Power transformation secondary cable automatic numbering method based on digital design platform

Abstract

The invention provides a power transformation secondary cable automatic numbering method based on a digital design platform, which is applied to a power transformation secondary digital design platform and is embedded into a system comprising a database server and a client. Comprising the following steps: generating a screen cabinet type based on semantic recognition, constructing screen cabinet multi-dimensional attributes in combination with a screen cabinet engineering identifier, an association interval and an installation position, and storing the screen cabinet multi-dimensional attributes in a database; configuring a classification coding rule base comprising a physical interval coding rule and a virtual interval coding rule, wherein the rule base supports coding field combination selection and configuration of serial numbers and connectors; the method comprises the following steps: for a to-be-numbered cable, obtaining function description of the cable and multi-dimensional attributes of screen cabinets on two sides connected with the cable, analyzing a mapping relation between cable functions and screen cabinet attributes through a graph neural network model, and determining a starting point screen cabinet and an attribution interval of the cable; and calling a corresponding coding rule according to the affiliation interval, traversing the created cable numbers in the database, and generating a unique cable number through carry cooperation of the digital codes and the serial numbers.

Description

Technical Field

[0001] This invention belongs to the field of substation secondary system design technology, specifically relating to an automatic numbering method for substation secondary cables based on a digital design platform. Background Technology

[0002] In traditional substation secondary circuit design, terminal block drawing and cable inventory compilation heavily rely on manual operation and experience of designers. This process is usually based on a 2D CAD design environment, where design information exists in scattered, unstructured graphical and tabular forms, lacking a unified data association and sharing mechanism. Key information such as the numbering, start point, and end point of secondary cables often needs to be manually entered and verified one by one according to internal rules or industry conventions. Especially in large substation projects, the number of secondary cables often reaches thousands or even tens of thousands. Manual coding not only occupies a considerable proportion of the design cycle, becoming an efficiency bottleneck that restricts project progress, but also makes it difficult to meet the pace requirements of multi-disciplinary collaborative design.

[0003] This manual approach has significant limitations: In terms of efficiency, the workload of repetitive data entry and cross-checking is enormous, requiring designers to spend a lot of energy processing basic data, making it difficult to focus on core technology design; in terms of accuracy, manual operation is prone to problems such as inconsistent numbering on both sides, duplicate numbering, discontinuous numbering, and chaotic cable classification intervals, and such oversights often require correction at a multiplied cost during subsequent construction wiring and equipment commissioning stages, and may even pose hidden dangers to the long-term safe operation and maintenance of substations; in terms of management and collaboration, when the design scheme changes, the relevant cable and terminal block information cannot be automatically updated with the changes, requiring manual searching and modification one by one, which not only results in high consistency maintenance costs, but also makes it difficult to effectively trace design versions, causing many inconveniences for multi-team collaboration and subsequent operation and maintenance.

[0004] With the development of digital design technology for substation secondary circuits, the design of secondary circuits in substation projects has begun to rely on digital design platforms. The core advantage of these platforms lies in their structured creation of data objects such as substation bays, secondary equipment, cabinets, and area locations, establishing relationships between these data objects. They also enable real-time collaboration of design objects based on a database during the design process, providing fundamental support for automatic cable numbering. However, the automatic numbering function in existing digital platforms still has many shortcomings: some schemes have fixed coding rules, making it difficult to adapt to the personalized needs of substations with different voltage levels and wiring methods, especially unable to flexibly match the differentiated coding requirements of physical and virtual bays; some tools lack deep correlation between cable functions and cabinet attributes, requiring manual intervention to determine the origin and destination cabinets, resulting in insufficient accuracy in bay configuration; furthermore, the industry's application of standardized coding such as KKS codes is becoming increasingly widespread, and some existing numbering tools struggle to achieve seamless integration with the standardized system, affecting the data's universality throughout the design, construction, and operation and maintenance lifecycle. These problems mean that existing digital solutions have not completely solved the core pain points of traditional manual coding, and a more flexible, intelligent, and standardized automatic numbering method is still needed to meet the actual needs of substation secondary design. Summary of the Invention

