Switch cabinet structure optimization design method and system

Abstract

The invention discloses a switch cabinet structure optimization design method and system, and relates to the technical field of switch cabinet structure optimizing.The switch cabinet element data is obtained, modeling is conducted on the switch cabinet element data according to preset configuration conditions, multiple switch cabinet design spaces are obtained, weight fixing processing is conducted on all the switch cabinet design spaces through an analytic hierarchy process, and the switch cabinet element data are obtained; obtaining a green characteristic weight corresponding to each switch cabinet design space, performing data preprocessing on all the switch cabinet design spaces according to each green characteristic weight, generating a design characteristic set, inputting the design characteristic set into a preset switch cabinet evaluation model for training, and generating a target switch cabinet evaluation model; and optimizing and evaluating all the switch cabinet design spaces by adopting the target switch cabinet evaluation model to obtain a switch cabinet optimization design scheme. The technical problems that the design of the switch cabinet generally lacks consideration on the environmental influence at present, and the structure of the switch cabinet cannot be optimally designed from the perspective of the environmental influence of the switch cabinet are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of switch cabinet structure optimization, and in particular to a switch cabinet structure optimization design method and system. Background Art

[0002] In the low-carbon economy, the environmental impact of switchgear has become one of the considerations for switchgear structural design. How to design the structure of switchgear green based on the environmental impact of switchgear has attracted widespread attention.

[0003] At present, the design of switchgear generally lacks consideration of the impact on the environment, and the environmental impact information is very complex, making it difficult to obtain accurate information, and it is impossible to optimize the switchgear structure from the perspective of the impact of the switchgear on the environment. Summary of the invention

[0004] The present invention provides a switch cabinet structure optimization design method and system, which solves the technical problems that the current design of switch cabinets generally lacks consideration of the impact on the environment, the environmental impact information is very complex, it is difficult to obtain accurate information, and the switch cabinet structure cannot be optimized from the perspective of the impact of the switch cabinet on the environment.

[0005] A first aspect of the present invention provides a switch cabinet structure optimization design method, comprising:

[0006] Acquire switch cabinet component data, and model the switch cabinet component data according to preset configuration conditions to obtain multiple switch cabinet design spaces;

[0007] The analytic hierarchy process is used to weight all the switch cabinet design spaces to obtain the green characteristic weights corresponding to the design spaces of each switch cabinet;

[0008] Performing data preprocessing on all the switch cabinet design spaces according to the weights of the green characteristics to generate a design feature set;

[0009] The design feature set is used to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model;

[0010] The target switch cabinet evaluation model is used to perform optimization evaluation on all the switch cabinet design spaces to obtain an optimized design solution for the switch cabinet.

[0011] Optionally, the step of acquiring switch cabinet component data, modeling the switch cabinet component data according to preset configuration conditions, and obtaining multiple switch cabinet design spaces includes:

[0012] Acquire switch cabinet component data, and divide the switch cabinet component data according to preset component types to obtain multiple component data;

[0013] Performing component parameter extraction processing on various component data according to preset configuration conditions to obtain multiple switch cabinet component sets;

[0014] Each of the switch cabinet component sets is respectively used to construct a switch cabinet design space corresponding to each of the switch cabinet component sets.

[0015] Optionally, the step of using the hierarchical analysis method to perform weight determination processing on all the switch cabinet design spaces to obtain the green characteristic weight corresponding to each switch cabinet design space includes:

[0016] respectively extracting engineering characteristic parameters of each switch cabinet design space;

[0017] Inputting each of the engineering characteristic parameters into a preset qualitative indicator list respectively, and matching the engineering characteristic evaluation parameters corresponding to each of the engineering characteristic parameters;

[0018] A triangular fuzzy algorithm is used to defuzzify each of the engineering characteristic evaluation parameters to obtain a green characteristic weight corresponding to each of the switch cabinet design spaces.

[0019] Optionally, the step of performing data preprocessing on all the switchgear design spaces according to the green characteristic weights to generate a design feature set includes:

[0020] arbitrarily selecting a plurality of the switch cabinet design spaces from all the switch cabinet design spaces as design evaluation spaces;

[0021] Standardizing all elements of the design evaluation space to obtain green evaluation parameters;

[0022] Inputting the green evaluation parameters and the green characteristic weights corresponding to each of the design evaluation spaces into a preset switch cabinet evaluation function to obtain an overall compromise value corresponding to each of the design evaluation spaces;

[0023] All of the design evaluation spaces are labeled according to all of the overall compromise values ​​to obtain a design feature set.

