Motor multi-objective optimization method and device based on combined agent model

Abstract

The invention discloses a motor multi-objective optimization method and device based on a combined proxy model. The method comprises the following steps: training each meta-proxy model by adopting a one-leaving cross validation method; determining a weight factor of each element agent model based on the error correlation matrix, and combining the element agent models into an optimized combination model according to the weight factors of the element agent models; during optimization, processing the extracted data of each to-be-optimized variable by using the optimization combination model to obtain optimization target data, and performing Sobol sensitivity analysis on each to-be-optimized variable by using the optimization target data to obtain a first-order influence index corresponding to each to-be-optimized variable and each total effect index; on the basis of the first-order influence index and the total effect index, hierarchically dividing each to-be-optimized variable; optimizing each to-be-optimized variable layer by layer by using the combinatorial optimization model; and selecting a final optimization result of each to-be-optimized variable of the target motor from the optimization result of the last layer.

Description

Technical Field

[0001] The present application relates to the technical field of parameter optimization, and in particular designs a motor multi-objective optimization method and device based on a combined agent model. Background Art

[0002] Currently, multiple parameter variables are involved in motor design, and each parameter variable will affect different engineering problems of the motor. Therefore, in order to solve the corresponding engineering problems and make the motor have better performance, it is necessary to optimize the motor's parameter variables.

[0003] Currently, analytical calculation analysis, finite element simulation, proxy model and other methods can be used to optimize the design of motors. The analytical modeling method is simple and has low time cost. However, since the motor is a strongly coupled and nonlinear model, a large number of conditions are ignored during the modeling process, resulting in low prediction accuracy. The finite element simulation has high accuracy, but its time cost is high. The motor may require hundreds of model calculations during the optimization process. The proxy model method has huge advantages over the first two methods in terms of accuracy and time cost, so the proxy model method has become an important method. This method is mainly for engineers to take a certain engineering problem of the motor as the optimization target, select a proxy model based on experience, and then optimize the parameter variables involved in the engineering problem through the proxy model analysis.

[0004] However, the current proxy model is single and is selected based on experience, so if the selection is inappropriate, the optimization effect will be relatively poor. In addition, a single proxy model usually performs well on only one problem and poorly on other problems, but a parameter variable will involve multiple problems, that is, the parameter variables will cross-influence each other, so the final overall optimization effect may be poor, and it is impossible to ensure that the designed motor reaches the accuracy required by the project. Summary of the invention

[0005] Based on the above-mentioned deficiencies of the prior art, the present application provides a motor multi-objective optimization method and device based on a combined agent model to solve the problem that the prior art cannot effectively achieve multi-objective optimization of clicks.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The first aspect of the present application provides a motor multi-objective optimization method based on a combined agent model, comprising:

[0008] Extracting data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data; wherein the value range of each variable to be optimized is a value range that meets the motor constraint condition;

[0009] The current variable extraction data is input into the combination optimization model, and the optimization target data corresponding to the variable extraction data is obtained through the combination optimization model; wherein the combination optimization model is obtained by combining a plurality of trained meta-agent models according to the weight factors of each meta-agent model; the weight factor of each meta-agent model is obtained based on the error correlation matrix of the meta-agent model; each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method; the training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data;

[0010] Using the optimization target data, a Sobol sensitivity analysis is performed on each of the variables to be optimized to obtain a first-order influence index and each total effect index corresponding to each of the variables to be optimized;

[0011] Based on the first-order influence index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and cross-degree; wherein, the variable to be optimized with higher sensitivity and the variable to be optimized with a cross-degree that meets a threshold value belongs to a higher level;

[0012] Utilizing the combined optimization model, the variables to be optimized at each level are still optimized in hierarchical order;

[0013] Based on the optimization target of the target motor, the final optimization results of each of the variables to be optimized of the target motor are selected from the optimization results of each group of the variables to be optimized obtained after the last layer of optimization.

[0014] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined proxy model, extracting data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data includes:

[0015] A Latin hypercube sampling method is adopted to extract multiple groups of data from the value range of each variable to be optimized of the target motor to form the current variable extraction data.

[0016] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined proxy model, before extracting data from the value range of each variable to be optimized of the target motor and obtaining the current variable extraction data, it also includes:

[0017] Determine various variables to be optimized, motor constraints and optimization objectives of the target motor;

[0018] Under the motor constraint conditions, determining the value range of each variable to be optimized;

[0019] Using the Latin hypercube sampling method, multiple groups of data are extracted from the value range of each variable to be optimized to form variable sample data;

[0020] Using finite element simulation, modeling and calculating each group of data in the variable sample data, and obtaining optimization target data corresponding to each group of data in the variable sample data; wherein the optimization target data is the value data of the optimization target;

[0021] Each group of data in the variable sample data and its corresponding optimization target data are used as the training sample set.

[0022] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined agent model, it also includes:

[0023] Using the initially constructed training sample set as the current training sample set;

[0024] Using the current training sample set respectively, adopting a leave-one-out cross-validation method to train each of the meta-agent models, to obtain each of the currently trained meta-agent models;

[0025] The current normalized square root error is calculated based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-proxy model when training is performed using the current training sample set; wherein the verification samples are samples in the current training sample set that do not participate in training during each training;

[0026] Determine whether the current normalized square root error is less than a threshold;

[0027] If it is determined that the current normalized square root error is not less than a threshold, taking the maximization of the EI criterion and the PoF criterion as the goal, a cluster analysis method is used to select multiple samples from the current training sample set to form a new current training sample set, and for the new current training sample set, the step of using the current training sample set to train each meta-proxy model by a leave-one-out cross-validation method is returned to execute, so as to obtain each meta-proxy model after training;

[0028] If it is determined that the current normalized square root error is less than a threshold, the training of each meta-agent model is terminated.

[0029] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined agent model, the current training sample set is used respectively to train each of the meta-agent models using a leave-one-out cross-validation method to obtain each of the trained meta-agent models, including:

[0030] Extract a sample that has not been extracted from the current training sample set as the current verification sample;

[0031] Using the remaining samples in the current training sample set respectively to train each of the meta-proxy models;

[0032] Using each of the trained meta-proxy models to process the current verification sample, and outputting the optimization target data corresponding to the current verification sample;

[0033] Determine whether there are any unextracted samples in the current training sample set;

[0034] If it is determined that there are unextracted samples in the current training sample set, returning to execute the step of extracting an unextracted sample from the current training sample set as the current verification sample;

[0035] If it is determined that there are no unextracted samples in the current training sample set, then each current meta-proxy model is determined to be the currently trained meta-proxy model.