[0005] To address the shortcomings and deficiencies of existing technologies, this invention provides an automatic numbering method for substation secondary cables based on a digital design platform. It aims to solve the problems of low efficiency, frequent duplicate or missing numbers, chaotic attribution intervals, and difficulties in collaborative management associated with traditional manual coding. At the same time, it compensates for the shortcomings of existing digital platforms, such as fixed numbering rules and insufficient intelligent judgment capabilities. This method, implemented through a substation secondary digital design platform, first constructs and stores multi-dimensional attributes in a database, including cabinet engineering identification, type, associated bay, and installation location. Cabinet types are intelligently generated using a semantic recognition model, automatically classifying cabinets into three levels. The third level is further subdivided into various specific functional types. Based on the system codes corresponding to the three-level cabinet classifications, cabinet type codes are configured one-to-one for cable coding. Second, an open coding rule library containing physical and virtual bays is configured. Both types of rules are equipped with general and personalized custom configuration modes, supporting flexible selection and arrangement of various coding fields, and allowing the addition of serial numbers and various types of connectors. For cables to be numbered, a graph neural network model analyzes the mapping relationship between cable function and cabinet attributes, intelligently determining the starting cabinet and assigned bay of the cable, while providing alternative implementation paths based on preset rule reasoning. Finally, based on the assigned bay, the corresponding coding rules are invoked, traversing the existing cable numbers in the database. Through the combination of numerical coding and serial number carry-over, a unique, unused number is automatically recommended. This invention automates and automates the entire cable numbering process, fundamentally avoiding various defects of traditional coding, enhancing design collaboration, and significantly improving the efficiency and quality of substation secondary circuit design. It can flexibly adapt to the personalized numbering needs of substations with different voltage levels and wiring methods.

[0006] The specific technical solution adopted by this invention to solve its technical problem is as follows: An automatic numbering method for substation secondary cables based on a digital design platform is applied to the substation secondary digital design platform, wherein the platform embeds a system including a database server and a client; the method includes: Based on semantic recognition, the type and type code of the cabinet are obtained. Combined with the cabinet engineering identifier, associated interval and installation location, the multi-dimensional attributes of the cabinet are constructed and stored in the database. Configure a classification coding rule library that includes physical interval coding rules and virtual interval coding rules. The rule library supports the selection of coding field combinations and the configuration of serial numbers and connectors. For the cable to be numbered, obtain its functional description and the multi-dimensional attributes of the cabinets on both sides it is connected to. Analyze the mapping relationship between the cable function and the cabinet attributes through a graph neural network model to determine the starting cabinet of the cable and the interval to which the cable belongs. According to the specified attribution interval, the corresponding encoding rules are invoked, the existing cable numbers in the database are traversed, and a unique cable number is generated by combining the numerical encoding with the serial number.

[0007] Furthermore, the type of the display cabinet is obtained through a semantic recognition model, the working process of which includes: By studying the screen cabinet names corresponding to the screen cabinet categories in historical projects, a matching relationship between the names of different screen cabinets and the screen cabinet types can be established. Perform data preprocessing on the cabinet names; The context-aware sentence vector of the cabinet name is obtained by semantic recognition model, and the cabinet type is matched to complete the three-level classification of the cabinet. Based on the system codes corresponding to the three-level classification of the cabinets, configure the cabinet type codes required for cable coding in a one-to-one correspondence.

[0008] Furthermore, the three-level classification hierarchy includes F1, F2, and F3, where F1 includes electrical systems and station service transformer systems; F2 includes monitoring systems, measuring equipment and meters, protection equipment panels, local secondary protection panels, switch cabinets, intelligent auxiliary control system cabinets, station service power distribution systems, UPS systems, battery systems, station service DC power distribution systems, and emergency power supplies; F3 is further subdivided into various functional types based on F2; the semantic recognition model includes a pre-trained language model.

[0009] Furthermore, the cabinet project identifier in the cabinet's multi-dimensional attributes includes the cabinet name, cabinet number, and cabinet KKS code, which are written into the database when the project is created; the associated interval attributes include interval type and interval name; the installation location attributes include room or area number and room or area characteristics, where the room or area characteristics include indoor or outdoor, switch site or non-switch site related identifiers; the cabinet object is created in the database using a system code plus a serial number, and the cabinet object is assigned the cabinet's multi-dimensional attributes.

[0010] Furthermore, the classification coding rule base is an open rule base, which can be configured according to engineering design requirements; the physical interval coding rule is subdivided into multiple interval type rules, and the virtual interval coding rule is subdivided into multiple interval type rules; the physical interval coding rule and the virtual interval coding rule are respectively configured with general rules, supporting general configuration and personalized custom configuration.

[0011] Furthermore, the encoding fields include cabinet number, cabinet KKS code, cabinet type code, interval name, location number, location numeric code, cable function type code, and cable function numeric code; the rule base supports selecting some encoding fields to participate in encoding, and supports adjusting the arrangement order of each encoding field, serial number, and connector; the connector includes at least one preset type; the location numeric code is configured according to different associated scenarios of the room or area where the cable to be numbered starts and ends; the cable function numeric code is divided into preset value ranges according to function type.