[0024] Optionally, the step of using the design feature set to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model includes:

[0025] The design feature set is used to input a preset switch cabinet evaluation model for training, and the overall training compromise data is output;

[0026] Calculate the training loss function value of the design feature set according to the training overall compromise data;

[0027] When the training loss function value is greater than or equal to a preset loss function threshold, adjusting the network parameters of the switch cabinet evaluation model until the training loss function value is less than the loss function threshold;

[0028] When the training loss function value is less than the loss function threshold, a target switch cabinet evaluation model is generated.

[0029] Optionally, the step of using the target switchgear evaluation model to perform optimization evaluation on each of the switchgear design spaces to obtain an optimized design solution for the switchgear includes:

[0030] Inputting all the switch cabinet design spaces into a target switch cabinet evaluation model to obtain an overall compromise value corresponding to each of the switch cabinet design spaces;

[0031] The switch cabinet design space with the smallest overall compromise value is selected as the switch cabinet optimization design solution.

[0032] A second aspect of the present invention provides a switch cabinet structure optimization design system, comprising:

[0033] Acquire switch cabinet component data, and model the switch cabinet component data according to preset configuration conditions to obtain multiple switch cabinet design spaces;

[0034] The analytic hierarchy process is used to weight all the switch cabinet design spaces to obtain the green characteristic weights corresponding to the design spaces of each switch cabinet;

[0035] Performing data preprocessing on all the switch cabinet design spaces according to the weights of the green characteristics to generate a design feature set;

[0036] The design feature set is used to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model;

[0037] The target switch cabinet evaluation model is used to perform optimization evaluation on all the switch cabinet design spaces to obtain an optimized design solution for the switch cabinet.

[0038] A third aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the switch cabinet structure optimization design method as described in any one of the above items.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the switch cabinet structure optimization design method as described in any one of the above items.

[0040] It can be seen from the above technical solutions that the present invention has the following advantages:

[0041] The present invention obtains switch cabinet component data, models the switch cabinet component data according to preset configuration conditions, obtains multiple switch cabinet design spaces, performs data preprocessing on part of the switch cabinet design space, generates a design feature set, inputs the design feature set into a preset switch cabinet evaluation model for training, generates a target switch cabinet evaluation model, and finally uses the target switch cabinet evaluation model to evaluate all switch cabinet design spaces, thereby obtaining an optimized design solution for the switch cabinet. This overcomes the technical problems that the current design of switch cabinets generally lacks consideration of environmental impacts, and that environmental impact information is very complex, making it difficult to obtain accurate information, and that the switch cabinet structure cannot be optimized from the perspective of the switch cabinet's impact on the environment. Compared with traditional optimization design methods, the present invention takes environmental impacts into consideration when optimizing the switch cabinet structure, and solves the problem of design solution combination explosion by evaluating all switch cabinet design spaces using a target switch cabinet evaluation model, thereby improving the reliability of switch cabinet structure optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 A flow chart of the steps of a switch cabinet structure optimization design method provided in Embodiment 1 of the present invention;

[0044] Figure 2 A flow chart of the steps of a switch cabinet structure optimization design method provided in the second embodiment of the present invention;

[0045] Figure 3 A schematic diagram of a switch cabinet structure function tree provided in Embodiment 2 of the present invention;

[0046] Figure 4 A schematic diagram for comparing the overall compromise value prediction results provided in the second embodiment of the present invention;

[0047] Figure 5 A structural block diagram of a switch cabinet structure optimization design system provided in Embodiment 3 of the present invention;

[0048] Figure 6 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0049] The embodiments of the present invention provide a switch cabinet structure optimization design method and system for solving the technical problems that the current design of switch cabinets generally lacks consideration of the impact on the environment, the environmental impact information is very complex, it is difficult to obtain accurate information, and the switch cabinet structure cannot be optimized from the perspective of the impact of the switch cabinet on the environment.

[0050] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 , Figure 1 A flow chart of the steps of a switch cabinet structure optimization design method provided in Embodiment 1 of the present invention.

[0052] The present invention provides a switch cabinet structure optimization design method, comprising:

[0053] Step 101: acquiring switch cabinet component data, modeling the switch cabinet component data according to preset configuration conditions, and obtaining multiple switch cabinet design spaces;

[0054] The switchgear component data refers to the various components of the switchgear, including but not limited to circuit breakers, busbars, trolley switches, insulating media, housings, heat dissipation systems, operating levers, and lighting systems.