[0036] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined agent model, the objective of maximizing the EI criterion and the PoF criterion is to select multiple samples from the current training sample set using a cluster analysis method to form a new current training sample set, including:

[0037] Calculating first criterion data and second criterion data for each sample in the current training sample set; wherein the first criterion data is data of the EI criterion; and the second criterion data is data of the PoF criterion;

[0038] Select the larger value of the first criterion data and the second criterion data of each sample respectively to obtain the current candidate test point set of each sample;

[0039] Clustering the data in the current candidate test point set in the current candidate test point using a clustering algorithm to obtain a plurality of clusters;

[0040] The samples corresponding to the data in each of the clusters are respectively screened out, and the samples with the largest product of the first criterion data and the second criterion data are screened out to form a new current training sample set.

[0041] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined agent model, after completing the training of each of the meta-agent models, the method further includes:

[0042] Calculating an error correlation matrix between each two meta-agent models based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-agent model;

[0043] Calculating a weight factor of each meta-agent model based on a proportion of the sum of error correlation matrices between each meta-agent model and the remaining meta-agent models;

[0044] The trained meta-agent models are weighted and combined according to their weight factors to obtain the combined optimization model.

[0045] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined agent model, based on the first-order influence index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and cross-degree, including:

[0046] Set the first level as the current level;

[0047] Classify each of the variables to be optimized that have not been divided into levels and whose corresponding first-order influence index is greater than the threshold value corresponding to the current level into the current level;

[0048] For each variable to be optimized in the current level, the variables to be optimized that have not been hierarchically divided and whose difference with the first-order influence index corresponding to the variable to be optimized is less than the cross-degree threshold, and the variables to be optimized that correspond to the total effect indexes corresponding to the variable to be optimized are divided into the current level;

[0049] Determine whether there are any variables to be optimized that have not been divided into levels;

[0050] If there are still variables to be optimized that have not been divided into levels, the next level of the current level is determined as the new current level, and the step of returning to execute the step of dividing each variable to be optimized that has not been divided into levels and whose corresponding first-order influence index is greater than the threshold value corresponding to the current level into the current level;

[0051] If there is no unclassified variable to be optimized, the class division is terminated.

[0052] Optionally, in the above-mentioned motor multi-objective optimization method based on the combined proxy model, the combined optimization model is used to optimize the variables to be optimized at each level in a hierarchical order, including:

[0053] The first-level data obtained by multiple value taking is processed by the combinatorial optimization model to obtain a Pareto solution set of the first level; wherein each of the first-level data is composed of each value of each of the variables to be optimized at the first level and the fixed values ​​of the variables to be optimized at the remaining levels;

[0054] Based on the optimization target of the target motor, a plurality of first-level data are selected from the frontier of the Pareto solution set of the first level as the optimization result of the first level;

[0055] Each level after the first level is taken as the current level in turn;

[0056] For each data in the optimization result of the previous level of the current level, the data of the current level obtained by multiple values ​​are processed by the combined optimization model to obtain a Pareto solution set of the current level; wherein the data of the current level is composed of the values ​​of the variables to be optimized of the current level and the values ​​of the variables to be optimized of the remaining levels in one data in the optimization result of the previous level of the current level;

[0057] Based on the optimization target of the target motor, a data of the current level is selected from the frontier of each Pareto solution set of the current level as the optimization result of the current level.

[0058] The second aspect of the present application provides a motor multi-objective optimization device based on a combined agent model, comprising:

[0059] A data extraction unit, used to extract data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data; wherein the value range of each variable to be optimized is a value range that meets the motor constraint condition;

[0060] A data processing unit, used for inputting the current variable extraction data into a combination optimization model, and obtaining the optimization target data corresponding to the variable extraction data through the combination optimization model; wherein the combination optimization model is obtained by combining a plurality of trained meta-agent models according to the weight factors of each meta-agent model; the weight factor of each meta-agent model is obtained based on the error correlation matrix of the meta-agent model; each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method; the training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data;

[0061] A sensitivity analysis unit, used to perform a Sobol sensitivity analysis on each of the variables to be optimized using the optimization target data, to obtain a first-order influence index and each total effect index corresponding to each of the variables to be optimized;

[0062] A hierarchical unit, for dividing each of the variables to be optimized into a plurality of levels according to sensitivity and cross-degree based on the first-order influence index and each total effect index corresponding to each of the variables to be optimized; wherein the variables to be optimized with higher sensitivity and the variables to be optimized with a cross-degree satisfying a threshold belong to a higher level;

[0063] An optimization unit, used to optimize the variables to be optimized at each level in a hierarchical order by using the combined optimization model;

[0064] The result selection unit is used to select the final optimization results of each of the variables to be optimized of the target motor from the optimization results of each group of the variables to be optimized obtained after the last layer of optimization based on the optimization target of the target motor.

[0065] The present application discloses a motor multi-objective optimization method based on a combined agent model, which preferentially utilizes a training sample set and adopts a leave-one-out cross-validation method to train multiple meta-agent models. Each prediction result of each model is unbiased and uncorrelated, and the model is also prevented from overfitting. The training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data, so that each meta-agent model can analyze the influence of the variable on the optimization target data from different aspects, that is, solve different work problems. Then, the weight factors of each meta-agent model are determined based on the error correlation matrix of the meta-agent model, and the combined optimization model is obtained according to the weight factors of each meta-agent model, so that according to the influence weight of each meta-agent model on the output, each meta-agent model is combined into a model that can realize analysis for multiple optimization targets. When optimizing, data is extracted from the value range of each variable to be optimized of the target motor to obtain the current variable extraction data. Among them, the value range of each variable to be optimized is the value range that meets the motor constraint condition to ensure that the value meets the requirements. Then the current variable extraction data is input into the combined optimization model, and the optimization target data corresponding to the variable extraction data is obtained through the combined optimization model. The optimization target data is used to perform Sobol sensitivity analysis on each variable to be optimized, and the first-order influence index and each total effect index corresponding to each variable to be optimized are obtained, so as to obtain the influence level of each variable to be optimized on the optimization target and the degree of mutual intersection between each variable to be optimized. Then, based on the first-order influence index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and intersection, and the combined optimization model is used to optimize the variables to be optimized in each level according to the hierarchical order. Among them, the higher the sensitivity of the variable to be optimized and the variable to be optimized whose intersection degree meets the threshold belong to the higher level, so as to give priority to optimizing the variables with greater influence on the optimization target, so as to ensure that the optimal result can be obtained in the end. Finally, based on the optimization target of the target motor, the final optimization results of each variable to be optimized of the target motor are selected from the optimization results of each group of variables to be optimized obtained after the last layer of optimization, thereby realizing a method of fast and effective optimization of each variable of the motor for multiple optimization targets through a combined optimization model. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present application 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 embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0067] Figure 1A flowchart of a motor multi-objective optimization method based on a combined agent model provided in an embodiment of the present application;

