Oil-immersed transformer design method and device based on data driving and storage medium

Abstract

The invention discloses an oil-immersed transformer design method and device based on data driving and a storage medium, and belongs to the technical field of transformers. According to the invention, an efficient solution is provided in the design of the oil-immersed transformer, and the design efficiency and quality are remarkably improved. By constructing a historical design data system and classifying and coding design indexes, the management and use efficiency of design data is optimized; through linkage of the design rule system and the calculation template library, the design process is standardized, and the design accuracy is improved; through a comprehensive evaluation method, the suitability of new product design and historical data is ensured; function expansion and flexible application are realized through a modular design device; the system and the template library are dynamically adjusted through feedback data, and iterative optimization of the design process is achieved. The method can effectively solve the problems of low efficiency and error proneness in the existing transformer design, and provides important support for stable operation of a power system.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of transformer technology, and in particular to a data-driven oil-immersed transformer design method, device, and storage medium. Background Art

[0002] Oil-immersed power transformers play an important role in the power system, mainly responsible for the transmission and conversion of energy. Their stable and reliable operation is a key factor in the safe operation of the power system. However, there are the following problems in the existing transformer design process.

[0003] Designers have insufficient understanding of transformer design principles; insufficient design experience; and the design process requires a lot of time to check and calculate production details one by one, which can easily lead to errors and waste of resources.

[0004] Therefore, there is an urgent need for an efficient data-driven design method that integrates historical data, design principles and intelligent optimization algorithms to help designers complete transformer design quickly and accurately, thereby improving design efficiency and product quality. Summary of the invention

[0005] The embodiment of the present application provides a data-driven oil-immersed transformer design method, device and storage medium, which significantly improves the efficiency and quality of transformer design by establishing a design data and principle database and comprehensively utilizing historical experience data and intelligent optimization algorithms. The technical solution is as follows:

[0006] On the one hand, a data-driven oil-immersed transformer design method is provided, the method comprising:

[0007] By acquiring and organizing the historical design data of oil-immersed power transformers, a historical design data system is established to support the design;

[0008] Establish a design rule system and parameter calculation template library based on national grid standards and historical design data;

[0009] According to the design parameters of the new product, a matching design template is selected in combination with the design rule system and the calculation template library;

[0010] Generate the bill of materials (BOM) and related design data for the new product based on the selected design template;

[0011] By obtaining production feedback data, the historical design data system, design rule system and calculation template library are updated.

[0012] Optionally, the acquiring and collating of historical design data of the oil-immersed power transformer to establish a historical design data system for supporting the design includes:

[0013] Acquire historical design data of an oil-immersed power transformer, the data including component data of a coil, a core, a lead wire, an insulation assembly, an oil tank, and a coupling;

[0014] Classifying the historical design data according to voltage levels, wherein the voltage levels include 35 kV, 110 kV, 220 kV and 500 kV;

[0015] The design indicators of the components are extracted, and the design indicators are encoded according to preset rules and stored in the historical design data system.

[0016] Optionally, the encoding includes the following rules:

[0017] The design index of the coil is coded in numerical form, and the code consists of voltage level, winding method, number of turns and wire gauge;

[0018] The design indexes of the core are coded in layers, and the coding includes core column width, window size, and core diameter parameters;

[0019] Bill of Materials (BOM) data is incrementally coded, with the codes assigned based on component priority and historical frequency of use.

[0020] Optionally, the establishment of a design rule system and a parameter calculation template library according to the national grid standards and historical design data includes:

[0021] According to the design standards of the national grid and the requirements of the regional grid, a design rule system for oil-immersed power transformers is established, wherein the design rules include coil arrangement rules, iron core number calculation rules and bill of materials generation rules;

[0022] Based on the historical design data, a parameter calculation template library is constructed, wherein the template library includes a coil calculation template, an iron core calculation template, and a bill of materials calculation template;

[0023] Define the association rules between the design rule system and the calculation template library, and realize the linkage between the two through matching logic.

