Automatic design method for electrical system of traction substation kiosk based on characteristic value matching
By dividing the electrical system of the traction substation into multi-level modules and defining characteristic values, and using the characteristic value matching method, the problems of low design reuse rate and difficulty in automatic combination in the existing technology are solved, realizing efficient and flexible electrical system design, which is suitable for multi-industry applications.
Patent Information
- Application Number
- CN202511401255.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-28
- Publication Date
- 2026-02-10
AI Technical Summary
Existing technologies lack structured feature value descriptions in the design of electrical systems for traction substations, making it difficult to automatically combine designs across levels, unable to achieve dynamic variant designs, and module library resources cannot learn and grow on their own. This results in low efficiency in local matching and replacement, low design reuse rate, and the inability to achieve top-down recursive generation.
Using an eigenvalue matching method, the electrical system of the traction substation is divided into four levels: substation level, system level, circuit level, and equipment level. Eigenvalues and weights are defined and assigned, and electrical system design documents are automatically generated through similarity calculation and recursive matching.
It improves design reusability and efficiency, achieves high-precision module matching, supports flexible adjustments, and has a continuously growing module library. It is suitable for electrical system design in multiple industries, and combines automation and freedom to enhance the flexibility and accuracy of design.
Smart Images
Figure CN121502985A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of rail transit traction power supply system, and particularly relates to a traction substation pavilion electrical system automation design method based on eigenvalue matching. BACKGROUND
[0002] With the rapid development of railways and urban rail transit, traction substation pavilions (hereinafter referred to as "pavilions") as an important part of the traction power supply system, the number and complexity of the electrical system design of the pavilions are increasing. At present, engineering design units generally use CAD, BIM and other drawing platforms to design the electrical system of the pavilion by calling the pre-established standard library or typical drawing template. Common practices include: 1) standard drawing application: find the pavilion or loop drawing similar to the project requirements in the library, and make parameter substitution and local adjustment. 2) block combination: manually combine CAD blocks (such as circuit breakers, switches, transformers, etc.) into loops or systems. 3) parameterized plug-in: some software introduces simple parameterization functions (such as device model selection, bus type selection), which can achieve a certain degree of automatic generation.
[0003] The existing technology mainly has the following deficiencies in the design of the electrical system of the traction substation pavilion:
[0004] (1) Lack of structured eigenvalue description
[0005] Blocks and templates are usually managed by file name or simple label, lacking a unified and calculable eigenvalue system, and cannot be accurately matched and automatically combined.
[0006] (2) Difficult to automatically combine design across levels
[0007] Existing systems are generated in units of single loops or single systems, and cannot recursively generate multi-level combined designs of "pavilion-system-loop-device" from top to bottom.
[0008] (3) Cannot realize dynamic variant design
[0009] When the project requirements differ greatly from the standard library (such as changes in the number of feeders), manual modification of the drawings is required, and there is a lack of ability to automatically expand or reduce modules.
[0010] (4) Library resources cannot be self-learning and growing
[0011] (5) The completed drawings are usually not recorded back into the system as matchable modules, resulting in fixed library resources that are difficult to accumulate and deposit the design assets of the enterprise.
[0012] (6) Low efficiency of local matching and replacement
[0013] In existing technologies, if the selected template does not match the requirements, designers need to manually replace the sub-modules, lacking a mechanism for automatically locating differences and recursively replacing them. Summary of the Invention
[0014] This invention provides an automated design method for the electrical system of traction substations based on eigenvalue matching, in order to solve the above-mentioned technical problems existing in the design of electrical systems for traction substations.
[0015] According to a first aspect, one embodiment provides an automated design method for the electrical system of a traction substation based on eigenvalue matching, the method comprising:
[0016] The electrical system of the traction substation is divided into structured hierarchical modules;
[0017] Define feature values and assign weights to modules at each level, and establish a module feature value database;
[0018] Based on the project design requirements, generate a set of design target feature values for each level of target module;
[0019] Based on the design target feature value set of each level of target module, the candidate module list of each level of target module is obtained by similarity calculation in the module feature value database, and the final matching result is obtained by selecting from the candidate module list;
[0020] By combining the final selected modules at each level, the electrical system design outcome document is automatically generated.
[0021] Furthermore, the electrical system of the traction substation is divided into structured hierarchical modules, specifically including:
[0022] The electrical system of the traction substation is divided into four levels of modules according to the tree structure: substation level, system level, circuit level, and equipment level. The substation level module is the root node, the system level module and the circuit level module are intermediate nodes, the equipment level module is the leaf node, and the equipment level module is the smallest design unit.