[0055] In an embodiment of the present invention, switch cabinet component data is obtained from an existing design knowledge base and patent design, and corresponding component parameters are selected from the switch cabinet component data according to preset configuration conditions for combination to obtain multiple switch cabinet component sets, and the switch cabinet design space of each switch cabinet component set is respectively adopted.

[0056] It should be noted that, referring to Table 1, the configuration conditions are specific, and the component parameters are divided into multiple feasible domains according to the component types of the component parameters.

[0057] Table 1

[0058]

[0059] Step 102: using the analytic hierarchy process to perform weight determination on all switch cabinet design spaces, and obtaining the green characteristic weight corresponding to each switch cabinet design space;

[0060] In an embodiment of the present invention, the environment-related engineering characteristic parameters in the design space of each switch cabinet are extracted respectively, and then each engineering characteristic parameter is input into a preset qualitative indicator list respectively, and the engineering characteristic evaluation parameters corresponding to each engineering characteristic parameter are matched, and the engineering characteristic parameters and the engineering characteristic evaluation parameters corresponding to each engineering characteristic parameter are defuzzified by converting triangular fuzzy numbers and linguistic values ​​of triangular fuzzy numbers to obtain the green characteristic weights corresponding to each switch cabinet design space.

[0061] Step 103: preprocess the data of all switchgear design spaces according to the weights of the green characteristics to generate a design feature set;

[0062] In the embodiment of the present invention, a preset number of switch cabinet design spaces are selected from all switch cabinet design spaces as design evaluation spaces, the elements of all design evaluation spaces are standardized to obtain green evaluation parameters, and the green evaluation parameters and the green characteristic weights corresponding to each of the design evaluation spaces are used to calculate the overall compromise value corresponding to each design evaluation space. Each design evaluation space is labeled according to its overall compromise value to obtain a design feature set.

[0063] Step 104: using the design feature set to input a preset switchgear evaluation model for training, and generating a target switchgear evaluation model;

[0064] In the embodiment of the present invention, a preset switch cabinet evaluation model is trained using a design feature set to obtain a target switch cabinet evaluation model.

[0065] Step 105: Use the target switchgear evaluation model to perform optimization evaluation on all switchgear design spaces to obtain an optimized design solution for the switchgear.

[0066] In an embodiment of the present invention, each switch cabinet design space is input into a target switch cabinet evaluation model to obtain an overall compromise value of each switch cabinet design space, and the switch cabinet design space with the smallest overall compromise value is selected as the switch cabinet optimization design solution.

[0067] In an embodiment of the present invention, the present invention obtains switch cabinet component data, models the switch cabinet component data according to preset configuration conditions, obtains multiple switch cabinet design spaces, and then performs data preprocessing on part of the switch cabinet design space to generate a design feature set, inputs the design feature set into a preset switch cabinet evaluation model for training, generates a target switch cabinet evaluation model, and finally uses the target switch cabinet evaluation model to evaluate all switch cabinet design spaces, thereby obtaining an optimized design scheme for the switch cabinet. This overcomes the technical problem that the current design of switch cabinets generally lacks consideration of environmental impacts, and that environmental impact information is very complex, making it difficult to obtain accurate information, and that it is impossible to optimize the design of the switch cabinet structure from the perspective of the environmental impact of the switch cabinet. Compared with traditional optimization design methods, the present invention takes environmental impacts into consideration when optimizing the design of the switch cabinet structure, and solves the problem of explosion of design scheme combinations by evaluating all switch cabinet design spaces through the target switch cabinet evaluation model, thereby improving the reliability of switch cabinet structure optimization.

[0068] See also Figure 2 , Figure 2 A flow chart of the steps of a switch cabinet structure optimization design method provided in Embodiment 2 of the present invention.

[0069] The present invention provides a switch cabinet structure optimization design method, comprising:

[0070] Step 201: Obtain switchgear component data, model the switchgear component data according to preset configuration conditions, and obtain multiple switchgear design spaces;

[0071] Further, step 201 includes the following sub-steps:

[0072] S11, acquiring switch cabinet component data, dividing the switch cabinet component data according to preset component types, and obtaining multiple component data;

[0073] In an embodiment of the present invention, switch cabinet component data is obtained, and the switch component data is divided according to preset component types to obtain multiple component data, wherein the component types include circuit breakers, busbars, trolley switches, insulating media, housings, operating levers, lighting systems, and cooling systems.