[0024] Optionally, selecting a matching design template based on the design parameters of the new product in combination with the design rule system and the calculation template library includes:

[0025] Input the design parameters of the new product, including capacity, voltage level, winding method, core size and insulation set parameters;

[0026] Call the design rule system to match the input design parameters with the historical design data and generate a matching score;

[0027] According to the matching score, a historical design template that meets the design requirements is selected from the calculation template library.

[0028] Optionally, the compatibility assessment includes the following process:

[0029] Constructing a discriminant matrix A for comparing design parameters with historical design data, wherein the discriminant matrix A is composed of differences between design indicators of historical design templates and design parameters of new products;

[0030] Calculate the consistency ratio for matching score based on the discriminant matrix A in,

[0031] C I =(λ max -N F ) / (N F -1) is the consistency index,

[0032] is the maximum eigenvalue of the discriminant matrix A,

[0033] ω is the weight column vector, ω m is the weight of the m-th data indicator, (A ω ) m is the product of the m-th data indicator discriminant matrix A and the weight column vector ω, is the random consistency index obtained from the standard, N F is the total number of influencing indicators of the i-th category indicator, a ij Represents data a i For data a j The importance of a mj Represents data a m For data a j The importance of , 0<i≤N F , 0<m≤N F , 0<j≤N F .

[0034] Optionally, the generating of a bill of materials (BOM) and related design data of a new product based on the selected design template includes:

[0035] Calling the calculation template library to generate a bill of materials (BOM) for a new product based on the selected historical design template and the input design parameters;

[0036] Link the bill of materials with the design rule system to generate design data for new products and store it in the historical design data system.

[0037] Optionally, the updating of the historical design data system, the design rule system and the calculation template library by acquiring the production feedback data includes:

[0038] Obtaining feedback data about the oil-immersed transformer from the production process, the feedback data including design adjustment information, material usage data and process improvement data;

[0039] Adjust the contents of the historical design data system, design rule system and calculation template library based on the feedback data;

[0040] According to the adjusted data, the association rules between the design rule system and the calculation template library are updated, and the updated results are applied to subsequent designs.

[0041] On the other hand, a data-driven oil-immersed transformer design device is provided, the device comprising:

[0042] A historical design data system building module is used to establish a historical design data system for supporting design by acquiring and organizing historical design data of oil-immersed power transformers;

[0043] Design rule and calculation template establishment module, used to establish a design rule system and parameter calculation template library based on national grid standards and historical design data;

[0044] A template-based design selection module is used to select a matching design template based on the design parameters of the new product in combination with the design rule system and the calculation template library;

[0045] Generate design output module, used to generate bill of materials (BOM) and related design data of new products based on the selected design template;

[0046] The data update module is used to update the historical design data system, design rule system and calculation template library by obtaining production feedback data.

[0047] On the other hand, a server is provided, comprising a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the data-driven oil-immersed transformer design method as described in the above aspect.

[0048] On the other hand, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is used to be executed by a processor to implement the data-driven oil-immersed transformer design method as described in the above aspects.

[0049] On the other hand, a computer program product is also provided, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the data-driven oil-immersed transformer design method described in the above aspect.

[0050] The technical effects brought about by this application are at least as follows.