[0068] Figure 2 A flowchart of a method for obtaining a training sample set provided in an embodiment of the present application;

[0069] Figure 3 A flowchart of a method for training a meta-agent model provided in an embodiment of the present application;

[0070] Figure 4 A flowchart of a method for training each meta-agent model using a leave-one-out cross-validation method provided in an embodiment of the present application;

[0071] Figure 5 A flowchart of a method for selecting a new current training sample set provided in an embodiment of the present application;

[0072] Figure 6 A flowchart of a combination method of a combination model provided in an embodiment of the present application;

[0073] Figure 7 A flowchart of a method for classifying various variables to be optimized provided in an embodiment of the present application;

[0074] Figure 8 A flowchart of a method for optimizing variables to be optimized at each level layer by layer provided in an embodiment of the present application;

[0075] Fig. 9 A schematic diagram of the architecture of a motor multi-objective optimization device based on a combined proxy model is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0077] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0078] The present application embodiment provides a motor multi-objective optimization method based on a combined agent model, such as Figure 1 As shown, the following steps are included:

[0079] S101 , extracting data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data.

[0080] The target motor is the motor to be optimized. Each variable to be optimized can be determined according to actual needs. Optionally, the variables to be optimized may include but are not limited to slot width, slot depth, yoke height, primary width, secondary elongation, air gap height, secondary aluminum plate thickness, and secondary iron plate thickness.

[0081] Due to the influence of limiting factors such as the motor spatial structure, processing accuracy and maximizing the use of the stator core and tooth slots, some constraints must be considered during optimization, that is, the value range of each variable to be optimized is the value range that meets the motor constraint conditions. Optionally, the motor constraint conditions can be specifically:

[0082]

[0083] Where, L is the length of the motor; h is the height of the motor; b tmin is the minimum tooth width of the motor; B t and By are the magnetic flux amplitudes of the primary teeth and yoke of the motor respectively; s f is the slot fill rate.

[0084] It should be noted that in order to analyze the influence of each variable to be optimized on the optimization target, that is, the sensitivity, and to analyze the degree of intersection between each optimization variable, that is, the degree of mutual influence, it is necessary to extract some data from the value range of each variable to be optimized of the target motor, to respectively analyze the changes in the optimization target of the motor when the value of each variable to be optimized changes.

[0085] Optionally, a data is extracted from the value range of each variable to be optimized, and then a group of data is formed, and then multiple extractions are performed, so that multiple groups of data, that is, multiple value situations, can be obtained. Of course, multiple data can also be extracted from the value range of each variable to be optimized, and then these data are arranged and combined to obtain multiple groups of data, or other methods can be used.

[0086] Optionally, in order to efficiently extract data and ensure full coverage of each variable range, a specific implementation of step S101 in another embodiment of the present application includes:

[0087] The Latin hypercube sampling method is used to extract multiple groups of data from the value range of each variable to be optimized of the target motor to form the current variable extraction data.

[0088] S102: Input the current variable extraction data into the combination optimization model, and obtain the optimization target data corresponding to the variable extraction data through the combination optimization model.

[0089] Among them, the optimization target data refers to the specific value data of the optimization target. In an embodiment of the present application, the optimization target may include multiple targets, for example, the motor optimization target is the motor thrust and normal force size. In order to achieve traversal optimization for multiple targets at the same time, in an embodiment of the present application, multiple meta-agent models are combined according to corresponding weight factors, and the combined optimization model is used to distinguish the optimization targets that can be achieved by the motor for a certain set of variables. That is, the combined optimization model is obtained by combining multiple trained meta-agent models according to the weight factors of each meta-agent model. Optionally, each meta-agent model may specifically include a sample set pair Kriging (KRG) meta-agent model, a radial basis function (RBF) meta-agent model, and a support vector machine (SVR) meta-agent model.

[0090] Since the error correlation matrix of each meta-agent model represents the correlation between the output error of the meta-agent model and the error of the entire combined optimization model, that is, the influence of the meta-agent model on the overall error, the error correlation matrix of the meta-agent model can reflect the importance of the meta-agent model. Therefore, the weight factor of each meta-agent model is obtained based on the error correlation matrix of the meta-agent model.

[0091] In order to ensure that each prediction result of each model is unbiased and uncorrelated, and also to prevent model overfitting and evaluate the generalization ability of the meta-agent model, in the embodiment of the present application, each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method. In order to allow the trained meta-agent model to have data that analyzes the optimization target that can be achieved by the motor based on the value of the variable to be optimized, the training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data. Among them, the optimization target data corresponding to the data extracted from the value range of the variable to be optimized can be obtained by simulation.

[0092] Therefore, each group of data in the current variable extraction data can be input into the combinatorial optimization model respectively, and each group of data can be analyzed through the combinatorial optimization model to obtain the optimization target data corresponding to each group of data in the variable extraction data, that is, the value of the optimization target under multiple value conditions.

[0093] In order to enable the combined optimization model to analyze the optimization target, it is necessary to train each meta-agent model. Optionally, in another embodiment of the present application, before executing step S101, it is also necessary to obtain a training sample set for training the meta-agent model. Figure 2 As shown, the embodiment of the present application provides a method for obtaining a training sample set, comprising the following steps:

[0094] S201, determining various variables to be optimized, motor constraints and optimization targets of the target motor.

[0095] S202: Under motor constraints, determine the value range of each variable to be optimized.

[0096] S203. Using the Latin hypercube sampling method, multiple groups of data are extracted from the value range of each variable to be optimized to form variable sample data.

[0097] It should be noted that how to use as few points as possible to obtain the training sample point set with the best space filling effect plays an important role in the prediction effect of the subsequent meta-agent model. Therefore, in the embodiment of the present application, the Latin hypercube sampling (LHS) method is used for data extraction, which can efficiently sample from the distribution interval of the variable. And it is based on the space filling technology, which satisfies the projection characteristics, that is, the projections of the sample points in the design variable space on each dimension are uniformly distributed, that is, the projections on each dimension satisfy that there is only one projection point on each sub-interval. Assuming that there are k variables now, we now want to take N samples from their specified intervals, then the cumulative distribution of each variable is divided into the same N small intervals, and a value is randomly selected from each interval, and the N values ​​of each variable are randomly combined with the values ​​of other variables. Different from random sampling, this method can ensure full coverage of the range of each variable by maximizing the stratification of each marginal distribution.

