types:

[0107] *.ifc: is an interface file used to describe the interaction between different systems.

[0108] *.sch: It is a circuit diagram file used to describe electrical connection relationships.

[0109] *.phm: It is a physical model file used to describe the physical properties of a component.

[0110] *.mod: is a model file used for 3D modeling.

[0111] *.stl: is a standard 3D mesh file used for 3D printing or modeling.

[0112] In this embodiment, when building a 3D model, a separate standard information structure tree is constructed for each transformer device (e.g., T1, T2, T3) based on its specific physical structure and functional characteristics. For example, for T1, you can start with the top-level *.gim file and gradually refine it to the specific component level *.dev.

[0113] Furthermore, a comparative analysis will be conducted on multiple information structure trees constructed for different transformer devices to find the tree that can fully cover the information structure of other similar devices.

[0114] For example, assuming that the information structure tree of T1 can cover the main features of T2 and T3, the information structure tree of T1 can be used as a universal standard information structure tree.

[0115] Furthermore, for those special devices that cannot be fully covered by the universal standard information structure tree (such as certain unique components of T2 or T3), a separate standard information structure tree is established for them and saved in the first information structure tree set.

[0116] Furthermore, the constructed information structure tree can be used to efficiently perform data stripping and semantic retrieval.

[0117] For example, when you need to extract data for a specific component, you can quickly locate the corresponding *.dev file through the information structure tree and extract the required information from it.

[0118] Through such an information structure tree, not only can the commonalities and differences of various transformer equipment in the substation be accurately described, but it can also facilitate subsequent data management and retrieval work and improve the efficiency and accuracy of data processing.

[0119] In the embodiment of the present application, performing a first preprocessing on the three-dimensional model includes:

[0120] Storing original hierarchical structure information, spatial geometry information and attribute information in an object representation file;

[0121] Write the attribute information corresponding to all levels in the geographic information model file into the database structured query language format file.

[0122] Exemplarily, data parsing is performed on an input geographic information model (GIM) file to obtain original hierarchical structure, spatial geometry, and attribute information of the geographic information model (GIM), and the information is stored in a JavaScript Object Notation (JSON) file;

[0123] Convert the geometric information in the Geographic Information Model (GIM) from parameter expressions to 3D mesh expressions, and complete the operation of converting *.ifc and *.stl model files into intermediate storage model files;

[0124] According to the hierarchical structure and spatial transformation matrix of the Geographic Information Model (GIM), the basic original intermediate model files constructed through parametric modeling are assembled and converted to complete the restoration from Geographic Information Model (GIM) data to 3D mesh data, and the model files in Film Box (FBX) format are obtained.

[0125] Optimize the FBX model using reconstruction optimization technology to obtain the optimized FBX model file. At the same time, use multi-level rendering optimization technology to optimize the loading and display of the model;

[0126] The attribute information corresponding to all levels in the Geographic Information Model (GIM) is written into the database Structured Query Language (SQL) format file to complete the construction of the attribute table.

[0127] It should be noted that establishing a three-dimensional model based on the target substation equipment and performing the first preprocessing on the three-dimensional model provides more intuitive and accurate spatial information for subsequent data stripping and semantic retrieval. Through the first preprocessing, this application effectively extracts and converts the original hierarchical structure information, spatial geometry information, and attribute information in the geographic information model data file, and generates an FBX model file that can be used for three-dimensional modeling and optimization processing, as well as an SQL format file containing all hierarchical attribute information. Such processing not only retains the integrity and accuracy of the original data, but also improves the readability and operability of the data, laying a solid foundation for subsequent data stripping and semantic retrieval.

[0128] S103, performing a first matching operation on the first preprocessing result and the first information structure tree set;

[0129] In the embodiment of the present application, performing a first matching operation on the first preprocessing result and the first information structure tree set includes:

[0130] Parsing the ontology file of the three-dimensional model according to the first information structure tree set to obtain a second information structure tree for the three-dimensional model;

[0131] Obtain all nodes in the first information structure tree set as a first node set, and obtain all nodes in the second information structure tree as a second node set;

[0132] Calculate the matching degree between the first node set and the second node set.