[0051] This patent provides an efficient solution in the design of oil-immersed transformers through data-driven methods, devices and computer-readable storage media, which significantly improves the design efficiency and quality. By constructing a historical design data system, classifying and coding design indicators, the management and use efficiency of design data are optimized; by linking the design rule system with the calculation template library, the design process is standardized and the design accuracy is improved; through a comprehensive evaluation method, the compatibility of new product design with historical data is ensured; through modular design devices, functional expansion and flexible application are achieved; through feedback data, the dynamic adjustment system and template library are used to achieve iterative optimization of the design process. It can effectively solve the problems of low efficiency and easy errors in existing transformer design, and provide important support for the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of a data-driven oil-immersed transformer design method is shown;

[0053] Figure 2 A flow chart of data-driven oil-immersed transformer design is shown;

[0054] Figure 3 The comprehensive evaluation score calculation process is shown;

[0055] Figure 4 A calculation template iteration flow chart is shown. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0057] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0058] Example 1

[0059] Please refer to Figure 1 , which shows a flow chart of a data-driven oil-immersed transformer design method provided by an exemplary embodiment of the present application. The method includes:

[0060] Step 101, by acquiring and organizing the historical design data of the oil-immersed power transformer, a historical design data system for supporting the design is established.

[0061] In a possible implementation, step 101 includes the following content.

[0062] Step S11, obtaining historical design data of the oil-immersed power transformer, wherein the data includes component data of the coil, the core, the lead wire, the insulation assembly, the oil tank and the coupling.

[0063] Step S12, classifying the historical design data according to voltage levels, wherein the voltage levels include 35 kV, 110 kV, 220 kV and 500 kV.

[0064] Step S13, extracting the design indicators of the components, encoding the design indicators according to preset rules, and storing them in the historical design data system.

[0065] However, the type of data can be adjusted and expanded according to the actual collection. In one example, the data of the same voltage level are obtained, including capacity, connection group, voltage combination and region; the coil data include the number of gears, winding method, number of parallel windings, total number of sections, total number of turns and wire gauge, the core data include core diameter, window height and window width, the insulation set data include gear, window width and high-voltage middle outlet method, the oil tank data include length, width and height, load switch, radiator connection method and tank edge connection structure, the lead data include load switch model, bushing model, connection group, and the core clamp and oil tank size data are obtained at the same time, the gas pipe data include oil storage cabinet, CT parameters, load switch and oil tank size. In the embodiment of the present application, these data are called indicators. Further, the indicators can also be coded with numbers 1-9, indicating that the important indicators of the components do not exceed 9, which together constitute the oil-immersed transformer indicator system.

[0066] Among them, the encoding includes the following rules.

[0067] Numerical coding is used for the design indicators of the coil, and the coding consists of voltage level, winding method, number of turns and wire gauge; hierarchical coding is used for the design indicators of the core, and the coding includes core column width, window size, and core diameter parameters; incremental coding is used for the bill of materials (BOM) data, and the incremental coding is allocated based on component priority and historical usage frequency.

[0068] Step 102, establishing a design rule system and parameter calculation template library according to the national grid standards and historical design data.

[0069] In a possible implementation, step 102 includes the following content.

[0070] Step S21, establishing a design rule system for oil-immersed power transformers according to the national grid design standards and regional grid requirements, wherein the design rules include coil arrangement rules, core sheet number calculation rules, and bill of materials generation rules;

[0071] Step S22, constructing a parameter calculation template library based on historical design data, wherein the template library includes a coil calculation template, a core calculation template, and a bill of materials calculation template;

[0072] Step S23, defining the association rules between the design rule system and the calculation template library, and realizing the linkage between the two through matching logic.

[0073] In one example, four voltage level component design principles are compiled. Taking conventional coil design as an example, the important principles include: the coil is designed from inside to outside according to high-medium impedance, high-low impedance and medium-low impedance. The common coil arrangement of 35kv and 110kv is low-high-adjustment, and the 220kv coil arrangement is low-medium-high-adjustment or stable-low-medium-high-adjustment. For single-phase autocoupled 500kv transformers, the coil arrangement is low-adjustment-medium-high; for coils of the same voltage level and different capacities, continuous, spiral and cylindrical winding methods are designed, and the winding direction, incoming line position, turn insulation, reactance height, line segment arrangement and oil channel distribution of each winding method are designed in different ways.