[0074] S12, performing component parameter extraction processing on various component data according to preset configuration conditions to obtain multiple switch cabinet component sets;

[0075] In an embodiment of the present invention, component parameter extraction processing is performed on various component data according to preset configuration conditions to obtain multiple switch cabinet component sets. For example, the preset configuration condition is that the switch cabinet is composed of a circuit breaker, a busbar, an insulating medium, a casing and a heat dissipation system. According to the configuration condition, any one component parameter is selected from each type of component data in turn for combination, and all feasible design schemes are listed to obtain multiple switch cabinet component sets (that is, each switch cabinet component set corresponds to a feasible design scheme).

[0076] In another embodiment, see Figure 3 As shown, a switch cabinet design scheme and an OR tree are constructed according to preset configuration conditions, appropriate component parameters are selected from various component data according to the switch cabinet design scheme and the OR tree, and the selected component parameters are combined to obtain multiple switch cabinet component sets.

[0077] S13, using each switch cabinet component set to construct a switch cabinet design space corresponding to each switch cabinet component set.

[0078] In the embodiment of the present invention, each switch cabinet component set is used to construct the switch cabinet design space corresponding to each switch cabinet component set. For example, for a switch cabinet component set, component modules of each component parameter in the switch cabinet component set are constructed respectively, and each component module is combined to obtain the switch cabinet design space corresponding to the switch cabinet component set.

[0079] It should be noted that the construction of the switchgear design space can be achieved through simulation or design software such as MATLAB, Simulink, ANSYS, and CAD.

[0080] Step 202: extracting engineering characteristic parameters of each switch cabinet design space respectively;

[0081] In the embodiment of the present invention, parameters related to the environment in the design space of each switch cabinet (ie, environmental attributes, resource attributes, energy attributes, etc. in the design space of the switch cabinet) are extracted respectively as engineering characteristic parameters.

[0082] Step 203, input each engineering characteristic parameter into a preset qualitative index list, and match the engineering characteristic evaluation parameter corresponding to each engineering characteristic parameter;

[0083] In the embodiment of the present invention, each engineering characteristic parameter is input into a qualitative indicator list constructed by investigation, actual measurement or reference to relevant data, and the engineering characteristic evaluation parameter corresponding to each engineering characteristic parameter is matched.

[0084] It should be noted that, as shown in Table 2, the indicator values ​​of the qualitative indicators in the green engineering evaluation characteristics list are semantic variables, and a 9-level semantic scale {extremely poor, very poor, poor, lower average, average, upper average, good, very good, excellent} is used for evaluation.

[0085] Table 2

[0086]

[0087] Step 204: Defuzzify each engineering characteristic evaluation parameter using a triangular fuzzy algorithm to obtain a green characteristic weight corresponding to each switch cabinet design space.

[0088] In the embodiment of the present invention, a quality house matrix of each engineering characteristic evaluation parameter is constructed respectively, and each quality house matrix (in, , that is, the contribution degree of the i-th secondary index to the engineering characteristic parameters) are input into the preset triangular fuzzy model to obtain the green characteristic weight corresponding to each switchgear design space.

[0089] It should be noted that the triangular fuzzy model is specifically:

[0090]

[0091] in, is the first triangular fuzzy number of the i-th secondary index for the j-th engineering characteristic parameter, is the second triangular fuzzy number of the i-th secondary index to the j-th engineering characteristic parameter, is the third triangular fuzzy number of the i-th secondary index for the j-th engineering characteristic parameter, is the first fuzzy weight value, is the second fuzzy weight value, is the third fuzzy weight value, is the green characteristic weight of the jth engineering characteristic parameter, and m is the total number of switchgear design spaces.

[0092] It is worth mentioning that, assuming that a switch cabinet design space has x equation characteristic evaluation values, that is, . A quality house of y engineering characteristic parameters and x secondary indicators is constructed. By considering the contribution of each secondary indicator to the engineering characteristic parameters, the relationship between the engineering characteristic parameters and the engineering characteristic evaluation parameters is established. According to the conversion between triangular fuzzy numbers and language values ​​in Table 3, the quality house matrix of each engineering characteristic evaluation parameter is obtained.

[0093] Table 3

[0094]

[0095] Step 205: preprocess the data of all switchgear design spaces according to the weights of the green characteristics to generate a design feature set;

[0096] Further, step 205 includes the following sub-steps:

[0097] S21, arbitrarily selecting a plurality of switch cabinet design spaces from all switch cabinet design spaces as design evaluation spaces;

[0098] In the embodiment of the present invention, a plurality of switch cabinet design spaces are arbitrarily selected from all switch cabinet design spaces as design evaluation spaces for training a preset switch cabinet evaluation model.