[0023] Furthermore, feature values are defined and weights are assigned to each level of module, and a module feature value database is established, specifically including:
[0024] According to the design technical standards, the characteristic values and weights of each type of module are defined, including: pavilion-level characteristic values, system-level characteristic values, loop-level characteristic values, and equipment-level characteristic values; the weights are set manually or adjusted based on historical data.
[0025] Furthermore, based on the project design requirements, a set of design target feature values for each level of target module is generated, specifically including:
[0026] Based on the input project design technical standards and principles, a set of target feature values for each level of module is generated.
[0027] Furthermore, based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is then selected based on the candidate module list, specifically including:
[0028] Matching of modules at each level is performed from top to bottom according to the hierarchical structure;
[0029] The design target feature value of the target module is matched with each feature value of the candidate module. Based on the matching results, the comprehensive similarity with each module in the module feature value database is calculated, and a candidate module list is generated from high to low according to the calculated comprehensive similarity.
[0030] Furthermore, based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is then selected based on the candidate module list. Specifically, this also includes:
[0031] Label the set of mismatched feature values for each candidate module;
[0032] If there are mismatched feature values, the corresponding mismatched sub-module is located and a recursive matching and replacement process is entered: the same rules are recursively applied until all level modules reach the set similarity threshold or the difference is manually confirmed to be acceptable.
[0033] Based on the CAD drawing preview function of the candidate module, designers can manually select from the sorting results, the set of mismatched feature values, and the drawing preview to obtain the final matching result.
[0034] Furthermore, the design target feature values of the target module are matched with each feature value of the candidate modules, and the comprehensive similarity with each module in the module feature value database is calculated based on the matching results. Specifically, this includes:
[0035] Each feature value of the target module is matched against that of the candidate module, and a complete match is denoted as the matching flag m. i =1, mismatch is denoted as m i =0;
[0036] Calculate the overall similarity:
[0037]
[0038] Where: S is the overall similarity; n is the total number of feature values of the module; w i The weights are dynamically adjusted based on technical standards, business priorities, or historical experience.
[0039] Furthermore, based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is then selected based on the candidate module list. Specifically, this also includes:
[0040] If the candidate module list is empty or all candidate modules do not meet the requirements, the initial creation mechanism is triggered:
[0041] Based on the input technical standards and parameters, a tree topology structure of the corresponding hierarchical modules is generated;
[0042] Perform a search on each sub-module in the topology: if a candidate module exists, proceed to the similarity ranking and manual selection process; if no match is found, continue to create a new module.
[0043] The corresponding process is executed recursively from top to bottom until all leaf nodes, i.e., device-level modules, are generated.
[0044] For device-level modules, which are the smallest design units, their feature values and graphics need to be predefined in the module feature value database. There is no need to use a new creation mechanism. Device-level modules are gradually combined into higher-level graphics through reverse recursive combination.
[0045] Furthermore, the method also includes:
[0046] The design deliverables, along with all modules used in this project, their feature sets, mismatch records, and weight information, will be stored in the database.
[0047] According to a second aspect, one embodiment provides an automated design device for the electrical system of a traction substation based on eigenvalue matching, the device comprising:
[0048] The hierarchical division module is used to divide the electrical system of the traction substation into structured hierarchical modules;
[0049] The feature value definition module is used to define feature values and assign weights to modules at each level, and to establish a feature value database for the modules.
[0050] The target feature value generation module is used to generate a set of design target feature values for each level of target module according to the project design requirements.
[0051] The retrieval and matching module is used to design target feature value sets based on target modules at each level. It obtains a list of candidate modules for each level of target modules by calculating similarity from top to bottom according to the hierarchical structure in the module feature value database, and selects the final matching result based on the candidate module list.
[0052] The design outcome generation module is used to combine the matching results of the finally selected modules at each level and automatically generate electrical system design outcome documents.
[0053] According to a third aspect, one embodiment provides an electronic device, the device comprising: a processor and a memory;
[0054] The memory is used to store one or more program instructions;
[0055] The processor is configured to run one or more program instructions to perform the steps of an eigenvalue matching-based automated design method for traction substation electrical systems as described in any of the preceding claims.
[0056] According to a fourth aspect, one embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of an automated design method for an electrical system of a traction substation based on eigenvalue matching as described in any of the preceding claims.