[0012] Furthermore, the graph neural network model uses cabinets as nodes and cables as edges, where node features include cabinet type, installation location, and associated interval, and edge features include cable function; the graph neural network model constructs a graph with known connections based on historical project data, and learns the representation of nodes and edges in the graph through training, and finds the corresponding source node as the starting cabinet and the target node as the ending cabinet for the cable to be numbered.

[0013] Furthermore, the numerical part of the number consists of a numerical encoding field and a serial number, which are incremented according to a preset value range and carried over; the traversal of the existing cable numbers in the database specifically involves traversing the existing cable numbers in the database that have the same interval as the cable to be numbered and recommending the next number that is not occupied; when the preset upper limit of the value is reached, the number is automatically carried over to a higher-order encoding segment.

[0014] Furthermore, the step of determining the cable starting cabinet and its assigned interval also includes: performing reasoning based on a pre-configured rule base that describes the correspondence between cable functions and cabinet types.

[0015] In addition, an automatic numbering system for substation secondary cables based on a digital design platform, the system being embedded in the substation secondary digital design platform, including a database server and a client; The database server is used to store the multi-dimensional attributes of the cabinets and the created cable numbers, as well as to deploy a semantic recognition model for automatic classification of cabinets and a graph neural network model for automatically determining the cable starting cabinet and the belonging interval.

[0016] The client is used to configure an open rule base and preset cabinet type codes, location numeric codes, cable function type codes, and cable function numeric codes. It is used to create cabinets and call the semantic recognition model to automatically classify cabinets. It is also used for cable design, calling the graph neural network model or preset rule base to analyze the mapping relationship between cable functions and cabinet attributes to determine the starting cabinet and belonging interval of the cable. Then, based on the belonging interval, it calls the corresponding coding rules, traverses the existing cable numbers in the database, and generates a unique cable number by combining the numeric code with the serial number and outputs it.

[0017] And a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described above.

[0018] A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described above.

[0019] Compared to existing technologies, this invention and its preferred solutions offer at least the following advantages: They completely change the traditional manual operation mode of substation secondary cable numbering. Through the collaboration of intelligent algorithms and preset rules, the entire numbering process is automated, significantly reducing the workload of manual input and verification, and effectively overcoming the efficiency bottleneck caused by manual coding. By leveraging the structured construction of multi-dimensional attributes of the cabinet, the intelligent application of semantic recognition and graph neural network models, and the refined configuration of the coding rule base, common problems such as duplicate or missing numbers, inconsistencies between the two sides, and chaotic attribution intervals are eliminated at the source, significantly improving the accuracy and standardization of cable numbering and laying a reliable foundation for subsequent construction, commissioning, and maintenance. The open design and flexible configuration capabilities of the coding rule base support differentiated coding requirements for physical and virtual intervals. The coding fields, order, and connection methods can be adjusted according to the personalized design requirements of different projects, resulting in stronger adaptability. Meanwhile, based on the structured storage and real-time collaboration features of the database, when the design changes, the relevant cable number information can be updated in a linked manner, reducing the cost of consistency maintenance, facilitating the traceability and management of design versions, enhancing the efficiency of multi-disciplinary collaborative design, and improving the overall quality of substation secondary circuit design and the level of full life cycle management. Attached Figure Description

[0020] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments: Figure 1 This is a flowchart illustrating the automatic numbering method for secondary cables in a power substation according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the cabinet attribute configuration in an embodiment of the present invention; Figure 3 This is a schematic diagram of the cabinet type code configuration in an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the configuration of the cabinet's location features in an embodiment of the present invention; Figure 5 This is a schematic diagram of the physical interval rule base configuration in an embodiment of the present invention; Figure 6 This is a schematic diagram of the virtual interval rule base configuration in an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the combination of cable encoding field, serial number, and connector in an embodiment of the present invention; Figure 8 This is a schematic diagram of the location digital code configuration in an embodiment of the present invention; Figure 9 This is a schematic diagram illustrating the configuration of cable function type code and cable function numeric code in an embodiment of the present invention. Detailed Implementation

[0021] To make the features and advantages of the present invention more apparent and understandable, specific embodiments are described below in detail: It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] The purpose of this invention is to provide an automatic numbering method for substation secondary cables based on a digital design platform. The method provides a system embedded in the substation secondary digital design platform, including a database server and a client. The database server is used to configure the automatic numbering intelligent algorithm and store cable numbers, while the client is used to call the algorithm and output cable numbers. The numbering system automatically numbers cables based on the cable group's origin and destination cabinets, cable function-driven intelligent algorithms, and rules. This allows a computer program to automatically number cables according to preset rules, fundamentally eliminating the possibility of duplicate, missing, or mismatched numbers, strengthening design collaboration, and significantly improving design efficiency and quality.