[0099] S22, standardizing all elements of the design evaluation space to obtain green evaluation parameters;

[0100] In the embodiment of the present invention, the elements of the entire design evaluation space are used to construct a switch cabinet green attribute evaluation matrix, and the switch cabinet green attribute evaluation matrix is ​​input into a preset standardized model to obtain green evaluation parameters.

[0101] It should be noted that, as shown in Table 4, the switch cabinet green attribute evaluation matrix contains many numerical types, interval numerical types and language variable types. Therefore, in order to eliminate the dimensional influence of different types of data, it is necessary to perform standardization.

[0102] Table 4

[0103]

[0104] It should be noted that the standardized model is specifically:

[0105]

[0106] in, is the jth green attribute corresponding to the i-th design evaluation space, is the jth green attribute standardized value corresponding to the i-th design evaluation space, n is the number of elements contained in the engineering characteristic set C, m is the number of design evaluation spaces, B is the benefit attribute set, C is the cost attribute set, is the minimum value of the jth green attribute corresponding to the i-th design evaluation space, is the jth maximum value of green attribute corresponding to the i-th design evaluation space.

[0107] S23, inputting the green evaluation parameters and the green characteristic weights corresponding to each design evaluation space into a preset switch cabinet evaluation function to obtain an overall compromise value corresponding to each design evaluation space;

[0108] In the embodiment of the present invention, the green evaluation parameters and the green characteristic weights corresponding to each design evaluation space are used as inputs of a preset switch cabinet evaluation function to obtain an overall compromise value corresponding to each design evaluation space.

[0109] It should be noted that the switch cabinet evaluation function is specifically:

[0110]

[0111] in, is the group utility value of the i-th design evaluation space, is the individual regret value of the i-th design evaluation space, is the overall compromise value of the i-th design evaluation space, is the jth green feature weight, d is the distance between elements, is the influence coefficient of the strategic decision-making mechanism, is a positive ideal solution set, is a negative ideal solution set, is the maximum group utility value in the design evaluation space, is the minimum group utility value in the design evaluation space, is the maximum individual regret value in the design evaluation space, is the minimum individual regret value in the design evaluation space.

[0112] S24. Annotate all design evaluation spaces according to all overall compromise values ​​to obtain a design feature set.

[0113] In the embodiment of the present invention, all overall compromise values ​​are used to mark the design evaluation space to obtain a design feature set.

[0114] Step 206: Use the design feature set to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model;

[0115] Further, step 206 includes the following sub-steps:

[0116] S31, using the design feature set to input a preset switch cabinet evaluation model for training, and outputting overall training compromise data;

[0117] In the embodiment of the present invention, the design feature set is input into a preset switch cabinet evaluation model for training, and the overall training compromise data is output.

[0118] It should be noted that the preset switch cabinet evaluation model is a PSO-BP neural network model.

[0119] S32, calculating the training loss function value of the design feature set according to the overall training compromise data;

[0120] In an embodiment of the present invention, the training overall compromise data and the actual output value of the design feature set are input into a preset training loss function to obtain the training loss function value of the design feature set.

[0121] It should be noted that the training loss function is specifically:

[0122]

[0123] in, is the training loss function value, is the overall compromise value of the i-th training, is the ith actual output value, is the sample size of the design feature set.

[0124] S33. When the training loss function value is greater than or equal to the preset loss function threshold, the network parameters of the switch cabinet evaluation model are adjusted until the training loss function value is less than the loss function threshold;

[0125] In an embodiment of the present invention, if the training loss function value is greater than or equal to a preset loss function threshold, the gradient descent method is used to adjust the network parameters of the switch cabinet evaluation model until the training loss function value is less than the loss function threshold.

[0126] S34. When the training loss function value is less than the loss function threshold, a target switch cabinet evaluation model is generated.

[0127] In an embodiment of the present invention, if the training loss function value is less than the loss function threshold, a target switch cabinet evaluation model is generated.

[0128] Step 207: Use the target switchgear evaluation model to perform optimization evaluation on all switchgear design spaces to obtain an optimized design solution for the switchgear.

[0129] Further, step 207 includes the following sub-steps:

[0130] S41, inputting all switchgear design spaces into the target switchgear evaluation model to obtain the overall compromise value corresponding to each switchgear design space;

[0131] In the embodiment of the present invention, the target switch cabinet evaluation model is used to perform green evaluation on each switch cabinet design space to obtain the overall compromise value corresponding to each switch cabinet design space.

[0132] S42. Select the switch cabinet design space with the smallest overall compromise value as the switch cabinet optimization design solution.