[0133] In the embodiment of the present application, performing the first matching operation on the first preprocessing result and the first information structure tree set further includes:

[0134] Preset several matching thresholds;

[0135] The matching degree between the first node set and the second node set is compared with a plurality of matching degree thresholds to obtain a matching result.

[0136] In the embodiment of the present application, the three-dimensional model is parsed according to the first information structure tree set.

[0137] Step 1: For each device, parse the relevant parts of the 3D model based on the standard information structure tree (the first information structure tree set) constructed based on its hierarchical structure and attribute information. This process involves identifying each component in the model and its attributes and converting them into a structured ontology representation.

[0138] The result of the analysis is a second information structure tree for the 3D model, which reflects the specific structural characteristics and attribute information of the equipment in the 3D model. For example, if the transformer is being processed, the second information structure tree will include detailed information about the core, windings, and other components.

[0139] Step 2: Determine the query subject node set Ns (the set of nodes belonging to the extended query ontology) and the target node set Na (the set of nodes belonging to the application ontology). In this context, Ns can be considered the set of nodes extracted from the second information structure tree, while Na is the set of nodes in the first information structure tree. This means identifying the information categories that need to be extracted from the GIM dataset and determining their location within the substation equipment hierarchy.

[0140] For all elements Ens belonging to Ns and elements Ena belonging to Na, the direct predecessor of Ens is the classification root node of the extended query ontology (Parent(Ens)=Class), and the direct predecessor of Ena is the classification root node of the application ontology (Parent(Ena)=Classsst).

[0141] It should be noted that Parent(Ens)=Class means that for all elements Ens in the node set Ns belonging to the extended query ontology, their direct parent node (i.e., direct predecessor node) is the classification root node of the extended query ontology, referred to as "Class." Here, "Class" can be understood as an abstract representation of a concept or category, which represents the basic classification of a certain type of device or component.

[0142] It should be noted that Parent(Ena)=Classsst means that for all elements Ena in the node set Na belonging to the application ontology, their direct parent node is the application ontology's classification root node, marked here as "Classsst." This mark may be a typo or a specific classification name defined within the document, used to distinguish classification root nodes in different contexts or application scenarios.

[0143] Typically this should be something like "Class", representing another concept or the root node in a category hierarchy.

[0144] Step 3: Use the formula to calculate the similarity or matching degree between the elements from Ns and Na. Several matching thresholds in this application include correlation thresholds and relevance thresholds. Specifically, the algorithm compares corresponding nodes in the two information structure trees to evaluate whether they represent the same component or have similar functions. For example, when processing a transformer, the algorithm may compare attribute values ​​such as core material and magnetic permeability to determine whether two nodes represent the same component.

[0145] For example, to match elements from Ns and Na, the following formula can be used:

[0146] Rel HS (C i ,C j )=m-len(C i ,C j )-n×turn(C i ,C j )

[0147] Calculate the correlation. When the above value is greater than or equal to the preset threshold T1, the two concepts are correlated. Under the premise of correlation matching, the correlation degree is calculated using the following formula:

[0148] S(C i ,C j )=α×SN+β×SA+δ×SS+γ×SR

[0149] in,

[0150]

[0151] If the similarity is greater than the preset threshold T2, then the two concepts are similarly matched.

[0152] Step ④: Once a pair of elements Ci and Cj are confirmed to be similar matches, narrow the matching range to the subtree of this pair of elements to obtain new sets Ns and Na.

[0153] Step 5: Repeat the matching process. This step aims to refine the matching accuracy and ensure that sub-components at each level are correctly identified and matched. For example, if the transformer winding has been preliminarily matched, further detailed matching of specific parameters such as the number of turns and wire diameter is performed.

[0154] Step 6: Based on the matching results, key data such as relevant equipment set information, physical attributes, and engineering parameters are intelligently extracted from the GIM dataset. During this process, a pre-built standard information structure tree is used to guide the direction and standards of data extraction.

[0155] Step 7: The extracted data will be verified according to industry norms and standards to ensure its accuracy and consistency. If any abnormal or deviating data is found during the verification process, the corresponding correction algorithm will be used to adjust it to ensure the quality of the final output data.

[0156] For example, a power company is digitally upgrading a large substation under its jurisdiction to improve equipment maintenance efficiency, reduce failure rates, and support intelligent operation and maintenance decision-making. To achieve this goal, the company decided to use this application to automatically process data from various devices in the substation.