[0074] In one example, calculation templates for components of four voltage levels are compiled. The coil template mainly calculates the clamping force, the insulation compression height of the pad, the length and weight of the wire, etc., which can be standardized using EXCEL formulas. The coil plane expansion diagram uses the CAD secondary development program to input the coil data to achieve automatic drawing, and the data can be adjusted again until the expansion diagram meets the design principles; the parameters of the iron core sheet calculation template include the side column sheet width, the upper and lower yoke sheet width, the core column sheet width, and the coil center distance. The number of sheets per level is automatically calculated using EXCEL formulas, and the number of main-level sheets is optimized by increasing 2-6 sheets to ensure that the number of upper and lower yoke sheets per level is twice the number of side yoke sheets and four times the number of core column sheets.

[0075] Step 103 , selecting a matching design template according to the design parameters of the new product in combination with the design rule system and the calculation template library.

[0076] In this step, a comprehensive evaluation method is used to select the optimal template. First, determine whether the new product data indicators are in the indicator system. If they are not in the system, it means that the input indicator data is not important; compare the new product data and system data for the same component in pairs, and build a discriminant matrix A; calculate the indicator weights; calculate the consistency ratio C for matching scores based on the discriminant matrix A. R , C R<0.1 indicates that the consistency test is successful. If the test is unsuccessful, the discriminant matrix needs to be adjusted and the consistency test needs to be repeated. After the consistency test is successful, taking the coil of the same voltage level as an example, the winding method, capacity, number of parallel windings, number of gears, total number of sections, section number distribution, total number of turns, and wire gauge are arranged from high to low according to the weight coefficient, and assigned a value of 1.9-1.1. After that, the data indicator values ​​are accumulated, and the templates with a comprehensive score greater than 7 are sorted again. Finally, the template that best matches the new product is selected for design. If the score is too small to be determined as a new product, a new indicator search needs to be added. The specific steps are as follows.

[0077] In a possible implementation, step 103 includes the following content.

[0078] Step S31, input design parameters of the new product, the parameters including capacity, voltage level, winding method, core size and insulation set parameters.

[0079] Step S32, calling the design rule system, matching the input design parameters with the historical design data, and generating a matching score;

[0080] Step S33: selecting a historical design template that meets the design requirements from the calculation template library according to the matching score.

[0081] In a possible implementation, the matching evaluation includes the following process.

[0082] Constructing a discriminant matrix A for comparing design parameters with historical design data, wherein the discriminant matrix A is composed of differences between design indicators of historical design templates and design parameters of new products;

[0083] Calculate the consistency ratio for matching score based on the discriminant matrix A Among them, C I =(λ max -N F ) / (N F -1) is the consistency index, is the maximum eigenvalue of the discriminant matrix A, ω is the weight column vector, ω m is the weight of the m-th data indicator, (A ω ) m is the product of the m-th data indicator discriminant matrix A and the weight column vector ω, is the random consistency index obtained from the standard, N F is the total number of influencing indicators of the i-th category indicator, a ij Represents data a i For data a j The importance of a mj Represents data a m For data aj The importance of , 0<i<N F , 0<m<N F , 0<j≤N F .

[0084] In one example, as shown in 3, the present application also provides a comprehensive evaluation score calculation flow chart, the process is carried out from top to bottom, and the specific process is as follows:

[0085] First level: Start and initiate the calculation process of the comprehensive evaluation score.

[0086] The second layer: input design indicators as basic data for comprehensive evaluation.

[0087] The third layer: Determine whether the input design parameters are in the index system. If so, directly enter the fourth layer, accumulate the index scores of the parameters, and sort them by score. If not, enter the alternative index library to connect to the fifth layer and enter the design principle library.

[0088] Build the indicator system: Responsible for dynamically supplementing and expanding the indicator system, ensuring the integrity of the indicator framework, and connecting it to the "calculation weights".