[0098] Therefore, the specific collection process can be to first divide each dimension into m non-overlapping intervals so that each interval has the same probability. Then randomly extract a point in each interval in each dimension. Then randomly extract the selected data from each dimension and form them into vectors to obtain variable sample data, that is, to obtain multiple vectors, each of which is a set of values ​​of each variable to be optimized.

[0099] S204, using finite element simulation to perform modeling calculations on each group of data in the variable sample data, and obtain optimization target data corresponding to each group of data in the variable sample data.

[0100] The optimization target data is the value data of the optimization target.

[0101] Since the data of the training sample set is relatively effective, and in order to obtain accurate optimization target data, in the embodiment of the present application, a finite element simulation method is adopted to obtain the optimization target data corresponding to each group of data in the variable sample data through modeling calculation.

[0102] S205: Use each group of data in the variable sample data and its corresponding optimization target data as a training sample set.

[0103] After obtaining the training sample set, the meta-agent model can be trained. Optionally, in another embodiment of the present application, a meta-agent model training method is provided, such as Figure 3 As shown, the following steps are included:

[0104] S301: Use the initially constructed training sample set as the current training sample set.

[0105] It should be noted that the training sample set will be continuously streamlined in the future, so the training sample set originally constructed is used for training at the beginning, so it is used as the current training sample set.

[0106] S302 , respectively using the current training sample set and adopting a leave-one-out cross-validation method to train each meta-agent model to obtain each currently trained meta-agent model.

[0107] The currently trained meta-agent model at this time refers to the meta-agent model obtained after a round of training, not the finally trained meta-agent model.

[0108] It should be noted that leave-one-out cross-validation means that only one data point is extracted from the training sample set for cross-validation, and the remaining data is used to train the model, and this process is repeated for each data point. For example, if there are n data points, cross-validation should be repeated n times, and then the trained model is used to predict the data points that are not involved in the training. In this way, the prediction points obtained are irrelevant and unbiased, and it also has the function of preventing the meta-agent model from overfitting and evaluating the generalization ability of the meta-agent model. The specific operation is as follows: If the size of the sample set D is N, then use N-1 data for training, and use the remaining data as validation. In the leave-one-out cross-validation, a group is taken from D as the validation set each time until all samples have been used as validation sets, and a total of N times are calculated, and finally the validation errors are averaged.

[0109] Optionally, in an embodiment of the present application, the meta-agent model may specifically be a Kriging (KRG) meta-agent model, a radial basis function (RBF) meta-agent model, and a support vector machine (SVR) meta-agent model.

[0110] Among them, the KRG model is an effective interpolation method, including regression terms and systematic error terms. The general expression is as follows:

[0111]

[0112] where g(x)=[g1(x),...,g p (x)] T is the basis function of the model; β=[β1,...,β p ] T is the regression coefficient matrix; z(x) is a matrix with a mean of zero and a covariance of Cov[z(x i ),z(x j )]=σ 2 R(x i ,x j ,θ) random process; where σ 2 is the variance, R(x i ,x j, θ) is a correlation function with θ as the unknown.

[0113] If the correlation function is determined, then the predicted response for the prediction point x can be expressed as:

[0114]

[0115] where p is a unit vector; r T (x) is the correlation vector between a prediction point x and N sample points; f is the response value of the N sample points; the vector r and the scalar can be obtained by the following formula:

[0116] r T (x) = [R(x, x1), R(x, x2),..., R(x, x N )] T

[0117]

[0118] where f0 is the mean of the response values of the sample points.

[0119] The general expression of the RBF model is as follows:

[0120]

[0121] where is the model prediction value; n s is the variable dimension; ||x - x i || represents the Euclidean norm; φ(·) represents the basis function, and generally the inverse multiquadric interpolation function is used as the basis function.

[0122] φ(r) = (r 2 + c 2 ) 1 / 2

[0123] where r = ||x - x i || is the Euclidean distance from the current predicted value x to any sample point x i ; c is the shape parameter, usually 0 < c < 10, and here c = 1 is taken.

[0124] The SVR model predicts the meta surrogate model based on the kernel function ψ and the support vectors α +i and α -i and is expressed as:

[0125]

[0126] where μ is a constant.

[0127] Optionally, in another embodiment of the present application, a specific implementation of step S302 is as follows: Figure 4 As shown, including:

[0128] S401: Extract a sample that has not been extracted from the current training sample set as the current verification sample.

[0129] S402: Train each meta-proxy model using the remaining samples in the current training sample set.

[0130] S403: Use each trained meta-proxy model to process the current verification sample, and output the optimization target data corresponding to the current verification sample.

[0131] S404: Determine whether there are any unextracted samples in the current training sample set.

[0132] If it is determined that there are samples that have not been extracted in the current training sample set, the process returns to step S401. If it is determined that there are samples that have not been extracted in the current training sample set, the process proceeds to step S405.

[0133] S405: Determine each current meta-agent model as a currently trained meta-agent model.

[0134] S303 , calculating a current normalized square root error based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-agent model when training using the current training sample set.

[0135] The verification samples are samples in the current training sample set that are not involved in the training at each time. That is, after the training in step S302, the optimization target data corresponding to each sample extracted by the meta-agent model will be obtained. The current training sample set contains the real optimization target data of these samples, so the error between the two is the error of the model. Therefore, the current normalized square root error can be specifically expressed as:

[0136]

[0137] Among them, y(x i ) is the optimization target data of the verification sample in the current training sample set; The optimization target data corresponding to the validation sample output by the meta-agent model.

[0138] S304: Determine whether the current normalized square root error is less than a threshold.

[0139] If it is determined that the current normalized square root error is not less than the threshold, step S305 is executed. If it is determined that the current normalized square root error is less than the threshold, step S306 is executed.

[0140] S305 , with the goal of maximizing the EI criterion and the PoF criterion, a cluster analysis method is used to select multiple samples from the current training sample set to form a new current training sample set.

[0141] Since the current normalized square root error is not less than the threshold at this time, it means that the training effect has not reached the threshold, so it is necessary to select representative data and train the model again. In order to select representative data, in the embodiment of the present application, with the goal of maximizing the EI criterion and the PoF criterion, multiple samples are selected from the current training sample set to form a new current training sample set. And after executing step S305, for the new current training sample set, return to execute step S302.

[0142] Optionally, in another embodiment of the present application, with the goal of maximizing the EI criterion and the PoF criterion, a cluster analysis method is used to select multiple samples from the current training sample set to form a new current training sample set. That is, an implementation method of selecting a new current training sample set is as follows: Figure 5 As shown, the following steps are included:

[0143] S501, calculating the first criterion data and the second criterion data of each sample in the current training sample set.