[0133] In the embodiment of the present invention, the design spaces of the switch cabinets are arranged from small to large, and the switch cabinet design space with the smallest overall compromise value is selected as the switch cabinet optimization design solution.

[0134] In another example, an air-insulated switchgear is selected as the research object to demonstrate the superiority of the design method. The component data of the air-insulated switchgear is obtained, and the component data of the air-insulated switchgear is modeled according to the preset configuration conditions to obtain multiple air-insulated switchgear design spaces. Each air-insulated switchgear design space is divided into four functional modules, namely, a transmission module, a circuit control module, an auxiliary module and a protection module. The four functional modules of the air-insulated switchgear design space are brought into the quality house and mapped to the green engineering characteristics. The correlation between the two is triangular fuzzy scored. Refer to Table 5. The weights of the functional modules are calculated by the AHP method as {0.23, 0.36, 0.11, 0.3}, and brought into the right side of the quality house. The weights of the green engineering characteristics of the insulating switchgear are obtained through the defuzzification operation of the process in step 204. , using orthogonal experiment, determine the circuit breaker module, busbar module, trolley switch module, insulation medium module, shell module, cooling system module and other six factors, the level of each factor is given in Table 1, establish the orthogonal experiment table (i.e. Table 6), and refer to Table 7 to construct the green attribute evaluation matrix of the 25 design schemes, refer to Table 8, input the green attribute evaluation matrix into the switch cabinet evaluation function, and obtain the group utility value, individual regret value and overall compromise value of the 25 schemes in the orthogonal experiment. Figure 4 As shown, the above 25 design schemes are selected as the training set of the prediction model, and another 10 groups of design schemes are selected as the test set. The inertia weight interval is set to 0.3~0.9, and the value of the learning factor is set to 0~4. The learning factors c1 and c2 are set to 0.5 and 1.2 respectively, the number of evolutions is set to 500 times, and the population number is set to 20. Determine the input layer, hidden layer, and output layer, the number of neurons is 6, the number of hidden layer neurons is 10, and the number of output layer neurons is 3. The sample data in Tables 3 and 5 are used as training sample input and target output, and 10 groups of test sets are brought into the training model to obtain a comparison chart of the actual value of the test set prediction value range. In order to evaluate the fitting effect and generalization ability of the model, the present invention selects three indicators: relative error 𝛿, mean absolute percentage error (MAPE) and mean absolute error (MAE), and the calculation formula is as follows:

[0135]

[0136] Where m is the number of samples, and are the actual value and predicted value of the ith sample respectively. The meanings of these evaluation indicators are: the smaller the relative error 𝛿, the smaller the gap between the predicted result and the true value, and the more accurate the prediction result; the value of MAPE is between [0, +∞), the smaller the value of MAPE, the more perfect the prediction model, and when the value of MAPE is greater than 100%, it means that the model performance is very poor; the value of MAE is between [0, +∞), the value of MAE represents the absolute error between the predicted value and the true value, which will not be offset by the positive and negative values ​​of the error. The smaller the value of MAE, the smaller the prediction error. By calculating the relative error, the maximum value reached 9.63%, the minimum was 0.17%, the MAPE value was 5.35%, and the MAE value was 0.00179. The effect is relatively good, and it can establish a mapping between green engineering characteristics and module instances. Through the network model, the evaluation value of the design scheme is obtained, sorted from small to large according to the overall compromise value, and The value of satisfies 0.227>0.05, which meets the optimal solution judgment condition. Therefore, the optimal solution for the insulating switchgear is the combination of A1B2C2D4E2F1.

[0137] Table 5

[0138]

[0139] Table 6

[0140]

[0141] Table 7

[0142]

[0143] Table 8

[0144]

[0145] In an embodiment of the present invention, the present invention obtains switch cabinet component data, models the switch cabinet component data according to preset configuration conditions, obtains multiple switch cabinet design spaces, and then performs data preprocessing on part of the switch cabinet design space to generate a design feature set, inputs the design feature set into a preset switch cabinet evaluation model for training, generates a target switch cabinet evaluation model, and finally uses the target switch cabinet evaluation model to evaluate all switch cabinet design spaces, thereby obtaining an optimized design scheme for the switch cabinet. This overcomes the technical problem that the current design of switch cabinets generally lacks consideration of environmental impacts, and that environmental impact information is very complex, making it difficult to obtain accurate information, and that it is impossible to optimize the design of the switch cabinet structure from the perspective of the environmental impact of the switch cabinet. Compared with traditional optimization design methods, the present invention takes environmental impacts into consideration when optimizing the design of the switch cabinet structure, and solves the problem of explosion of design scheme combinations by evaluating all switch cabinet design spaces through the target switch cabinet evaluation model, thereby improving the reliability of switch cabinet structure optimization.