[0057] This invention provides an automated design method for the electrical system of traction substations based on eigenvalue matching, which has the following advantages:
[0058] 1. Improve design reuse rate and efficiency
[0059] By establishing a module hierarchy at the pavilion, system, loop, and equipment levels, and defining feature values and weights for each type of module, feature-value-based module retrieval and combination are achieved, enabling the accurate reuse of existing design results. As the module library expands, the efficiency of subsequent design matching is significantly improved, reducing repetitive work.
[0060] 2. Achieve high-precision module matching and rigorous manual selection.
[0061] By employing a comprehensive approach that combines similarity calculation, similarity ranking, and mismatch feature value set annotation, along with CAD graphic preview functionality, designers can manually select the most suitable solution from candidate modules. This ensures the rigor and accuracy of engineering design and avoids the error risks associated with purely automatic generation.
[0062] 3. Recursive positioning and replacement enhance flexibility.
[0063] During the matching process, when there are mismatched feature values in the top-level module, the corresponding sub-module can be automatically located and the matching and replacement can be performed recursively. This allows only the mismatched parts to be replaced while maintaining the overall design framework, reducing the overall amount of modification and improving the flexibility of the solution.
[0064] 4. Supports expansion to multiple industries
[0065] This method is not only applicable to the design of rail transit traction power supply systems, but also to electrical systems or modular engineering designs in other industries. It can be quickly migrated and applied simply by adjusting the characteristic value types and value ranges of each level of module, making it highly versatile.
[0066] 5. The module library continues to grow organically.
[0067] After each design result is generated, the system will store each level of modules, along with the feature value set, weight, mismatch records, and associated graphs, into the database. This allows the module library to continuously expand during use, forming a positive feedback mechanism, and the design efficiency and reusability will naturally improve over time.
[0068] 6. A combination of greater automation and freedom
[0069] Unlike the traditional method of applying standard drawings, this invention combines modular standardization with free combination. It can flexibly adjust the number and structure of modules based on automated generation. For example, when the number of feeders changes, the module layout can be automatically adjusted to generate new drawings, achieving a high degree of design freedom. Attached Figure Description
[0070] Figure 1 A flowchart illustrating an automated design method for the electrical system of a traction substation based on eigenvalue matching, provided as an embodiment of the present invention;
[0071] Figure 2 An overall architecture diagram of an automated design method for the electrical system of a traction substation based on eigenvalue matching, provided as an embodiment of the present invention;
[0072] Figure 3 A schematic diagram of the module hierarchy architecture in an automated design method for the electrical system of a traction substation based on eigenvalue matching, provided as an embodiment of the present invention;
[0073] Figure 4 A schematic diagram illustrating the definition and weight setting of eigenvalues in an automated design method for the electrical system of a traction substation based on eigenvalue matching, provided in an embodiment of the present invention.
[0074] Figure 5 The flowchart of retrieval and matching in an automated design method for the electrical system of a traction substation based on feature value matching provided in one embodiment of the present invention includes comprehensive similarity calculation, sorting, manual selection, recursive replacement, and recursive creation.
[0075] Figure 6 This is a schematic diagram of the module matching result interface (feature value set and graphic preview function) in an automated design method for the electrical system of a traction substation based on feature value matching, provided as an embodiment of the present invention. Detailed Implementation
[0076] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.
[0077] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.
[0078] The first embodiment of this invention provides an automated design method for the electrical system of a traction substation based on eigenvalue matching. The following is in conjunction with... Figure 1 and Figure 2 Please provide a detailed explanation.
[0079] like Figure 1 As shown, in step S100, the electrical system of the traction substation is divided into structured hierarchical modules.
[0080] The above steps specifically include:
[0081] S110 divides the electrical system into at least four levels of modules, including the station level, system level, circuit level, and equipment level. Each level of module can be defined, combined, and reused independently.
[0082] Specifically, in this embodiment, the overall structure of the traction substation adopts a tree structure to represent the hierarchical relationship of each level of modules (e.g., Figure 3 As shown), where:
[0083] The root node is the pavilion-level module;
[0084] Intermediate nodes are system-level modules and loop-level modules;
[0085] Leaf nodes are device-level modules, and device-level modules are the smallest design units.
[0086] (1) Substation level: Describe the overall configuration of the substation (high voltage side connection type, number of feeders, main transformer model, etc.).
[0087] (2) System level: including high voltage system, traction transformer system, traction system, etc.
[0088] (3) Circuit level: various functional circuits (feeder circuit, bus tie circuit, transformer circuit, etc.).