[0024] The implementation of the solution includes the following steps: Step S1: Construct multi-dimensional attributes of the cabinet object, including cabinet name, cabinet number, cabinet KKS code, cabinet type, cabinet association interval, cabinet location, etc., and store them in the database; Step S2: Configure the cable coding rule library based on the cabinet's multi-dimensional attributes and cable functions; Step S3: Utilize the cable functions and cabinet attributes, call the algorithm rules to determine one of the two cabinets as the cable starting cabinet, and configure the cable belonging interval according to the starting cabinet's association interval; Step S4: Call the corresponding interval type coding rule based on the cable belonging interval, and traverse the created cable numbers, automatically recommend the next numeric code and serial number within the rule value range, and generate the cable number.

[0025] As a preferred embodiment, step S1: The numbering system constructs multi-dimensional attributes of the cabinet object, including cabinet name, cabinet number, cabinet KKS code, cabinet type, cabinet association interval, cabinet location, etc., and stores them in the database, specifically: In the database, a cabinet object is created using a system code and a serial number, and attributes such as name, number, KKS code, type, association interval, and installation location are assigned to the cabinet object. Among these, the cabinet name, number, and KKS code are project attributes of the cabinet, which are written when the project is created; the system code is a unique internal identifier assigned to the cabinet object by the platform, and its encoding rules are usually related to information such as the cabinet's classification level (F1-F3).

[0026] Cabinet Type Code: Based on a semantic recognition algorithm, the system identifies cabinet names and automatically categorizes cabinets into three levels. Simultaneously, it modifies and supplements the cabinet system code according to the category. The system creates a one-to-one correspondence between cabinet type codes and system codes, thereby obtaining the cabinet type code configuration.

[0027] As a further preferred embodiment, the cabinets are automatically classified into three levels: F1, F2, and F3. F1 includes electrical systems and station service transformer systems; F2 includes monitoring systems, measuring equipment and meters, protection equipment panels, local secondary protection panels, switch cabinets, intelligent auxiliary control system cabinets, station service power distribution systems, UPS systems, battery systems, station service DC power distribution systems, emergency power supplies, etc.; F3 is a further subdivision based on F2, including 56 types such as five-proof, interval monitoring and control, and public monitoring and control.

[0028] As a further preferred embodiment, the cabinet type matching algorithm architecture adopts a semantic recognition model, and its modules are designed as follows: Module 1: Data Preprocessing. The purpose is to standardize the messy original names to prepare for subsequent semantic similarity calculations. This includes text cleaning, keyword standardization, word segmentation, etc.

[0029] Module 2: Training and Matching of Semantic Recognition Model. Based on the dataset of cabinet names labeled with cabinet types from historical projects, a pre-trained language model (such as BERT) is fine-tuned to learn the mapping relationship between cabinet names and cabinet types, establishing a semantic-level cabinet name-type matching model. Matching logic: The pre-processed cabinet names are input into the trained semantic recognition model to obtain the context-aware sentence vectors of the cabinet names. By calculating the similarity between the sentence vectors and the standard sentence vectors of various cabinet types in the model, the cabinet type with the highest matching degree is output.

[0030] As a preferred approach, the priority of rules in the rule base is set according to the order of first definition and first matching: that is, when traversing the rule base, the rules that appear earlier are matched first. Once the name of the cabinet to be classified meets the keyword combination condition of a certain rule, the matching of subsequent rules is immediately terminated, and the cabinet type corresponding to that rule is output.

[0031] Module 3: Semantic Similarity-Based Matching. This module uses models such as BERT to directly obtain context-aware sentence vectors of names.

[0032] As a preferred approach, after obtaining the context-aware sentence vector of the cabinet name based on the BERT model, the cosine similarity algorithm is used to calculate the vector similarity between the cabinet name to be classified and the standard cabinet type name in the rule base. The similarity threshold is set to 0.7 (when the similarity is ≥0.7, it is considered a successful match; when it is below the threshold, the result of the matching in the rule base is output by default).

[0033] The BERT model used was the pre-trained BERT-base-uncased model. During fine-tuning, the parameters of the bottom 6 layers were frozen, and only the top 4 layers and the classification layer were trained. The learning rate for fine-tuning was set to 2e-5, and gradient accumulation (with 4 gradient accumulation steps) was used to adapt to small batch training data. The training data was a dataset of cabinet names that had been labeled with cabinet types in historical projects.

[0034] After completing the cabinet type configuration, modify and supplement the cabinet system codes according to the three cabinet levels. Create a one-to-one correspondence between cabinet type codes and system codes, and configure the cabinet type codes.