[0157] Specifically, assume that there is a key transformer in the substation that requires detailed data extraction and analysis. The following are the specific implementation steps for the first matching operation:

[0158] First, engineers built a standard information structure tree based on the hierarchical structure of the transformer in the substation (such as components such as the iron core, windings, and oil tank) and its attribute information (such as voltage level, capacity, insulation parameters, etc.).

[0159] For example, the core node is associated with properties such as material information and magnetic permeability; the winding node is connected to parameters such as the number of winding turns, wire diameter, and insulation level.

[0160] Next, the GIM file containing the transformer's detailed information was imported into the system. A series of preprocessing steps, including data parsing, parameter modeling, model assembly, optimization, and attribute storage, generated a 3D model of the transformer.

[0161] During this process, the model is converted to an intermediate format and optimized to ensure efficient rendering and display.

[0162] Then, the ontology file is parsed for the three-dimensional model according to the established standard information structure tree to obtain a second information structure tree for the three-dimensional model.

[0163] Initialize the matching sets Ns and Na, where Ns is the set of nodes extracted from the second information structure tree, and Na is the set of nodes in the first information structure tree. For example, in this scenario, "Parent(Ens)=Class" means that the direct predecessor of all nodes in the query ontology is the root node under the "Transformer" category, while "Parent(Ena)=Classsst" should be understood as the root node corresponding to a specific type or category in the application ontology.

[0164] Furthermore, a semantic search algorithm is used to calculate the similarity between elements from Ns and NaNa. For example, in the transformer example, the algorithm compares specific parameters such as core material and magnetic permeability to determine whether two nodes represent the same component or have similar functions.

[0165] Assuming that it is found during the matching process that a component node in the 3D model is very similar to a core node in the standard information structure tree, the two nodes will be considered to be preliminarily matched successfully.

[0166] When the initial matching is completed, the matching scope is narrowed down to the subtree of the successfully matched node, and more detailed attribute information, such as the number of winding turns and wire diameter, is further compared to confirm a more accurate matching relationship.

[0167] This process is repeated until all possible matching pairs are identified.

[0168] Based on the final matching results, key data such as relevant equipment collection information, physical properties, and engineering parameters are intelligently extracted from the GIM dataset.

[0169] The extracted data is verified according to industry specifications and standards, and any anomalies or deviations will be adjusted through corresponding correction algorithms to ensure the accuracy and consistency of the data.

[0170] It should be noted that the first matching operation performed on the first preprocessing result and the first information structure tree set can efficiently extract the specific information of the target substation equipment from the massive GIM data by accurately matching the three-dimensional model with the standard information structure tree. This method not only reduces the need for manual intervention and reduces the cost of data processing, but also significantly improves the accuracy and efficiency of data processing. More importantly, by constructing a standard information structure tree, a unified data standard is provided for the digital management of substation equipment, making subsequent data analysis and decision support more reliable and efficient. In addition, the use of semantic retrieval algorithms for matching can also automatically identify and associate the similarities and correlations between different devices, providing strong support for the intelligent operation and maintenance and fault prediction of substation equipment.

[0171] S104: Search according to the result of the first matching operation to obtain the result after device data stripping.

[0172] In an optional embodiment, after completing the first matching operation, the system has determined the correspondence between each component node in the 3D model and the standard information structure tree. For example, it has been confirmed that the core node in the 3D model matches the core node in the standard information structure tree, and the matching is further refined to a more detailed attribute level (such as material, magnetic permeability, etc.).

[0173] Next, based on these matching results, the system intelligently extracts all necessary information related to the transformer from the GIM dataset. This includes but is not limited to:

[0174] Physical properties: such as the material of the core, the number of turns of the winding and the wire diameter, etc.

[0175] Engineering parameters: such as voltage level, capacity, insulation parameters, etc.

[0176] Aggregate information: information related to the overall structure of the transformer, such as the connection method between components and their relative positions.

[0177] The extracted data is verified against industry specifications and standards. This process ensures that the acquired data is accurate and conforms to the expected format. If any anomalies or deviations are detected during the verification process, the system automatically activates the corresponding correction algorithm to make adjustments.