[0089] (4) Equipment level: Basic equipment such as circuit breakers, disconnect switches, and transformers.
[0090] like Figure 1 As shown, in step S200, feature values are defined and weights are assigned to each level of module, and a module feature value database is established.
[0091] The above steps specifically include:
[0092] For each type of module, define the feature value type, value range, and weight value (weight range 0.1 to 1.0). The weight is used to characterize the importance of the feature value in the similarity calculation. Examples of feature values include: wiring type, rated voltage, number of feeders, main transformer model, etc.
[0093] In this embodiment, characteristic value types and value ranges are established for each level of the electrical system module, including but not limited to, but preferably including: pavilion-level characteristic values (such as high-voltage side wiring type, number of feeders, voltage level, etc.), system-level characteristic values (such as main wiring scheme, backup mode), circuit-level characteristic values (such as circuit purpose, rated current), and equipment-level characteristic values (such as equipment model, rated capacity, installation method).
[0094] Feature value definition and weight allocation for each level of module, such as Figure 4 As shown, the details are as follows:
[0095] (1) The feature value type, value range and weight of each type of module shall be determined by the project leader according to the design technical standards;
[0096] (2) Example of characteristic values: wiring type (single busbar segment = 1, double busbar = 2), rated voltage (kV value), number of feeders (integer), etc.;
[0097] (3) Weight settings can be manually entered or adjusted by the system based on historical data.
[0098] In this embodiment, the weights can be manually set by the project leader, automatically calculated and generated by the system based on historical design data, or dynamically adjusted through expert systems and data mining methods, thereby improving matching accuracy and adaptability.
[0099] like Figure 1As shown, in step S300, a set of design target feature values for each level of target module is generated according to the project design requirements.
[0100] The above steps specifically include:
[0101] Generate target feature value set: The project leader inputs the project's design technical standards and principles, and the system generates target feature value sets for each level of module based on these standards.
[0102] like Figure 1 As shown, in step S400, based on the design target feature value set of each level target module, a candidate module list of each level target module is obtained from the module feature value database through similarity calculation, and the final matching result is obtained based on the candidate module list.
[0103] The above steps specifically include:
[0104] In this embodiment, the feature value matching and manual selection process is performed from top to bottom, such as... Figure 5 As shown, the details are as follows:
[0105] 1) Input technical standards and design parameters: The project leader or designer inputs the set of design technical standards and parameters for the pavilion level;
[0106] 2) For each feature value of the target module and the candidate module, a matching judgment is performed, and a complete match is denoted as the matching flag m. i =1, mismatch is denoted as m i =0;
[0107] 3) Calculate the overall similarity starting from the institute level:
[0108]
[0109] Where: S is the overall similarity, with a value range of [0,1]; n is the total number of feature values for this module; and the weight w is... i It can be dynamically adjusted based on technical standards, business priorities, or historical experience;
[0110] In this embodiment, in the comprehensive similarity calculation, in addition to the weighted matching method, cosine similarity, Euclidean distance, fuzzy matching, machine learning classification model and other methods can also be used to achieve module matching. As long as the similarity can be calculated based on feature values and sorted, the same module filtering effect can be achieved.
[0111] 4) Generate a list of candidate modules in descending order of similarity, and label each candidate module with a set of mismatched feature values;
[0112] 5) The system provides a CAD drawing preview function for candidate modules, such as... Figure 6As shown, designers manually select based on the sorting results, the set of mismatched feature values, and the graphic preview to ensure the rigor of the project.
[0113] In this embodiment, the CAD graphic preview can be replaced by various display methods such as 3D visualization, BIM model preview, and simplified schematic diagram; the presentation of mismatched feature value sets can also adopt methods such as highlighting and comparison tables, which makes it convenient for designers to make quick judgments.
[0114] 6) Designers manually select from the candidate results to ensure the rigor of the design;
[0115] 7) If there are mismatched feature values, locate the corresponding submodule and proceed with recursive matching and replacement.
[0116] The recursive matching and replacement is as follows:
[0117] a. Repeat the above matching steps at the system level, loop level, and device level;
[0118] b. Supports locking some modules to avoid unnecessary replacements;
[0119] c. The recursion ends when all modules meet the set similarity or complete match.
[0120] In this embodiment, the recursive process can be adjusted according to different project requirements. For example, different levels of similarity thresholds can be set, parallel replacement of some modules can be supported, or users can lock modules that do not need to be replaced in batches before recursion to improve replacement efficiency.