[0089] Calculate weights: After the indicator system is constructed, the weight values ​​of each indicator are calculated based on the design indicators and connected to the fourth layer to optimize the sorting logic of the comprehensive evaluation score.

[0090] Fourth level: After completing the accumulation and ranking of indicator scores, a comprehensive evaluation score is generated.

[0091] Fifth layer: End, output the final comprehensive evaluation score.

[0092] The above comprehensive evaluation score calculation process can not only handle the input and judgment of design parameters, but also further optimize the score calculation logic by supplementing the indicator system and calculating weights, thereby achieving more accurate template matching and design selection.

[0093] Step 104 , generating a bill of materials (BOM) and related design data of the new product based on the selected design template.

[0094] In the embodiment of the present application, the historical experience calculation data is compiled into a general calculation formula. After selecting the template, relying on the CAD secondary development program, first obtain the template drawing number, and then calculate according to the important data of each component. Also use EXCEL formula to calculate the material data, and link the EXCEL calculation results through CAD to realize the automatic update of the BOM material details. Then, determine whether the new design material number data is the same as all the data under the same material number code in the system. If the data is the same, use the calculated data to check the material number code. If it is a new calculation result, open the material details and click "Update Material Number", and the drawing number code will automatically increase by 1. For newly added materials, the calculation template database formula is also used to calculate the results, and then manually added to the BOM material table. The specific steps are as follows.

[0095] In a possible implementation, step 104 includes the following content.

[0096] Step S41, calling the calculation template library, and generating a bill of materials (BOM) of the new product based on the selected historical design template and the input design parameters.

[0097] Step S42, linking the bill of materials with the design rule system to generate design data for new products and store them in the historical design data system.

[0098] Step 105, updating the historical design data system, design rule system and calculation template library by acquiring production feedback data.

[0099] In a possible implementation, step 105 includes the following content.

[0100] Step S51, obtaining feedback data about the oil-immersed transformer from the production process, wherein the feedback data includes design adjustment information, material usage data and process improvement data.

[0101] Step S52: adjusting the contents of the historical design data system, the design rule system and the calculation template library according to the feedback data.

[0102] Step S53, updating the association rules between the design rule system and the calculation template library according to the adjusted data, and applying the updated results to subsequent designs.

[0103] In one possible implementation, the weight distribution in the design rule system is adjusted according to the design adjustment suggestions found in the feedback data; the incremental logic of the component priority in the bill of materials (BOM) is dynamically adjusted based on the material usage data; and the parameter calculation logic of the template calculation library is re-verified according to the process improvement data. In summary, this step refers to accumulating experience in the actual production process, updating the database through continuous iteration, improving product quality and efficiency, and shortening the product life cycle.

[0104] like Figure 2 As shown, the present application also provides a data-driven oil-immersed transformer design flow chart, the design process is carried out from top to bottom, and the steps are as follows:

[0105] First level: To begin, start the design process of oil immersed transformer.

[0106] The second layer: input the voltage level of the new product as the basic design parameter.

[0107] The third layer: input design parameters for coils, cores, assemblies, oil tanks, leads, connecting pipes and other components as basic data for product design.

[0108] The fourth layer: Compare the input new product parameters with the historical design data in the system to establish a matching discriminant matrix.

[0109] Fifth layer: Based on the comprehensive evaluation method, the matching results are scored to obtain a comprehensive score value.

[0110] Level 6: Determine whether the comprehensive score reaches 7 points. If the score is ≥ 7 points, enter the seventh level and select the optimal template from the calculation template library for product design; if the score is < 7 points, refer to the design principle library, call the alternative index library to add it to the new product design index system, adjust the design parameters and return to the fifth level for re-scoring.

[0111] The eighth layer: Acquisition and processing of production feedback data. Determine the number of problems in the feedback data. If the feedback is 0, the design process ends; if the number of feedback is ≤3, enter the template calculation library for optimization, connect to the seventh layer, and reselect the optimal template design; if the number of feedback is >3, refer to the design principle library for adjustment, and return to the fifth layer for comprehensive scoring again.