[0178] For example, if a physical property value is detected to be outside the normal range, the value may be adjusted to return to a reasonable range by referring to historical data trends, statistical laws of data for similar types of equipment, or expert experience rules.

[0179] After verification and necessary corrections, the system will generate a complete equipment data stripping report. For the transformer in this example, this report will include all key equipment information, such as:

[0180] Core information: material, magnetic permeability, etc.

[0181] Winding information: number of turns, wire diameter, insulation grade, etc.

[0182] Other component information: fuel tank specifications, cooling system configuration, etc.

[0183] Overall performance parameters: voltage level, rated capacity, operating status monitoring indicators, etc.

[0184] Ultimately, the stripped data can be directly used to support various subsequent application scenarios, such as equipment maintenance planning, fault diagnosis and analysis, and optimization and upgrade decision-making. Furthermore, this data can be integrated into a broader grid management system to enable effective monitoring and management of the entire substation and even the larger power network.

[0185] In summary, the present invention proposes a GIM equipment data stripping method based on three-dimensional model semantic retrieval, which obtains target substation equipment information and establishes a first information structure tree set based on the target substation equipment; establishes a three-dimensional model based on the target substation equipment, and performs a first preprocessing on the three-dimensional model; performs a first matching operation on the first preprocessing result and the first information structure tree set; and performs a search based on the result of the first matching operation to obtain the result after the equipment data is stripped. This application constructs a standard information structure tree with the equipment as the core, deeply analyzes the equipment hierarchical architecture and attribute logic, and combines this with semantic retrieval technology as the cornerstone to accurately locate and extract equipment sets, physical and engineering parameters, accurately extract key parameters, innovate the traditional data stripping mode, realize intelligent and precise extraction, and solve the complex and inefficient dilemma of manual stripping.

[0186] Example 2, in a preferred embodiment, as Figure 3 The following is a diagram showing the accuracy comparison between this algorithm and the traditional algorithm. This diagram intuitively shows the performance of the two algorithms at different matching thresholds. The specific explanations are as follows:

[0187] Among them, the blue one is the traditional algorithm, and the red one is the algorithm adopted by the present invention;

[0188] The horizontal axis (X-axis) represents the range of the matching threshold, from 0 to 1. 0 represents the lowest matching requirement, while 1 represents the highest matching requirement. As the value increases, the system's requirements for data matching become more stringent.

[0189] The vertical axis (Y-axis) represents the result of the matching operation or the change of a certain performance indicator, which is also from 0 to 1. 0 represents the lowest performance, that is, in this case, the algorithm is almost unable to correctly identify and match the corresponding data; 1 represents the highest performance, which means that the algorithm can accurately match data under this condition.

[0190] Blue curve (traditional algorithm): This curve shows the performance of the traditional algorithm at different matching thresholds. Generally, as the matching threshold increases, the performance of the traditional algorithm decreases significantly. This is because traditional manual or semi-automatic methods have difficulty adapting to more stringent matching conditions, resulting in poor performance at high matching thresholds.

[0191] Red curve (algorithm used in this paper): In comparison, the algorithm proposed in this paper outperforms traditional algorithms at all matching thresholds. In particular, at higher matching thresholds, the algorithm maintains relatively high performance. This is due to its semantic retrieval technology combined with 3D models, which enables more intelligent and accurate identification and matching of relevant data.

[0192] In summary, the algorithm of this application demonstrates greater flexibility and accuracy in responding to varying matching requirements. By introducing 3D model semantic retrieval technology, the system can gain a deeper understanding of the inherent meaning and structure of the data, thereby achieving high-precision matching while reducing sensitivity to changes in matching conditions. This not only improves the efficiency of data stripping but also significantly enhances the intelligence level of overall GIM device data management. Therefore, the present invention provides a more advanced and efficient method for GIM device data stripping, which is expected to be widely used in related fields in the future.

[0193] Example 3: This embodiment also provides a GIM device data stripping system based on 3D model semantic retrieval, including:

[0194] A data acquisition module, configured to acquire target substation equipment information and establish a first information structure tree set based on the target substation equipment;

[0195] The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation;

[0196] A preprocessing module, configured to establish a three-dimensional model based on target substation equipment and perform a first preprocessing on the three-dimensional model;

[0197] A matching module, configured to perform a first matching operation on the first preprocessing result and the first information structure tree set;

[0198] The stripping module is used to perform a search based on the result of the first matching operation to obtain a result after the device data is stripped.