[0121] 8) If the candidate list is empty or all candidate modules do not meet the requirements, the system triggers the initial creation mechanism (applicable to modules at all levels except the device level):
[0122] a. Generate the tree topology structure of this level of module based on the input technical standards and parameters;
[0123] b. Perform a search on each sub-module in the topology: if a candidate module exists, proceed to the similarity ranking and manual selection process; if no match is found, continue to create a new module.
[0124] c. This process is executed recursively from top to bottom until all leaf nodes (device-level modules) are generated;
[0125] Among them, the device-level module, as the basic unit, needs to predefine its feature values and graphics in the module feature value database. Instead of using a new creation mechanism, the device-level modules are gradually combined into higher-level graphics through reverse recursion.
[0126] like Figure 1 As shown, in step S500, the matching results of the finally selected modules at each level are combined to automatically generate the electrical system design outcome document.
[0127] In this embodiment, the final selected modules at each level are combined to automatically generate electrical system design output documents such as main wiring diagrams and general layout diagrams.
[0128] like Figure 1 As shown, in step S600, the design result file, along with all modules used in this project and their feature value sets, mismatch records, and weight information, are stored in the database.
[0129] Specifically, the system will generate CAD drawings, bill of materials, and other design deliverables from the final combined modules; at the same time, it will store all modules used in this process, along with their feature value sets, mismatch records, and weight information, into the database; the database storage structure can be JSON, XML, or relational tables.
[0130] In this embodiment, the modules and their feature values can be stored in relational databases, NoSQL databases, graph databases, or cloud-based distributed storage systems; the stored data structures can include various forms such as JSON, XML, and relational tables to meet different scale and access performance requirements.
[0131] Furthermore, automatic expansion modules (such as adjusting the number of feeders) can be achieved through parametric drawing, template insertion, rule derivation, and BIM modular generation. As long as new module combinations can be generated based on existing modules, the same effect can be obtained.
[0132] Corresponding to the aforementioned eigenvalue matching-based automated design method for traction substation electrical systems, this invention also discloses an eigenvalue matching-based automated design device for traction substation electrical systems, which specifically includes:
[0133] The hierarchical division module is used to divide the electrical system of the traction substation into structured hierarchical modules;
[0134] The feature value definition module is used to define feature values and assign weights to modules at each level, and to establish a feature value database for the modules.
[0135] The target feature value generation module is used to generate a set of design target feature values for each level of target module according to the project design requirements.
[0136] The retrieval and matching module is used to design target feature value sets based on target modules at each level. It obtains a list of candidate modules for each level of target modules by calculating similarity from top to bottom according to the hierarchical structure in the module feature value database, and selects the final matching result based on the candidate module list.
[0137] The design outcome generation module is used to combine the matching results of the finally selected modules at each level and automatically generate electrical system design outcome documents.
[0138] It should be noted that for a detailed description of the automated design device for the electrical system of a traction substation based on eigenvalue matching provided in the embodiments of the present invention, please refer to the relevant description of the automated design method for the electrical system of a traction substation based on eigenvalue matching provided in the embodiments of the present invention, which will not be repeated here.
[0139] In addition, embodiments of the present invention also provide an electronic device, the device comprising: a processor and a memory; the memory for storing one or more program instructions; the processor for executing one or more program instructions to perform the steps of an automated design method for an electrical system of a traction substation based on feature value matching as described in any of the preceding embodiments.
[0140] It should be noted that for a detailed description of an electronic device provided in the embodiments of the present invention, please refer to the relevant description of an automated design method for the electrical system of a traction substation based on feature value matching provided in the embodiments of this application, which will not be repeated here.
[0141] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the eigenvalue matching-based automated design method for the electrical system of a traction substation as described in any of the preceding claims.
[0142] It should be noted that for a detailed description of a computer-readable storage medium provided in the embodiments of the present invention, please refer to the relevant description of a vibration inversion enhancement method based on singular value adaptive regularization provided in the embodiments of this application, which will not be repeated here.
[0143] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.
[0144] The above examples illustrate the present invention only to aid in understanding it and are not intended to limit the scope of the invention. Those skilled in the art can make various simple deductions, modifications, or substitutions based on the principles of this invention.
Claims
1. An automated design method for the electrical system of a traction substation based on eigenvalue matching, characterized in that, The method includes: The electrical system of the traction substation is divided into structured hierarchical modules; Define feature values and assign weights to modules at each level, and establish a module feature value database; Based on the project design requirements, generate a set of design target feature values for each level of target module; Based on the design target feature value set of each level of target module, the candidate module list of each level of target module is obtained by similarity calculation in the module feature value database, and the final matching result is obtained by selecting from the candidate module list; By combining the final selected modules at each level, the electrical system design outcome document is automatically generated.
2. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 1, characterized in that, The electrical system of the traction substation is divided into structured hierarchical modules, specifically including: The electrical system of the traction substation is divided into four levels of modules according to the tree structure: substation level, system level, circuit level, and equipment level. The substation level module is the root node, the system level module and the circuit level module are intermediate nodes, the equipment level module is the leaf node, and the equipment level module is the smallest design unit.
3. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 2, characterized in that, Define feature values and assign weights for each level of module, and establish a module feature value database, specifically including: According to the design technical standards, the characteristic values and weights of each type of module are defined, including: pavilion-level characteristic values, system-level characteristic values, loop-level characteristic values, and equipment-level characteristic values; the weights are set manually or adjusted based on historical data.
4. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 1, characterized in that, Based on the project design requirements, generate a set of design target feature values for each level of target module, specifically including: Based on the input project design technical standards and principles, a set of target feature values for each level of module is generated.
5. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 1, characterized in that, Based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is then selected based on the candidate module list, specifically including: Matching of modules at each level is performed from top to bottom according to the hierarchical structure; The design target feature value of the target module is matched with each feature value of the candidate module. Based on the matching results, the comprehensive similarity with each module in the module feature value database is calculated, and a candidate module list is generated from high to low according to the calculated comprehensive similarity.
6. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 5, characterized in that, Based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is obtained based on the candidate module list. Specifically, it also includes: Label the set of mismatched feature values for each candidate module; If there are mismatched feature values, the corresponding mismatched sub-module is located and a recursive matching and replacement process is entered: the same rules are recursively applied until all level modules reach the set similarity threshold or the difference is manually confirmed to be acceptable. Based on the CAD drawing preview function of the candidate module, designers can manually select from the sorting results, the set of mismatched feature values, and the drawing preview to obtain the final matching result.
7. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 5, characterized in that, The design target feature value of the target module is matched with each feature value of the candidate module, and the comprehensive similarity with each module in the module feature value database is calculated based on the matching results. Specifically, this includes: Each feature value of the target module is matched against that of the candidate module, and a complete match is denoted as the matching flag m. i =1, mismatch is denoted as m i =0; Calculate the overall similarity: Where: S is the overall similarity; n is the total number of feature values of the module; w i The weights are dynamically adjusted based on technical standards, business priorities, or historical experience.
8. The automated design method for the electrical system of a traction substation based on eigenvalue matching as described in claim 1, characterized in that, Based on the design target feature value set of each level of target module, a candidate module list for each level of target module is obtained through similarity calculation in the module feature value database. The final matching result is obtained based on the candidate module list. Specifically, it also includes: If the candidate module list is empty or all candidate modules do not meet the requirements, the initial creation mechanism is triggered: Based on the input technical standards and parameters, a tree topology structure of the corresponding hierarchical modules is generated; Perform a search on each sub-module in the topology: if a candidate module exists, proceed to the similarity ranking and manual selection process; if no match is found, continue to create a new module. The corresponding process is executed recursively from top to bottom until all leaf nodes, i.e., device-level modules, are generated. For device-level modules, which are the smallest design units, their feature values and graphics need to be predefined in the module feature value database. There is no need to use a new creation mechanism. Device-level modules are gradually combined into higher-level graphics through reverse recursive combination.
9. An automated design device for the electrical system of a traction substation based on eigenvalue matching, characterized in that, The device includes: The hierarchical division module is used to divide the electrical system of the traction substation into structured hierarchical modules; The feature value definition module is used to define feature values and assign weights to modules at each level, and to establish a feature value database for the modules. The target feature value generation module is used to generate a set of design target feature values for each level of target module according to the project design requirements. The retrieval and matching module is used to design target feature value sets based on target modules at each level. It obtains a list of candidate modules for each level of target modules by calculating similarity from top to bottom according to the hierarchical structure in the module feature value database, and selects the final matching result based on the candidate module list. The design outcome generation module is used to combine the matching results of the finally selected modules at each level and automatically generate electrical system design outcome documents.
10. An electronic device, characterized in that, The device includes: a processor and a memory; The memory is used to store one or more program instructions; The processor is configured to run one or more program instructions to perform the steps of the eigenvalue matching-based automated design method for traction substation electrical systems as described in any one of claims 1 to 8.