[0144] The first criterion data is data of the EI criterion, that is, the calculation result of the EI criterion. The second criterion data is data of the PoF criterion, that is, the data of the PoF criterion.

[0145] Specifically, the data calculation process of the EI criterion is:

[0146]

[0147] Among them, y n min =min{y1,…,y n} represents the optimal response value at the current test point; I(x)=(y n min -Y(x) + Indicates the model's predicted value Y(x) relative to the current optimal response value y n min Improvements; represents the posterior distribution of the model at point x; Φ and φ represent the distribution and density functions of the standard normal distribution, respectively.

[0148] In order to make it applicable to constrained optimization problems, the feasibility of new test points must also be considered. represents the joint posterior distribution of the constraint model, where The feasibility probability of the test point x falling into the feasible region can be obtained from the joint posterior distribution of the model: If the constraints are assumed to be independent of each other, the PoF of the test point x can be expressed as:

[0149]

[0150] It should also be noted that when using the EI criterion, the test point set must contain at least one feasible test point; if the initial design does not contain a feasible test point, first use the following criterion to add a feasible test point at the place with the highest feasibility probability:

[0151]

[0152] Among them, P(G i (x)) is the feasibility probability.

[0153] S502 , respectively select the larger value of the first criterion data and the second criterion data of each sample to obtain a current candidate test point set for each sample.

[0154] Specifically, the current candidate test point set is generated using a multi-objective evolutionary algorithm:

[0155] Ps=max(EI(x),PoF(x))

[0156] S503: clustering the data in the current candidate test point set in the current candidate test point using a clustering algorithm to obtain a plurality of clusters.

[0157] S504, respectively filter out samples corresponding to each data in each cluster, and filter out samples with the largest product of the first criterion data and the second criterion data to form a new current training sample set.

[0158] Specifically, select from each cluster As new experimental points, they constitute a new current training sample set.

[0159] S306: End the training of each meta-agent model.

[0160] Optionally, in another embodiment of the present application, a combination method of a combination model is provided, such as Figure 6 As shown, the following steps are included:

[0161] S601 : Calculate the error correlation matrix between each two meta-agent models based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-agent model.

[0162] Specifically, the error correlation matrix of the error correlation matrix between the two meta-surrogate models can be expressed as:

[0163]

[0164] in, is the corresponding input x k The true response value of is the optimized target data of the verification sample in the current training sample set; and are the corresponding prediction values ​​of the i-th and j-th meta-surrogate models, that is, the errors of the optimized target data corresponding to the validation samples output by the meta-surrogate model.

[0165] S602 : Calculate a weight factor of each meta-agent model based on the proportion of the sum of the error correlation matrices between each meta-agent model and the other meta-agent models.

[0166] Specifically, the calculation method of the weight factor of a meta-agent model can be expressed as:

[0167]

[0168] Where C is the set of error correlation tools and M is the number of meta-agent models.

[0169] S603: Perform weighted combination of the trained meta-agent models according to their weight factors to obtain a combined optimization model.

[0170] So the expression of the combined optimization model can be expressed as:

[0171] in,

[0172] Among them, x is the variable to be optimized; is the predicted response value of the combined agent model, that is, the optimized target data output by the combined agent model; ω i is the weight factor of the ith meta-agent model; is the predicted response value of the ith meta-agent model, that is, the optimized target data output by the meta-agent model; and m is the number of initial meta-models for constructing the combined agent model.

[0173] S103, using the optimization target data to perform Sobol sensitivity analysis on each variable to be optimized, to obtain the first-order impact index and each total effect index corresponding to each variable to be optimized.

[0174] It should be noted that as a strongly coupled and strongly nonlinear model, the motor not only needs to consider the impact of a single parameter on the optimization target, but also the interaction between different variables. For example. The variable air gap height has a large correlation coefficient with the thrust target, while the variable slot depth has a small correlation coefficient with the thrust target, but the interaction between the slot depth and the air gap height is strong, and the impact on the thrust target after being combined as a whole is large. Therefore, for such situations, when performing hierarchical analysis, the air gap height and the slot depth must be divided together for in-depth research. Therefore, in order to analyze the sensitivity of each variable to be optimized, that is, to analyze the degree of influence of each variable to be optimized on the output optimization target data, and the correlation between each variable to be optimized, the variables to be optimized with greater correlation are divided together, so that the variables to be optimized can be optimized in a targeted manner. Therefore, in the embodiment of the present application, Sobol sensitivity analysis is used to analyze the sensitivity of each variable to be optimized to the output of the combined optimization model, and the first-order influence index corresponding to each variable to be optimized and each total effect index are obtained.

[0175] S104: Based on the first-order impact index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and cross-degree.

[0176] Among them, the variables to be optimized with higher sensitivity and the variables to be optimized whose intersection degree meets the threshold belong to a higher level.

[0177] It should be noted that there are usually many variables to be optimized, and they will affect multiple objectives, and each objective is mutually constrained, so the improvement of one objective performance often sacrifices other performance objectives, so it is difficult to find a perfect solution that achieves the best of all objectives. Therefore, in the optimization process, a compromise solution for multiple optimization objectives is actually obtained to obtain a solution that meets the needs. The more sensitive the variable to be optimized, the greater the impact on the output, that is, the greatest impact on each optimization objective. Therefore, in order to have a good optimization result for each optimization objective, it is necessary to focus on optimizing it first. Therefore, the more sensitive the variable to be optimized, the higher the level will be set so that it can be optimized first. Other variables to be optimized that have a deeper intersection with the variable to be optimized with higher sensitivity will affect the optimization objective together with the variable to be optimized, so they also need to be placed in the same layer so that they can be optimized together.

[0178] Among them, the first-order influence index corresponding to the variable to be optimized indicates the high sensitivity of the variable to be optimized. The total effect index is the overall impact of the input parameter, reflecting the impact of all interactive coupling effects of the parameter on the model output. Therefore, the difference between the total effect index ST and the first-order influence index S of the input variable can measure the effect of the interaction between the input and other input variables, and the degree of intersection between a variable to be optimized and other variables to be optimized.

[0179] Optionally, in another embodiment of the present application, a specific implementation of step S104 is as follows: Figure 7 As shown, the following steps are included:

[0180] S701. Set the first level as the current level.

[0181] S702: Classify all variables to be optimized that have not been divided into levels and whose corresponding first-order influence index is greater than the threshold corresponding to the current level into the current level.