[0146] See also Figure 5 , Figure 5 This is a structural block diagram of a switch cabinet structure optimization design system provided in Embodiment 3 of the present invention.

[0147] The present invention provides a switch cabinet structure optimization design system, comprising:

[0148] The acquisition module 301 is used to acquire switchgear component data, model the switchgear component data according to preset configuration conditions, and obtain multiple switchgear design spaces;

[0149] The weight determination module 302 is used to perform weight determination processing on all switch cabinet design spaces by using the hierarchical analysis method to obtain the green characteristic weight corresponding to each switch cabinet design space;

[0150] A preprocessing module 303 is used to perform data preprocessing on the entire switchgear design space according to each green characteristic weight to generate a design feature set;

[0151] A training module 304 is used to use the design feature set to input a preset switchgear evaluation model for training to generate a target switchgear evaluation model;

[0152] The optimization module 305 is used to use the target switchgear evaluation model to perform optimization evaluation on all switchgear design spaces to obtain an optimized design solution for the switchgear.

[0153] Furthermore, the acquisition module 301 includes:

[0154] The classification submodule is used to obtain switch cabinet component data, divide the switch component data according to preset component types, and obtain multiple component data;

[0155] The combination submodule is used to extract component parameters of various component data according to preset configuration conditions to obtain multiple switch cabinet component sets;

[0156] The space construction submodule is used to respectively use each switch cabinet component set to construct the switch cabinet design space corresponding to each switch cabinet component set.

[0157] Furthermore, the weight determination module 302 includes:

[0158] The extraction submodule is used to extract the engineering characteristic parameters of each switchgear design space respectively;

[0159] A matching submodule, used to input each engineering characteristic parameter into a preset qualitative index list, and match the engineering characteristic evaluation parameter corresponding to each engineering characteristic parameter;

[0160] The fuzzy submodule is used to defuzzify each engineering characteristic evaluation parameter using a triangular fuzzy algorithm to obtain the green characteristic weight corresponding to each switchgear design space.

[0161] Furthermore, the preprocessing module 303 includes:

[0162] A selection submodule is used to select any number of switch cabinet design spaces from all switch cabinet design spaces as design evaluation spaces;

[0163] The standardization submodule is used to standardize the elements of all design evaluation spaces to obtain green evaluation parameters;

[0164] An evaluation submodule, used to input the green evaluation parameters and the green characteristic weights corresponding to each design evaluation space into a preset switch cabinet evaluation function to obtain an overall compromise value corresponding to each design evaluation space;

[0165] The labeling submodule is used to label the entire design evaluation space according to all overall trade-off values ​​to obtain a design feature set.

[0166] Furthermore, the training module 304 includes:

[0167] A first analysis submodule is used to use a design feature set to input a preset switch cabinet evaluation model for training, and output overall training compromise data;

[0168] A second analysis submodule is used to calculate the training loss function value of the design feature set based on the training overall compromise data;

[0169] The third analysis submodule is used to adjust the network parameters of the switch cabinet evaluation model when the training loss function value is greater than or equal to a preset loss function threshold, until the training loss function value is less than the loss function threshold;

[0170] When the training loss function value is less than the loss function threshold, the target switchgear evaluation model is generated.

[0171] Furthermore, the optimization module 305 includes:

[0172] An evaluation submodule is used to input all switchgear design spaces into the target switchgear evaluation model to obtain the overall compromise value corresponding to each switchgear design space;

[0173] The screening submodule is used to select the switch cabinet design space with the smallest overall compromise value as the switch cabinet optimization design solution.

[0174] See also Figure 6 , Figure 6 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention.

[0175] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 402 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes a switch cabinet structure optimization design method according to any of the above embodiments.

[0176] The memory 401 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 401 has a storage space 403 for a program code 413 for executing any method step in the above method. For example, the storage space 403 for the program code may include individual program codes 413 for implementing the various steps in the above method, respectively. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program code may be compressed, for example, in an appropriate form. When these codes are run by a computing and processing device, the computing and processing device performs the various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program code may be compressed, for example, in an appropriate form. When these codes are executed by a computing and processing device, the computing and processing device is caused to execute each step of the switch cabinet structure optimization design method described above.

[0177] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the switch cabinet structure optimization design method according to any of the above embodiments is implemented.

