Electromagnetic relay multi-target parameter optimization design method considering performance index and quality consistency at same time

Abstract

The invention discloses an electromagnetic relay multi-target parameter optimization design method considering performance index and quality consistency at the same time. The method comprises the following steps: step 1, randomly sampling to determine a decision parameter combination sample; step 2, calculating a parameter combination sample suction by a finite element simulation method; step 3, establishing a multi-model stacked suction rapid calculation model; step 4, uniformly sampling and calculating a suction standard deviation by introducing a normal distribution weight; step 5, objective function establishment and optimization problem dimensionality reduction; and step 6, Pareto optimal solution set solving and optimal parameter combination screening are carried out. Different from other parameter optimization methods, the method has the advantages that a rapid suction calculation model is established, constraint conditions during actual engineering application are considered, optimal parameter combinations are really approached, suction fluctuation is reduced, suction mean values are optimized, and the method is good in overall optimization effect, objective in result and low in time and labor cost.

Description

Technical Field

[0001] The invention relates to a parameter optimization design method for an electromagnetic relay, and in particular to a multi-objective parameter optimization design method for an electromagnetic relay that simultaneously considers performance indicators and quality consistency. Background Art

[0002] As a core component of power systems and automatic control systems, electromagnetic relays are widely used in high-tech industries and defense fields due to their high conversion depth and strong anti-interference capabilities, playing the role of converting circuits and safety protection.

[0003] The design of electrical components mainly relies on the three-dimensional design concept to improve product quality consistency and reduce costs and increase efficiency. The three-dimensional design mainly includes three steps: overall design, parameter design and tolerance design. The parameter design aims to obtain the sensitivity and signal-to-noise ratio of all major parameters affecting product quality characteristics by designing orthogonal experiments, and select the best parameter combination according to the nonlinear effect to minimize the fluctuation of product quality characteristics, that is, to improve product quality consistency. In the design of electromagnetic relays, the standard deviation of the pull-in voltage of batch products is one of the key quality characteristic indicators to measure the quality consistency of this model of products, and the pull-in voltage is determined by the combination of suction and reaction forces. If the product is in the release state, at the specified pull-in voltage, due to fluctuations in part size, assembly factors, etc., the electromagnetic suction force is not greater than the reaction force, then the product will not be able to complete the expected pull-in action. Therefore, optimizing the design value of part size parameters through parameter design to reduce suction fluctuations is an important method to improve the quality consistency of relay products.

[0004] At present, the relay industry aims to reduce suction fluctuations and optimize the values ​​of part size parameters. The existing parameter design methods have the following problems:

[0005] First, although the existing parameter design method can reduce the standard deviation of suction by adjusting the stabilizing factor, it can also improve the mean value of suction by adjusting the adjustment factor. This method seems to be able to compensate for the mean loss caused by reducing the suction fluctuation. However, when solving actual engineering problems in the field of electromagnetic relays, due to the fact that there are usually fewer adjustment factors in the electromagnetic system structure, this compensation is often ineffective. Although the result of parameter design effectively reduces the standard deviation of suction, it sacrifices the mean value of suction at the same time, causing the pull-in voltage to deviate significantly from the index requirements. This is an optimization result that sacrifices the essentials for the sake of the trivial, and often does not make up for the loss. Therefore, due to the contradiction between the pull-in voltage performance index requirements and the quality consistency improvement requirements of reducing the standard deviation of suction, the parameter design method cannot be applied to the actual relay product quality consistency improvement design.

[0006] Secondly, although the existing parameter design methods can select parameter combinations that reduce the suction standard deviation by analyzing sensitivity and signal-to-noise ratio, the number of parameter value levels is small, and the specific value of each level is highly dependent on engineering experience. The result of parameter design is the best combination of each parameter level. Therefore, the results of existing methods are often affected by subjective factors.

[0007] Third, the existing parameter design methods require multiple rounds of parameter design attempts to approximate the optimal combination, and each parameter design requires a large number of simulation calculations through the finite element method to obtain the internal and external surface results of the orthogonal test. This is not only computationally intensive and time-consuming, but also due to the discretization of the parameter values ​​in the existing methods, the results are still just a combination of manually selected parameter levels, which is often not the optimal solution to the problem. Summary of the invention

[0008] In order to solve the problems of current parameter design methods, such as poor overall optimization effect, susceptibility to subjective factors, large amount of calculation, high time cost, and inability to be applied to actual relay product quality consistency improvement design, the present invention provides an electromagnetic relay multi-objective parameter optimization design method that simultaneously considers performance indicators and quality consistency.