[0182] For example, for the first level, each variable to be optimized whose first-order influence index S is greater than 0.6 is classified into the first level.

[0183] S703. For each variable to be optimized in the current level, the variables to be optimized that have not been hierarchically divided and correspond to the total effect indexes corresponding to the variable to be optimized whose difference with the first-order influence index corresponding to the variable to be optimized is less than the cross-degree threshold are divided into the current level.

[0184] It should be noted that each total effect index corresponding to a variable to be optimized is the total effect index corresponding to all combinations of it and other variables to be optimized. Therefore, a total effect index of a variable to be optimized represents the influence of the combination of the variable to be optimized and multiple other variables to be optimized on the model output. Therefore, the difference between the total effect index and the first-order influence index corresponding to the variable to be optimized is the effect of the interaction between the other variables to be optimized in the combination and the variable to be optimized.

[0185] Therefore, the variables to be optimized corresponding to the total effect indexes corresponding to the variable to be optimized whose difference in the first-order influence index corresponding to the variable to be optimized is less than the intersection degree threshold are the variables to be optimized that have a deeper degree of intersection with the variable to be optimized. Therefore, if they have not been divided into levels, they need to be placed at the same level for processing.

[0186] S704: Determine whether there are any variables to be optimized that have not been divided into levels.

[0187] If there are still unclassified variables to be optimized, then step S705 is executed. If there are no unclassified variables to be optimized, then step S706 is executed.

[0188] S705: Determine the next level of the current level as the new current level.

[0189] After executing step S705, the process returns to executing step S702.

[0190] S706: End the hierarchical division.

[0191] S105. Utilize the combined optimization model to optimize the variables to be optimized at each level in order of levels.

[0192] Since the process of optimizing the variables to be optimized is a process of compromise selection, and the higher the level of the variables to be optimized, the greater the impact on the optimization target, in order to obtain a result in which the optimization target meets the optimization requirements, it is necessary to optimize the variables with higher levels first, so it is necessary to optimize the variables to be optimized at each level in order from high to low. Specifically, the variables to be optimized at the previous level are optimized first, and one or more optimal values ​​of the variables to be optimized at a higher level are determined. Then, based on the determined variables to be optimized at the upper level, the variables to be optimized at the next level are optimized.

[0193] When optimizing the variables to be optimized, the goal is to determine the values ​​of the variables to be optimized that can make the optimization target data closest to the optimization target. The combinatorial optimization model can analyze the optimization effect that can be achieved with the values ​​of the variables to be optimized, that is, to obtain the corresponding optimization target data. Therefore, the combinatorial optimization model needs to be used for optimization.

[0194] Optionally, in another embodiment of the present application, a specific implementation of step S105 is as follows: Figure 8 As shown, including:

[0195] S801. Processing the first-level data obtained by multiple samplings through a combined optimization model to obtain a first-level Pareto solution set.

[0196] Among them, each first-level data is composed of each value of each variable to be optimized in the first level and the fixed value of the variable to be optimized in the remaining levels. Since the values ​​of the variables to be optimized in the first level need to be analyzed at this time to determine the optimal values ​​of the variables to be optimized in the first level, a large number of values ​​need to be taken for the variables to be optimized in the first level, and the input value combination optimization model is processed, and the optimization target data that can be achieved by different values ​​can be determined, so as to select the values ​​of the variables to be optimized in the first level that achieve the optimal optimization target data. However, since all the variables to be optimized are required to be input into the combination optimization model for processing, the values ​​of the variables to be optimized in other levels need to be fixed at this time, that is, the values ​​of the variables to be optimized in each level are fixed values, and only the values ​​of the variables to be optimized in the first level are changing, thereby forming each first-level data.

[0197] Among them, the Pareto solution set of the first level is each first-level data and its corresponding optimization target data.

[0198] Optionally, multiple value acquisition operations may be performed, with multiple values ​​selected each time.

[0199] S802 . Based on the optimization target of the target motor, select a plurality of first-level data from the frontier of the first-level Pareto solution set as the first-level optimization result.

[0200] The frontier of the Pareto solution set includes the optimal solution in each solution set obtained, that is, in the solution set obtained for the i-th time, if there is a point x1, and the optimization target data predicted and output by the combined optimization model for x1 is optimal, then it is added to the frontier of the Pareto solution set. For example, in the optimization target data predicted and output for x1, its thrust is greater than the thrust of all points in the set, and the normal force is closest to 0, then it is added to the frontier of the Pareto solution set. Since multiple values ​​are taken and there are multiple variables to be optimized at the first level, there are usually multiple data in the frontier of the Pareto solution set at the first level.

[0201] Since the data in the frontier of the first-level Pareto solution set are all the optimal values ​​of the variables to be optimized at the first level, and there may be a certain overlap between the variables to be optimized at the first level and the variables to be optimized at other levels, although the degree of overlap may be small, in order to take into account multiple situations and obtain better results, multiple first-level data are selected from the frontier of the first-level Pareto solution set as the optimization results of the first level.

[0202] S803. Take each level after the first level as the current level in turn.

[0203] Since the next level needs to be optimized based on the optimization results of the previous level, and the first level has no previous level, it needs additional processing. The other levels can be optimized based on the optimization results of their previous levels. So at this time, each level after the first level can be used as the current level in turn, and each time a current level is determined, the following steps are performed on it until the last level is processed as the current level.

[0204] S804, for each data in the optimization result of the previous level of the current level, the data of the current level obtained by multiple samplings are processed by the combined optimization model to obtain a Pareto solution set of the current level.

[0205] It should be noted that, since there are multiple optimization results of the previous level of the current level, that is, there are multiple possibilities, it is necessary to perform optimization operations separately based on each optimization result.

[0206] Since the optimization result of the previous level is the result of selecting the optimal values ​​of the variables to be optimized in the previous level, that is, the values ​​of the variables to be optimized in the previous level are fixed, the data of the current level are composed of the values ​​of the variables to be optimized in the current level and the values ​​of the variables to be optimized in the remaining levels in one of the data in the optimization result of the previous level of the current level, that is, only the values ​​of the variables to be optimized in the current level are changing, and the values ​​of the variables to be optimized in the remaining levels are collected using the values ​​in the optimization result of the previous level.

[0207] Specifically, one of the data in the optimization result of the previous level can be directly used as the starting point for optimization, and only the values ​​of the variables to be optimized in the current level in the data are continuously changed, so as to ensure that the values ​​of other levels are the values ​​of the optimization result of the previous level.

[0208] S805 , based on the optimization target of the target motor, select a data of the current level from the frontier of each Pareto solution set of the current level as the optimization result of the current level.