[0035] The associated interval of the cabinet refers to the system interval to which the secondary equipment installed in the cabinet belongs. Its attributes include interval type and interval name.

[0036] The installation location of the screen cabinet refers to the room (area) where the screen cabinet is installed. Its attributes include the room (area) number and the characteristics of the room (area) (indoor, outdoor, switch site markings, protection room markings, etc.).

[0037] As a preferred embodiment, step S2: configuring a cable coding rule base based on the multi-dimensional attributes of the cabinet and cable functions, specifically: The numbering system embeds an open cable coding rule library, which designers can configure according to design needs. The rule library divides coding rules into physical bay coding rules and virtual bay coding rules. Physical bay rules are further subdivided into bay type rules for main transformers, circuit breakers, capacitors, main transformer incoming lines, grounding transformers, bus couplers, bus branch lines, lines, busbars, fault recording systems, reactors, station service transformers, and station service transformer circuit breakers. Virtual bay rules are further subdivided into bay type rules for network communication systems, public measurement and control systems, integrated monitoring systems, time synchronization systems, AC / DC integrated power supplies, intelligent substation auxiliary control systems, primary equipment online monitoring systems, relay protection fault information systems, network message analysis systems, power quality monitoring systems, secondary equipment online monitoring, safety automatic devices, and synchronous phasor measurement devices. Simultaneously, general physical bay rules and general virtual bay rules are configured in both physical and virtual bay coding rules, enabling both general and personalized customization of bay rules.

[0038] Among various interval coding rules and general coding rules, cable coding is based on the multi-dimensional attributes of the cabinet and the cable function to form multiple coded concatenation fields: cabinet number, cabinet KKS code, cabinet type code, interval name, location number, location numeric code, cable function type code, and cable function numeric code. Then, necessary serial numbers and connectors are added according to the numbering requirements. The numbering system supports selecting some coding fields as needed and supports adjusting the order of each field, serial number, and connector to maximize the fulfillment of numbering requirements.

[0039] As a further preferred embodiment, the numbering system supports selecting some coding fields for coding as needed. The serial number supplements the numerical segment numbering of the cable number, reflecting the diversity and flexibility of the numbering configuration. Various connector formats are supported, such as "+" and "-". When concatenating codes, the order of each part can be adjusted, such as by using "move up" or "move down" to adjust the order of the selected fields, forming a left-to-right code according to the adjusted top-to-bottom order.

[0040] As a preferred embodiment, step S3: Utilizing cable functionality and cabinet attributes, the algorithm rules are invoked to determine one of the two cabinets as the cable starting cabinet. Simultaneously, the cable assignment interval is configured according to the associated interval of the starting cabinet. Specifically: An algorithmic tool is developed to automatically recommend the starting and ending cabinets for a cable based on its functional description, the types of cabinets on both sides, the associated interval, and location characteristics. It then automatically determines the interval associated with the starting cabinet as the cable's assigned interval. For example, if the cable's function is DC power, and the cabinets on both sides are a line protection cabinet and a DC feeder cabinet respectively, then according to the cable assembly mechanism, the DC feeder cabinet provides DC power to the line protection cabinet. Therefore, the starting cabinet is determined to be the DC feeder cabinet, and the ending cabinet to be the line protection cabinet. The interval to which the cable belongs is determined to be the AC / DC integrated power supply interval associated with the DC feeder cabinet.

[0041] As a further preferred embodiment, the implementation scheme is as follows: A graph neural network model is selected, with display cabinets as nodes and cables as edges. Node features include display cabinet type and location, while edge features include cable function and the area they belong to. The workflow is as follows: (1) Graph construction: Based on a large amount of historical project data (including data accumulated by this digital platform or imported data accumulated by other projects), construct a graph containing all known connection relationships.

[0042] (2) Model training: Train a GNN model to learn the representation of nodes and edges in the graph.

[0043] (3) Prediction: When a new cable (with various characteristics) needs to be connected, the model finds the most likely source node (starting screen cabinet) and target node (ending screen cabinet) in the graph.

[0044] As a preferred embodiment, step S4: The numbering system calls the corresponding interval type coding rule based on the cable belonging interval, and traverses the created cable numbers, automatically recommending the next numeric code and serial number within the rule value range to generate the cable number, specifically: Based on the cable's assigned interval type, an encoding rule is selected. Cable numbers are generated using the encoding fields, serial number, connectors, and their concatenation order selected under this interval encoding rule. For generating the numerical segment of the number, the database of already created cable object numbers is traversed, and the next unused number is recommended. This number must be within the range of values ​​for the numeric code and serial number. Carry coordination is implemented between the numeric code and the serial number.