[0178] Embodiment 6 of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes a switch cabinet structure optimization design method as described in any of the above embodiments.

[0179] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0180] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0183] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0184] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A switch cabinet structure optimization design method, characterized in that: include: Acquire switch cabinet component data, and model the switch cabinet component data according to preset configuration conditions to obtain multiple switch cabinet design spaces; The analytic hierarchy process is used to weight all the switch cabinet design spaces to obtain the green characteristic weights corresponding to the design spaces of each switch cabinet; Performing data preprocessing on all the switch cabinet design spaces according to the weights of the green characteristics to generate a design feature set; The design feature set is used to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model; The target switch cabinet evaluation model is used to perform optimization evaluation on all the switch cabinet design spaces to obtain an optimized design solution for the switch cabinet.

2. The switch cabinet structure optimization design method according to claim 1, characterized in that: The step of acquiring switch cabinet component data, modeling the switch cabinet component data according to preset configuration conditions, and obtaining multiple switch cabinet design spaces includes: Acquire switch cabinet component data, and divide the switch cabinet component data according to preset component types to obtain multiple component data; Performing component parameter extraction processing on various component data according to preset configuration conditions to obtain multiple switch cabinet component sets; Each of the switch cabinet component sets is respectively used to construct a switch cabinet design space corresponding to each of the switch cabinet component sets.

3. The switch cabinet structure optimization design method according to claim 1, characterized in that: The step of using the analytic hierarchy process to perform weight determination on all the switch cabinet design spaces to obtain the green characteristic weight corresponding to each switch cabinet design space includes: respectively extracting engineering characteristic parameters of each switch cabinet design space; Inputting each of the engineering characteristic parameters into a preset qualitative indicator list respectively, and matching the engineering characteristic evaluation parameters corresponding to each of the engineering characteristic parameters; A triangular fuzzy algorithm is used to defuzzify each of the engineering characteristic evaluation parameters to obtain a green characteristic weight corresponding to each of the switch cabinet design spaces.

4. The switch cabinet structure optimization design method according to claim 1, characterized in that: The step of performing data preprocessing on all the switch cabinet design spaces according to the weights of the green characteristics to generate a design feature set comprises: arbitrarily selecting a plurality of the switch cabinet design spaces from all the switch cabinet design spaces as design evaluation spaces; Standardizing all elements of the design evaluation space to obtain green evaluation parameters; Inputting the green evaluation parameters and the green characteristic weights corresponding to each of the design evaluation spaces into a preset switch cabinet evaluation function to obtain an overall compromise value corresponding to each of the design evaluation spaces; All of the design evaluation spaces are labeled according to all of the overall compromise values ​​to obtain a design feature set.

5. The switch cabinet structure optimization design method according to claim 1, characterized in that: The step of using the design feature set to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model includes: The design feature set is used to input a preset switch cabinet evaluation model for training, and the overall training compromise data is output; Calculate the training loss function value of the design feature set according to the training overall compromise data; When the training loss function value is greater than or equal to a preset loss function threshold, adjusting the network parameters of the switch cabinet evaluation model until the training loss function value is less than the loss function threshold; When the training loss function value is less than the loss function threshold, a target switch cabinet evaluation model is generated.

6. The switch cabinet structure optimization design method according to claim 1, characterized in that: The step of using the target switch cabinet evaluation model to perform optimization evaluation on each switch cabinet design space to obtain an optimized design solution for the switch cabinet includes: Inputting all the switch cabinet design spaces into a target switch cabinet evaluation model to obtain an overall compromise value corresponding to each of the switch cabinet design spaces; The switch cabinet design space with the smallest overall compromise value is selected as the switch cabinet optimization design solution.

7. A switch cabinet structure optimization design system, characterized in that: include: Acquire switch cabinet component data, and model the switch cabinet component data according to preset configuration conditions to obtain multiple switch cabinet design spaces; The analytic hierarchy process is used to weight all the switch cabinet design spaces to obtain the green characteristic weights corresponding to the design spaces of each switch cabinet; Performing data preprocessing on all the switch cabinet design spaces according to the weights of the green characteristics to generate a design feature set; The design feature set is used to input a preset switch cabinet evaluation model for training to generate a target switch cabinet evaluation model; The target switch cabinet evaluation model is used to perform optimization evaluation on all the switch cabinet design spaces to obtain an optimized design solution for the switch cabinet.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the switch cabinet structure optimization design method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the switch cabinet structure optimization design method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the switch cabinet structure optimization design method according to any one of claims 1 to 6.

Images