[0209] Since the processing is performed on the basis of each data in the optimization result of the previous level, multiple frontiers of Pareto solution sets will be obtained accordingly. The frontier of each Pareto solution set is the optimal solution in each case, so a data of the current level is selected from the frontier of each Pareto solution set as the optimization result of the first level. Of course, multiple data can also be selected, but it will lead to an increase in the amount of subsequent processing, and the effect it can bring is usually limited, or almost non-existent.

[0210] S106 , based on the optimization target of the target motor, the final optimization results of the variables to be optimized of the target motor are selected from the optimization results of the groups of variables to be optimized obtained after the last layer of optimization.

[0211] Since the optimization is performed layer by layer, when the optimization reaches the last layer, all the layers in the obtained results have been optimized. Therefore, at this time, based on the optimization target of the target motor, one of the optimization results can be selected as the final optimization result of each variable to be optimized of the target motor.

[0212] The present application discloses a motor multi-objective optimization method based on a combined agent model, which preferentially utilizes a training sample set and adopts a leave-one-out cross-validation method to train multiple meta-agent models. Each prediction result of each model is unbiased and uncorrelated, and the model is also prevented from overfitting. The training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data, so that each meta-agent model can analyze the influence of the variable on the optimization target data from different aspects, that is, solve different work problems. Then, the weight factors of each meta-agent model are determined based on the error correlation matrix of the meta-agent model, and the combined optimization model is obtained according to the weight factors of each meta-agent model, so that according to the influence weight of each meta-agent model on the output, each meta-agent model is combined into a model that can realize analysis for multiple optimization targets. When optimizing, data is extracted from the value range of each variable to be optimized of the target motor to obtain the current variable extraction data. Among them, the value range of each variable to be optimized is the value range that meets the motor constraint condition to ensure that the value meets the requirements. Then the current variable extraction data is input into the combined optimization model, and the optimization target data corresponding to the variable extraction data is obtained through the combined optimization model. The optimization target data is used to perform Sobol sensitivity analysis on each variable to be optimized, and the first-order influence index and each total effect index corresponding to each variable to be optimized are obtained, so as to obtain the influence level of each variable to be optimized on the optimization target and the degree of mutual intersection between each variable to be optimized. Then, based on the first-order influence index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and intersection, and the combined optimization model is used to optimize the variables to be optimized in each level according to the hierarchical order. Among them, the higher the sensitivity of the variable to be optimized and the variable to be optimized whose intersection degree meets the threshold belong to the higher level, so as to give priority to optimizing the variables with greater influence on the optimization target, so as to ensure that the optimal result can be obtained in the end. Finally, based on the optimization target of the target motor, the final optimization results of each variable to be optimized of the target motor are selected from the optimization results of each group of variables to be optimized obtained after the last layer of optimization, thereby realizing a method of fast and effective optimization of each variable of the motor for multiple optimization targets through a combined optimization model.

[0213] Another embodiment of the present application provides a motor multi-objective optimization device based on a combined agent model, such as Fig. 9 As shown, including:

[0214] The data extraction unit 901 is used to extract data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data.

[0215] The value range of each variable to be optimized is a value range that meets the motor constraint conditions.

[0216] The data processing unit 902 is used to input the current variable extraction data into the combination optimization model, and obtain the optimization target data corresponding to the variable extraction data through the combination optimization model.

[0217] The combined optimization model is obtained by combining multiple trained meta-agent models according to the weight factors of each meta-agent model. The weight factors of each meta-agent model are obtained based on the error correlation matrix of the meta-agent model. Each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method. The training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data.

[0218] The sensitivity analysis unit 903 is used to perform Sobol sensitivity analysis on each variable to be optimized using the optimization target data to obtain the first-order impact index and each total effect index corresponding to each variable to be optimized.

[0219] The stratification unit 904 is used to divide each variable to be optimized into multiple levels according to sensitivity and cross-degree based on the first-order influence index and each total effect index corresponding to each variable to be optimized.

[0220] Among them, the variables to be optimized with higher sensitivity and the variables to be optimized whose intersection degree meets the threshold belong to a higher level.

[0221] The optimization unit 905 is used to optimize the variables to be optimized at each level in a hierarchical order by using the combined optimization model.

[0222] The result selection unit 906 is used to select the final optimization results of each variable to be optimized of the target motor from the optimization results of each group of variables to be optimized obtained after the last layer of optimization based on the optimization target of the target motor.

[0223] It should be noted that the specific working process of each unit provided in the embodiment of the present application can refer to the corresponding steps in the above method embodiment, and will not be repeated here.

[0224] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0225] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A motor multi-objective optimization method based on a combined agent model, characterized in that: include: Extracting data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data; wherein the value range of each variable to be optimized is a value range that meets the motor constraint condition; The current variable extraction data is input into the combination optimization model, and the optimization target data corresponding to the variable extraction data is obtained through the combination optimization model; wherein the combination optimization model is obtained by combining a plurality of trained meta-agent models according to the weight factors of each meta-agent model; the weight factor of each meta-agent model is obtained based on the error correlation matrix of the meta-agent model; each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method; the training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data; Using the optimization target data, a Sobol sensitivity analysis is performed on each of the variables to be optimized to obtain a first-order influence index and each total effect index corresponding to each of the variables to be optimized; Based on the first-order influence index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and cross-degree; wherein, the variable to be optimized with higher sensitivity and the variable to be optimized with a cross-degree that meets a threshold value belongs to a higher level; Utilizing the combined optimization model, the variables to be optimized at each level are still optimized in hierarchical order; Based on the optimization target of the target motor, the final optimization results of each of the variables to be optimized of the target motor are selected from the optimization results of each group of the variables to be optimized obtained after the last layer of optimization.

2. The method according to claim 1, characterized in that The step of extracting data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data includes: A Latin hypercube sampling method is adopted to extract multiple groups of data from the value range of each variable to be optimized of the target motor to form the current variable extraction data.

3. The method according to claim 1, characterized in that The step of extracting data from the value range of each variable to be optimized of the target motor to obtain the current variable extracted data also includes: Determine various variables to be optimized, motor constraints and optimization objectives of the target motor; Under the motor constraint conditions, determining the value range of each variable to be optimized; Using the Latin hypercube sampling method, multiple groups of data are extracted from the value range of each variable to be optimized to form variable sample data; Using finite element simulation, modeling and calculating each group of data in the variable sample data, and obtaining optimization target data corresponding to each group of data in the variable sample data; wherein the optimization target data is the value data of the optimization target; Each group of data in the variable sample data and its corresponding optimization target data are used as the training sample set.