[0045] As a preferred approach, the algorithm for combining the numerical code and the serial number is as follows: prioritize incrementing the numerical code field (such as the location numerical code, cable function numerical code). When the numerical code field reaches the upper limit of its preset value range, the numerical code field is reset to the minimum value of the value range, and the serial number is incremented by 1. When the serial number reaches the preset upper limit, trigger the carry-in of the higher-level code field (such as the numerical identifier corresponding to the cabinet type code) to ensure that the numbering is continuous and without repetition.

[0046] In this embodiment, the numeric code refers to the numeric field selected in the encoding rules that needs to be sequentially incremented, such as the location numeric code or the cable function numeric code. It, together with the serial number, constitutes the numeric part of the number, and the carry relationship can be set according to the value range.

[0047] This invention enables a computer program to automatically number cables according to preset rules, fundamentally eliminating the possibility of duplicate numbers, missing numbers, and mismatches, strengthening design collaboration, and significantly improving design efficiency and quality.

[0048] The present invention will be further described below with reference to the accompanying drawings and through more specific embodiments.

[0049] refer to Figure 1 In this embodiment, automatic cable numbering is achieved based on the origin and destination cabinets of the cable group, the intelligent algorithm driven by cable function, and rules, including the following steps: Step S1: Construct the multidimensional attributes of the cabinet object, including cabinet name, cabinet number, cabinet KKS code, cabinet type, cabinet association interval, cabinet location, etc., and store them in the database; Step S2: Configure the cable coding rule base based on the multi-dimensional attributes of the cabinet and cable functions; Step S3: Using cable functions and cabinet attributes, call the algorithm rules to determine one of the two cabinets as the cable starting cabinet, and configure the cable belonging interval according to the associated interval of the starting cabinet. Step S4: Based on the cable ownership interval, call the corresponding interval type encoding rule, and traverse the created cable numbers to automatically recommend the next numeric code and serial number in the rule value range to generate the cable number.

[0050] Preferredly, in this embodiment, step S1 creates a cabinet object in the database using a system code plus a serial number, and assigns attributes such as cabinet object name, number, KKS code, type code, association interval, and installation location, such as... Figure 2 As shown. The name, number, and KKS code of the display cabinet are project attributes of the display cabinet, which are entered when the project is created. Preferably, in this embodiment, the cabinet type matching algorithm adopts a semantic recognition model to complete the intelligent matching of cabinet types based on cabinet names in the project; after extracting semantic features and matching types of cabinet names through the semantic recognition model, the cabinets are automatically classified into three levels, F1, F2 and F3, to achieve standardized classification of cabinet types.

[0051] Preferably, in this embodiment, the cabinet type is configured according to industry standard specifications, such as... Figure 3 As shown: F1 includes electrical systems and station service transformer systems; F2 includes monitoring systems, measuring equipment and meters, protection equipment panels, local secondary protection panels, switchgear, intelligent auxiliary control system cabinets, station service power distribution systems, UPS systems, battery systems, station service DC power distribution systems, emergency power supplies, etc.; F3 is a further subdivision of F2, including 56 types such as five-proof, interval measurement and control, and public measurement and control. Simultaneously, the cabinet type rule base also implements a cabinet type code configuration function that corresponds one-to-one with the cabinet system code.

[0052] Preferably, in this embodiment, the automatic association between the cabinet and the interval is realized based on the system interval to which the secondary equipment installed in the cabinet belongs. The interval attributes include interval type and interval name.

[0053] Preferably, in this embodiment, the installation location attributes of the cabinet are designed as follows: Figure 4 As shown, this includes room (area) number and room (area) characteristics (indoor, outdoor, switchyard markings, protective room markings, etc.).

[0054] Preferredly, in this embodiment, step S2: Configure the cable coding rule base based on the multi-dimensional attributes of the cabinet and cable functions, such as... Figures 5-9 As shown.

[0055] The numbering system embeds an open cable coding rule library, which designers can configure according to their design needs. For example, through a graphical configuration interface provided by the client, designers can select coding fields, set connectors, and adjust the order to define coding rules. The rule library divides coding rules into physical interval coding rules and virtual interval coding rules. Physical interval rules are further subdivided into interval type rules such as main transformers, circuit breakers, capacitors, main transformer incoming lines, grounding transformers, bus couplers, bus branch lines, lines, busbars, fault recording systems, reactors, station service transformers, and station service transformer circuit breakers. Virtual interval rules are further subdivided into interval type rules such as network communication systems, public measurement and control systems, integrated monitoring systems, time synchronization systems, AC / DC integrated power supplies, intelligent substation auxiliary control systems, primary equipment online monitoring systems, relay protection fault information systems, network message analysis systems, power quality monitoring systems, secondary equipment online monitoring, safety automatic devices, and synchronous phasor measurement devices. At the same time, general physical interval rules and general virtual interval rules are configured in both physical and virtual interval coding rules, enabling general configuration and personalized customization of interval rules.