[0112] pass Figure 2 The flow chart clearly shows how the data-driven oil-immersed transformer design method integrates historical data, design rules and template libraries to achieve efficient and accurate design. At the same time, it dynamically optimizes the design rules and template libraries through production feedback to further improve the quality and efficiency of the design.

[0113] like Figure 4 As shown, the present application also provides an iterative flow chart of a data-driven oil-immersed transformer calculation template, the process is unfolded from top to bottom, and the steps are as follows:

[0114] First level: Start, initiate the iterative process of calculating the template.

[0115] The second layer: call the formulas in the existing calculation template library as the calculation basis for the design parameters.

[0116] The third level: Determine whether the calculation logic needs to be improved during the design process. If improvement is needed, enter the fourth level and adjust the calculation logic based on production feedback; if improvement is not needed, return to the second level and continue to use the existing calculation template library formula for calculation.

[0117] The fourth layer: Based on the production feedback data, determine whether the result of the adjusted calculation logic meets the design requirements. If the adjusted calculation logic meets the design requirements, it will enter the fifth layer and the process ends; if it does not meet the design requirements, it will return to the second layer and call the existing calculation template library formula again for adjustment, and iterate in a cycle.

[0118] Fifth layer: End, completing the iterative optimization of the calculation template.

[0119] pass Figure 4 The flow chart can intuitively display the iterative update process of the calculation template library. This process continuously optimizes the formulas and parameter calculation logic in the calculation template library through logic improvements in the design process and dynamic adjustments of production feedback data, ensuring that the calculation process meets the design requirements and achieving continuous improvement in design quality.

[0120] In an embodiment of the present application, a data-driven oil-immersed transformer design method is proposed. The method is based on national standard power transformer design standards and guidelines, adds regional power grid design requirements for transformers, and is based on the data and expert experience retained by historical design products. The accumulation and reuse of historical experience data is achieved, which can greatly improve the design efficiency and quality for conventional products.

[0121] Specifically, the establishment of a historical design data system has improved the systematicness and integrity of the data; the classification and coding of design indicators has optimized data management and query efficiency; the provision of a design rule system and a calculation template library has standardized the design process; the introduction of a comprehensive evaluation method has improved the accuracy of template selection; the automatic generation of a bill of materials (BOM) has achieved efficient linkage from design to production; and the system has been dynamically adjusted through feedback data to iteratively improve design quality and efficiency.

[0122] Example 2

[0123] On the other hand, a data-driven oil-immersed transformer design device is provided, the device comprising:

[0124] A historical design data system building module is used to establish a historical design data system for supporting design by acquiring and organizing historical design data of oil-immersed power transformers;

[0125] Design rule and calculation template establishment module, used to establish a design rule system and parameter calculation template library based on national grid standards and historical design data;

[0126] A template-based design selection module is used to select a matching design template based on the design parameters of the new product in combination with the design rule system and the calculation template library;

[0127] Generate design output module, used to generate bill of materials (BOM) and related design data of new products based on the selected design template;

[0128] The data update module is used to update the historical design data system, design rule system and calculation template library by obtaining production feedback data.

[0129] Optionally, the historical design data system construction module includes:

[0130] A first construction unit is used to obtain historical design data of the oil-immersed power transformer, wherein the data includes component data of a coil, a core, a lead wire, an insulation set, an oil tank, and a coupling;

[0131] A second construction unit is used to classify the historical design data according to voltage levels, wherein the voltage levels include 35 kV, 110 kV, 220 kV and 500 kV;

[0132] The third construction unit is used to extract the design indicators of the components, encode the design indicators according to preset rules, and store them in the historical design data system.