4. The method according to claim 1, characterized in that: Also includes: Using the initially constructed training sample set as the current training sample set; Using the current training sample set respectively, adopting a leave-one-out cross-validation method to train each of the meta-agent models, to obtain each of the currently trained meta-agent models; The current normalized square root error is calculated based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-proxy model when training is performed using the current training sample set; wherein the verification samples are samples in the current training sample set that do not participate in training during each training; Determine whether the current normalized square root error is less than a threshold; If it is determined that the current normalized square root error is not less than a threshold, taking the maximization of the EI criterion and the PoF criterion as the goal, a cluster analysis method is used to select multiple samples from the current training sample set to form a new current training sample set, and for the new current training sample set, the step of using the current training sample set to train each meta-proxy model by a leave-one-out cross-validation method is returned to execute, so as to obtain each meta-proxy model after training; If it is determined that the current normalized square root error is less than a threshold, the training of each meta-agent model is terminated.

5. The method according to claim 4, characterized in that The method of respectively using the current training sample set and adopting a leave-one-out cross-validation method to train each meta-agent model to obtain each meta-agent model after training includes: Extract a sample that has not been extracted from the current training sample set as the current verification sample; Using the remaining samples in the current training sample set respectively to train each of the meta-proxy models; Using each of the trained meta-proxy models to process the current verification sample, and outputting the optimization target data corresponding to the current verification sample; Determine whether there are any unextracted samples in the current training sample set; If it is determined that there are unextracted samples in the current training sample set, returning to execute the step of extracting an unextracted sample from the current training sample set as the current verification sample; If it is determined that there are no unextracted samples in the current training sample set, then each current meta-proxy model is determined to be the currently trained meta-proxy model.

6. The method according to claim 4, characterized in that The method of selecting a plurality of samples from the current training sample set to form a new current training sample set by using a cluster analysis method with the goal of maximizing the EI criterion and the PoF criterion includes: Calculating first criterion data and second criterion data for each sample in the current training sample set; wherein the first criterion data is data of the EI criterion; and the second criterion data is data of the PoF criterion; Select the larger value of the first criterion data and the second criterion data of each sample respectively to obtain the current candidate test point set of each sample; Clustering the data in the current candidate test point set in the current candidate test point using a clustering algorithm to obtain a plurality of clusters; The samples corresponding to the data in each of the clusters are respectively screened out, and the samples with the largest product of the first criterion data and the second criterion data are screened out to form a new current training sample set.

7. The method according to claim 4, characterized in that After the training of each of the meta-agent models is completed, the method further includes: Calculating an error correlation matrix between each two meta-agent models based on the error between the optimization target data in the current training sample set and the optimization target data corresponding to the verification samples output by each meta-agent model; Calculating a weight factor of each meta-agent model based on a proportion of the sum of error correlation matrices between each meta-agent model and the remaining meta-agent models; The trained meta-agent models are weighted and combined according to their weight factors to obtain the combined optimization model.

8. The method according to claim 1, characterized in that Based on the first-order impact index and each total effect index corresponding to each variable to be optimized, each variable to be optimized is divided into multiple levels according to sensitivity and cross-degree, including: Set the first level as the current level; Classify each of the variables to be optimized that have not been divided into levels and whose corresponding first-order influence index is greater than the threshold value corresponding to the current level into the current level; For each variable to be optimized in the current level, the variables to be optimized that have not been hierarchically divided and whose difference with the first-order influence index corresponding to the variable to be optimized is less than the cross-degree threshold, and the variables to be optimized that correspond to the total effect indexes corresponding to the variable to be optimized are divided into the current level; Determine whether there are any variables to be optimized that have not been divided into levels; If there are still variables to be optimized that have not been divided into levels, the next level of the current level is determined as the new current level, and the step of returning to execute the step of dividing each variable to be optimized that has not been divided into levels and whose corresponding first-order influence index is greater than the threshold value corresponding to the current level into the current level; If there is no unclassified variable to be optimized, the class division is terminated.

9. The method according to claim 1, characterized in that: The method of using the combined optimization model to optimize the variables to be optimized at each level in a hierarchical order includes: The first-level data obtained by multiple value taking is processed by the combinatorial optimization model to obtain a Pareto solution set of the first level; wherein each of the first-level data is composed of each value of each of the variables to be optimized at the first level and the fixed values ​​of the variables to be optimized at the remaining levels; Based on the optimization target of the target motor, a plurality of first-level data are selected from the frontier of the Pareto solution set of the first level as the optimization result of the first level; Each level after the first level is taken as the current level in turn; For each data in the optimization result of the previous level of the current level, the data of the current level obtained by multiple values ​​are processed by the combined optimization model to obtain a Pareto solution set of the current level; wherein the data of the current level is composed of the values ​​of the variables to be optimized of the current level and the values ​​of the variables to be optimized of the remaining levels in one data in the optimization result of the previous level of the current level; Based on the optimization target of the target motor, a data of the current level is selected from the frontier of each Pareto solution set of the current level as the optimization result of the current level.

10. A motor multi-objective optimization device based on a combined agent model, characterized in that: include: A data extraction unit, used to extract data from the value range of each variable to be optimized of the target motor to obtain current variable extraction data; wherein the value range of each variable to be optimized is a value range that meets the motor constraint condition; A data processing unit, used for inputting the current variable extraction data into a combination optimization model, and obtaining the optimization target data corresponding to the variable extraction data through the combination optimization model; wherein the combination optimization model is obtained by combining a plurality of trained meta-agent models according to the weight factors of each meta-agent model; the weight factor of each meta-agent model is obtained based on the error correlation matrix of the meta-agent model; each meta-agent model is trained using a training sample set and a leave-one-out cross-validation method; the training sample set includes data extracted from the value range of each variable to be optimized and its corresponding optimization target data; A sensitivity analysis unit, used to perform a Sobol sensitivity analysis on each of the variables to be optimized using the optimization target data, to obtain a first-order influence index and each total effect index corresponding to each of the variables to be optimized; A hierarchical unit, for dividing each of the variables to be optimized into a plurality of levels according to sensitivity and cross-degree based on the first-order influence index and each total effect index corresponding to each of the variables to be optimized; wherein the variables to be optimized with higher sensitivity and the variables to be optimized with a cross-degree satisfying a threshold belong to a higher level; An optimization unit, used to optimize the variables to be optimized at each level in a hierarchical order by using the combined optimization model; The result selection unit is used to select the final optimization results of each of the variables to be optimized of the target motor from the optimization results of each group of the variables to be optimized obtained after the last layer of optimization based on the optimization target of the target motor.

Images