[0056] In various interval coding rules and general coding rules, cable coding is based on the multi-dimensional attributes of the cabinet and the cable function to form multiple code concatenation fields: cabinet number, cabinet KKS code, cabinet type code, interval name, location number, location numeric code, cable function type code, and cable function numeric code. Then, according to the numbering, necessary serial numbers and connectors are added, including: Location digital codes are configured according to the characteristics of the room and area where the cable origin and destination switch cabinet is located, such as: from secondary equipment room to switchyard, within secondary equipment room, between different secondary equipment rooms, within the same switchyard, between different switchyards, from switchyard to secondary equipment room, etc.

[0057] The numbering system supports selecting certain coding fields as needed for coding. The serial number supplements the numerical segment numbering of the cable number, reflecting the diversity and flexibility of the numbering configuration. Various connector formats are supported, such as "+" and "-". When concatenating codes, the order of each part can be adjusted, such as by using "move up" or "move down" to adjust the order of selected fields, forming a left-to-right code based on the adjusted top-to-bottom order.

[0058] Preferably, in this embodiment, step S3 involves constructing an algorithm tool that automatically recommends the starting and ending cabinets of the cable based on information such as the cable's functional description, the types of cabinets on both sides, the associated interval, and location characteristics. This automatically determines the interval associated with the starting cabinet as the cable's assigned interval. For example, if the cable's function is DC power, and the cabinet types on both sides are a line protection cabinet and a DC feeder cabinet, then according to the cable assembly mechanism, the DC feeder cabinet provides DC power to the line protection cabinet. Therefore, the starting cabinet is determined to be the DC feeder cabinet, the ending cabinet to be the line protection cabinet, and the interval to which the cable belongs is determined to be the AC / DC integrated power supply interval associated with the DC feeder cabinet.

[0059] Preferably, in this embodiment, the implementation scheme for the algorithm to predict the start and end points of cables is as follows: A graph neural network model is selected, with display cabinets as nodes and cables as edges. Node features include display cabinet type and location, while edge features include cable function and the area they belong to. The workflow is as follows: Graph Construction: Based on a large amount of historical project data, construct a huge graph that contains all known connections.

[0060] Model training: Train a GNN model to learn the representations of nodes and edges in the graph.

[0061] As an example of implementation, the graph neural network model preferably adopts the graph attention network (GAT) architecture, which is suitable for learning the correlation features between the cabinet and the cable. During training, the cross-entropy loss function is selected, the Adam optimizer is used, the learning rate is set to 0.001~0.01, the number of iterations is 100~500 rounds, and the batch size is set to 32~128 according to the amount of historical project data. The termination condition for model training is that the validation set loss does not decrease for 10 consecutive rounds or the maximum number of iterations is reached.

[0062] Prediction: When a new cable (with various characteristics) needs to be connected, the model searches the graph for the most likely source node (starting cabinet) and target node (ending cabinet).

[0063] Preferably, in this embodiment, in step S4, an encoding rule is selected based on the interval type of the cable's assigned interval. Based on the encoding field, serial number, connector, and their concatenation order selected under this interval encoding rule, a cable number is generated. For the generation of the number's numerical segment, the database of already created cable object numbers needs to be traversed, and the next unused number is recommended. This numerical part of the number consists of a serial number and a numerical encoding field, with the serial number and numerical encoding field incrementing according to their value range and incorporating carry-over.

[0064] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.

[0065] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0066] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0067] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

[0068] This invention is not limited to the above-described preferred embodiments. Anyone inspired by this invention can derive other forms of automatic numbering methods for substation secondary cables based on a digital design platform. All equivalent variations and modifications made within the scope of the claims of this invention should be included within the scope of this invention.

Claims

1. A method for automatically numbering secondary cables in substations based on a digital design platform, characterized in that, A method is applied to a digital design platform for substation secondary systems, wherein the platform embeds a system including a database server and a client; the method includes: Based on semantic recognition, the type and type code of the cabinet are obtained. Combined with the cabinet engineering identifier, associated interval and installation location, the multi-dimensional attributes of the cabinet are constructed and stored in the database. Configure a classification coding rule library that includes physical interval coding rules and virtual interval coding rules. The rule library supports the selection of coding field combinations and the configuration of serial numbers and connectors. For the cable to be numbered, obtain its functional description and the multi-dimensional attributes of the cabinets on both sides it is connected to. Analyze the mapping relationship between the cable function and the cabinet attributes through a graph neural network model to determine the starting cabinet of the cable and the interval to which the cable belongs. According to the specified attribution interval, the corresponding encoding rules are invoked, the existing cable numbers in the database are traversed, and a unique cable number is generated by combining the numerical encoding with the serial number.

2. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The cabinet type is obtained through a semantic recognition model, and the working process of the semantic recognition model includes: By studying the screen cabinet names corresponding to the screen cabinet categories in historical projects, a matching relationship between the names of different screen cabinets and the screen cabinet types can be established. Perform data preprocessing on the cabinet names; The context-aware sentence vector of the cabinet name is obtained by semantic recognition model, and the cabinet type is matched to complete the three-level classification of the cabinet. Based on the system codes corresponding to the three-level classification of the cabinets, configure the cabinet type codes required for cable coding in a one-to-one correspondence.

3. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 2, characterized in that: The three-level classification hierarchy includes F1, F2, and F3, where F1 includes electrical systems and station service transformer systems; F2 includes monitoring systems, measuring equipment and meters, protection equipment panels, local secondary protection panels, switch cabinets, intelligent auxiliary control system cabinets, station service power distribution systems, UPS systems, battery systems, station service DC power distribution systems, and emergency power supplies. F3 is further subdivided into multiple functional types based on F2; the semantic recognition model includes a pre-trained language model.

4. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The multi-dimensional attributes of the display cabinet include the display cabinet name, display cabinet number, and display cabinet KKS code, which are written into the database when the project is created; the attributes of the associated interval include the interval type and interval name; the attributes of the installation location include the room or area number and room or area characteristics, and the room or area characteristics include indoor or outdoor, switch site or non-switch site related identifiers; the display cabinet object is created in the database using a system code plus a serial number, and the display cabinet object is assigned the multi-dimensional attributes of the display cabinet.

5. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The classification coding rule base is an open rule base that can be configured according to engineering design requirements; the physical interval coding rule is further subdivided into multiple interval type rules, and the virtual interval coding rule is further subdivided into multiple interval type rules; the physical interval coding rule and the virtual interval coding rule are each configured with general rules, supporting general configuration and personalized custom configuration.

6. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The encoding fields include cabinet number, cabinet KKS code, cabinet type code, interval name, location number, location numeric code, cable function type code, and cable function numeric code. The rule base supports selecting some encoding fields to participate in encoding and supports adjusting the arrangement order of each encoding field, serial number, and connector. The connector includes at least one preset type. The location numeric code is configured according to different associated scenarios of the room or area where the cable to be numbered starts and ends. The cable function numeric code is divided into preset value ranges according to function type.

7. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The graph neural network model uses cabinets as nodes and cables as edges. The node features include cabinet type, installation location, and associated intervals, while the edge features include cable function. The graph neural network model constructs a graph with known connections based on historical project data. By training, it learns the representation of nodes and edges in the graph and finds the corresponding source node as the starting cabinet and the target node as the ending cabinet for the cable to be numbered.

8. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The numerical part of the number consists of a numerical encoding field and a serial number, which are incremented according to a preset value range and carried over. The process of traversing the existing cable numbers in the database specifically involves traversing the existing cable numbers in the database that have the same interval as the cable to be numbered and recommending the next number that is not currently occupied. When the preset upper limit is reached, the number is automatically carried over to a higher-order encoding segment.

9. The automatic numbering method for substation secondary cables based on a digital design platform according to claim 1, characterized in that: The step of determining the starting cabinet and cable allocation interval also includes: performing reasoning based on a pre-configured rule base that describes the correspondence between cable functions and cabinet types.

10. An automatic numbering system for substation secondary cables based on a digital design platform, the system being embedded in a substation secondary digital design platform, including a database server and a client; The database server is used to store the multi-dimensional attributes of the cabinet and the created cable numbers, as well as to deploy a semantic recognition model for automatic classification of the cabinet and a graph neural network model for automatically determining the cable starting cabinet and the belonging interval. The client is used to configure an open rule base and preset cabinet type codes, location numeric codes, cable function type codes, and cable function numeric codes. It is used for cabinet creation, calling the semantic recognition model to automatically classify cabinets; and for cable design, calling the graph neural network model or preset rule base to analyze the mapping relationship between cable functions and cabinet attributes to determine the starting cabinet and belonging interval of the cable. Then, based on the belonging interval, it calls the corresponding coding rules, traverses the existing cable numbers in the database, and generates a unique cable number by combining the numeric code with the serial number and outputs it.

Images