[0199] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0200] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a GIM device data stripping method based on three-dimensional model semantic retrieval is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0201] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented:

[0202] Acquire target substation equipment information and establish a first information structure tree set based on the target substation equipment;

[0203] The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation;

[0204] Establishing a three-dimensional model based on target substation equipment and performing a first preprocessing on the three-dimensional model;

[0205] performing a first matching operation on the first preprocessing result and the first information structure tree set;

[0206] A search is performed based on the result of the first matching operation to obtain a result after the device data is stripped.

[0207] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0208] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages.

[0209] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0210] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0211] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0212] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0213] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A GIM device data stripping method based on 3D model semantic retrieval, characterized in that: include: Acquire target substation equipment information, and establish a first information structure tree set based on the target substation equipment; The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation; Establishing a three-dimensional model based on the target substation equipment, and performing a first preprocessing on the three-dimensional model; performing a first matching operation on the first preprocessing result and the first information structure tree set; A search is performed based on the result of the first matching operation to obtain a result after device data stripping.

2. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 1, characterized in that: The first information structure tree set includes: The first information structure tree set is a plurality of standard information structure trees for target substation equipment. The establishment of the standard information structure tree includes: The equipment in the target substation is regarded as the basic unit; Establishing different standard information structure trees for the basic units; The standard information structure tree includes the hierarchical relationship of the components within the basic unit and the attribute parameters of several components.

3. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 2, characterized in that: The first information structure tree set also includes: Compare the tree structure of the standard information structure tree of the same type of equipment in the target substation; If there is a first standard information structure tree that can fully cover the standard information structure trees of other devices of the same type, the first standard information structure tree is used as the universal standard information structure tree for devices of this type; If it does not exist, the standard information structure tree of the same type of equipment is recorded as a different standard information structure tree and stored in the first information structure tree set.

4. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 3, characterized in that: The establishing of the three-dimensional model based on the target substation equipment includes: Obtaining a geographic information model data file of the target substation; Performing a first data analysis on the geographic information model data file, wherein the first data analysis is used to separate the geographic information model data file into original hierarchical structure information, spatial geometric shape information, and attribute information; Performing format conversion on the geographic information model data file after parsing the first data, and converting the geographic information model data into three-dimensional grid data; The three-dimensional model is established according to the three-dimensional mesh data.

5. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 4, characterized in that: The performing a first preprocessing on the three-dimensional model comprises: Storing the original hierarchical structure information, spatial geometric shape information and attribute information in an object representation file; Write the attribute information corresponding to all levels in the geographic information model file into the database structured query language format file.

6. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 5, characterized in that: The performing a first matching operation on the first preprocessing result and the first information structure tree set includes: Parsing the ontology file of the three-dimensional model according to the first information structure tree set to obtain a second information structure tree for the three-dimensional model; Obtain all nodes in the first information structure tree set as a first node set, and obtain all nodes in the second information structure tree as a second node set; A matching degree between the first node set and the second node set is calculated.

7. The method for stripping GIM device data based on 3D model semantic retrieval according to claim 6, characterized in that: The performing a first matching operation on the first preprocessing result and the first information structure tree set further includes: Preset several matching thresholds; The matching degree between the first node set and the second node set is compared with a plurality of matching degree thresholds to obtain a matching result.

8. A GIM equipment data stripping system based on 3D model semantic retrieval, applying the method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, configured to acquire target substation equipment information and establish a first information structure tree set based on the target substation equipment; The target substation equipment information includes the hierarchical structure and attribute information of different equipment in the target substation; A preprocessing module, configured to establish a three-dimensional model based on the target substation equipment and perform a first preprocessing on the three-dimensional model; a matching module, configured to perform a first matching operation on the first preprocessing result and the first information structure tree set; The stripping module is used to perform a search based on the result of the first matching operation to obtain a result after the device data is stripped.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the processor implements the steps of a GIM device data stripping method based on three-dimensional model semantic retrieval according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a GIM device data stripping method based on three-dimensional model semantic retrieval according to any one of claims 1 to 7 are implemented.

Images