[0133] Optionally, the encoding includes the following rules:

[0134] Numerical coding is used for the design indicators of the coil, and the coding consists of voltage level, winding method, number of turns and wire gauge; hierarchical coding is used for the design indicators of the core, and the coding includes core column width, window size, and core diameter parameters; incremental coding is used for the bill of materials (BOM) data, and the incremental coding is allocated based on component priority and historical usage frequency.

[0135] Optionally, the design rule and calculation template establishment module includes:

[0136] A first establishing unit is used to establish a design rule system for oil-immersed power transformers according to the national grid design standards and regional grid requirements, wherein the design rules include coil arrangement rules, core sheet number calculation rules, and bill of materials generation rules;

[0137] A second establishing unit is used to construct a parameter calculation template library based on historical design data, wherein the template library includes a coil calculation template, an iron core calculation template, and a bill of materials calculation template;

[0138] The third establishment unit is used to define the association rules between the design rule system and the calculation template library, and realize the linkage between the two through matching logic.

[0139] Optionally, the template-based design selection module includes:

[0140] The first selection unit is used to input design parameters of the new product, including capacity, voltage level, winding method, core size and insulation set parameters;

[0141] A second selection unit is used to call the design rule system, match the input design parameters with the historical design data, and generate a matching score;

[0142] The third selection unit is used to select a historical design template that meets the design requirements from the calculation template library according to the matching score.

[0143] Optionally, the compatibility assessment includes the following process:

[0144] Constructing a discriminant matrix A for comparing design parameters with historical design data, wherein the discriminant matrix A is composed of differences between design indicators of historical design templates and design parameters of new products;

[0145] Calculate the consistency ratio for matching score based on the discriminant matrix A in,

[0146] is the consistency indicator,

[0147] is the maximum eigenvalue of the discriminant matrix A,

[0148] ω is the weight column vector, ω m is the weight of the m-th data indicator, (A ω ) m is the product of the m-th data indicator discriminant matrix A and the weight column vector ω, is the random consistency index obtained from the standard, N F is the total number of influencing indicators of the i-th category indicator, a ij Represents data a i For data a j The importance of a mj Represents data a m For data a j The importance of , 0<i≤N F , 0<m≤N F , 0<j≤N F .

[0149] Optionally, the generation design output module includes:

[0150] A first output unit, for calling a calculation template library to generate a bill of materials (BOM) of a new product based on a selected historical design template and input design parameters;

[0151] The second output unit is used to link the bill of materials with the design rule system to generate design data for new products and store them in the historical design data system.

[0152] Optionally, the data updating module includes:

[0153] A first updating unit, configured to obtain feedback data on the oil-immersed transformer from a production process, wherein the feedback data includes design adjustment information, material usage data, and process improvement data;

[0154] A second updating unit is used to adjust the contents of the historical design data system, the design rule system and the calculation template library according to the feedback data;

[0155] The third updating unit is used to update the association rules between the design rule system and the calculation template library according to the adjusted data, and apply the updated results to subsequent designs.

[0156] An embodiment of the present application also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the data-driven oil-immersed transformer design method provided in the above embodiments.

[0157] Optionally, the computer readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid state drive (SSD), or an optical disk, etc. Among them, the random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM).

[0158] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0159] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0160] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A data-driven oil-immersed transformer design method, characterized in that: The method comprises: By acquiring and organizing the historical design data of oil-immersed power transformers, a historical design data system is established to support the design; Establish a design rule system and parameter calculation template library based on national grid standards and historical design data; According to the design parameters of the new product, a matching design template is selected in combination with the design rule system and the calculation template library; Generate the bill of materials (BOM) and related design data for the new product based on the selected design template; By obtaining production feedback data, the historical design data system, design rule system and calculation template library are updated.

2. The method according to claim 1, characterized in that The historical design data system for supporting design is established by acquiring and arranging the historical design data of the oil-immersed power transformer, including: Acquire historical design data of an oil-immersed power transformer, the data including component data of a coil, a core, a lead wire, an insulation assembly, an oil tank, and a coupling; Classifying the historical design data according to voltage levels, wherein the voltage levels include 35 kV, 110 kV, 220 kV and 500 kV; The design indicators of the components are extracted, and the design indicators are encoded according to preset rules and stored in the historical design data system.

3. The method according to claim 2, characterized in that The encoding includes the following rules: The design index of the coil is coded in numerical form, and the code consists of voltage level, winding method, number of turns and wire gauge; The design indexes of the core are coded in layers, and the coding includes core column width, window size, and core diameter parameters; Bill of Materials (BOM) data is incrementally coded, with the codes assigned based on component priority and historical frequency of use.

4. The method according to claim 1, characterized in that: The design rule system and parameter calculation template library are established according to the national grid standards and historical design data, including: According to the design standards of the national grid and the requirements of the regional grid, a design rule system for oil-immersed power transformers is established, wherein the design rules include coil arrangement rules, iron core number calculation rules and bill of materials generation rules; Based on the historical design data, a parameter calculation template library is constructed, wherein the template library includes a coil calculation template, an iron core calculation template, and a bill of materials calculation template; Define the association rules between the design rule system and the calculation template library, and realize the linkage between the two through matching logic.

5. The method according to claim 1, characterized in that The selecting a matching design template according to the design parameters of the new product in combination with the design rule system and the calculation template library includes: Input the design parameters of the new product, including capacity, voltage level, winding method, core size and insulation set parameters; Call the design rule system to match the input design parameters with the historical design data and generate a matching score; According to the matching score, a historical design template that meets the design requirements is selected from the calculation template library.

6. The method according to claim 5, characterized in that Compatibility evaluation The process includes: Constructing a discriminant matrix A for comparing design parameters with historical design data, wherein the discriminant matrix A is composed of the differences between design indicators and historical design templates; Calculate the consistency ratio for matching score based on the discriminant matrix A in, C I =(λ max -N F ) / (N F -1) is the consistency index, is the maximum eigenvalue of the discriminant matrix A, ω is the weight column vector, ω m is the weight of the m-th data indicator, (A ω ) m is the product of the m-th data indicator discriminant matrix A and the weight column vector ω, is the random consistency index obtained from the standard, N F is the total number of influencing indicators of the i-th category indicator, a ij Represents data a i For data a j The importance of a mj Represents data a m For data a j The importance of , 0<i≤N F , 0<m≤N F , 0<j≤N F .

7. The method according to claim 1, characterized in that The method generates a bill of materials (BOM) and related design data for a new product based on the selected design template, including: Calling the calculation template library to generate a bill of materials (BOM) for a new product based on the selected historical design template and the input design parameters; Link the bill of materials with the design rule system to generate design data for new products and store it in the historical design data system.

8. The method according to claim 1, characterized in that The method of obtaining production feedback data and updating the historical design data system, design rule system and calculation template library includes: Obtaining feedback data about the oil-immersed transformer from the production process, the feedback data including design adjustment information, material usage data and process improvement data; Adjust the contents of the historical design data system, design rule system and calculation template library based on the feedback data; According to the adjusted data, the association rules between the design rule system and the calculation template library are updated, and the updated results are applied to subsequent designs.

9. A data-driven oil-immersed transformer design device, characterized in that: The device comprises: A historical design data system building module is used to establish a historical design data system for supporting design by acquiring and organizing historical design data of oil-immersed power transformers; Design rule and calculation template establishment module, used to establish a design rule system and parameter calculation template library based on national grid standards and historical design data; A template-based design selection module is used to select a matching design template based on the design parameters of the new product in combination with the design rule system and the calculation template library; Generate design output module, used to generate bill of materials (BOM) and related design data of new products based on the selected design template; The data update module is used to update the historical design data system, design rule system and calculation template library by obtaining production feedback data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the data-driven oil-immersed transformer design method as described in any one of claims 1 to 8.

Images