[0009] The objective of the present invention is achieved through the following technical solutions:

[0010] A multi-objective parameter optimization design method for an electromagnetic relay that simultaneously considers performance indicators and quality consistency comprises the following steps:

[0011] Step 1: Randomly sample and determine the decision parameter combination sample:

[0012] Step 11, take two points A and B where the suction reaction force curve is most likely to intersect, and define them as the key points of the armature position;

[0013] Step 12: The influence of the decision parameters on the suction force of the electromagnetic system is expressed as:

[0014]

[0015] Where x is the armature position, x A and x B Respectively represent the armature position point A and point B, F EMF (x A ,z) and F EMF (x B , z) represent the relationship between the suction of point A and point B affected by the decision parameters, z is the row vector representing the combination of decision parameters, z i represents the i-th decision parameter, and n represents the total number of decision parameters;

[0016] Step 13: Define the decision parameter space as [zi,min ,z i,max ] n-dimensional hypercube, i = 1, 2, ..., n, z i,min and z i,max Represent the minimum and maximum values ​​of the i-th decision parameter, respectively. For each decision parameter z i The value range is divided into M layers of equal width, and the width of each layer is expressed as:

[0017]

[0018] The endpoints of the jth layer are represented as:

[0019] z i,j =z i,min +(j-1)·Δz i ,j=1,2,...,M

[0020] Step 14: For each decision parameter z i , uniformly extract a sample point from each layer:

[0021]

[0022] Among them, U i,j is a random number uniformly drawn from the interval [0,1);

[0023] Step 15: Randomly arrange and combine the sampling results of each decision parameter to obtain the decision parameter combination training sample matrix:

[0024]

[0025] Among them, any k-th row of the matrix Z k,· They are all a combination of decision parameters;

[0026] Step 16: Repeat steps 13 to 15 to obtain the decision parameter combination test sample matrix:

[0027]

[0028] in, It represents the test sample point randomly selected from the Mth layer for the nth decision parameter;

[0029] Step 2: Calculate the suction force of the parameter combination sample using the finite element simulation method:

[0030] Step 21: Using the finite element simulation calculation method, solve the suction force F of point A and point B under the decision parameter combination of each row of the decision parameter combination training sample matrix Z and the decision parameter combination test sample matrix T. EMF (x A ,Z k,· ), FEMF (x A ,T k,· ) and F EMF (x B ,Z k,· ), F EMF (x B ,T k,· );

[0031] Step 22: The decision parameter combination training sample matrix Z and its output data set are represented as matrix X. The matrix X is divided into two matrices by row, including the training set X 1:h,· and validation set X h+1:M,· , where the training set is used to train the fast computing model; the validation set is used to verify the model during training, evaluate the generalization ability of the model in real time, and adaptively adjust the hyperparameters;

[0032] Step 23, the decision parameter combination test sample matrix T and its output data set are represented as a matrix Y, which itself is used as a test set to evaluate the established fast calculation model;

[0033] Step 3: Establish a fast calculation model for suction force of multi-model stacking:

[0034] Step 31: Use the same data set and two different methods to establish two basic models, numbered as model 1 and model 2, denoted as C and 1 (x,z) and C 2 (x,z);

[0035] Step 32: When training model 1, the calculation result is obtained by weighted average of each known data point. The model weight to be determined is represented by λ a , the model is expressed as:

[0036]

[0037] Solve the model weight λ by minimizing the covariance matrix a , list the matrix equation:

[0038]

[0039] Among them, Cov(,) represents the covariance, and the model weight λ is obtained by solving a and the Lagrange constant μ, and determine the best hyperparameters by minimizing the prediction error using the validation set data;

[0040] Step 33, when training model No. 2, the optimal hyperplane is found by minimizing the loss function. The model is expressed as:

[0041] C 2 (x,za )=w·(x,Z a,· )+b

[0042] Among them, w is the undetermined weight vector, b is the undetermined bias term, and the undetermined coefficients are determined by constructing and minimizing the objective function. The objective function and its constraints are expressed as:

[0043]

[0044] Among them, ξ a and is the slack variable, c is the regularization parameter, and δ is the error upper limit constant. By solving this minimization problem, we can obtain the undetermined weight vector and undetermined bias term of the model. We can use the validation set to optimize the regularization parameter of the model and determine the optimal hyperparameter.

[0045] Step 34: stack the two established basic models to train the final suction rapid calculation model, which is expressed as:

[0046] C(x,z a )=β 1 C 1 (x,z a )+β 2 C 2 (x,z a )

[0047] Among them, β 1 and β 2 are the weight parameters of the two basic models, and the optimal weight parameters are solved by minimizing the prediction error;

[0048] Step 35, using the decision parameter combination test sample matrix T to calculate the mean square error and goodness of fit of the suction rapid calculation model, and evaluate the suction rapid calculation model;

[0049] Step 4: Calculation of suction standard deviation with uniform sampling and introduction of normal distribution weights

[0050] Step 41: Since each decision parameter obeys the normal distribution, its fluctuation affects the suction force so that the suction force also obeys the normal distribution:

[0051] F EMF ~N(μ F ,σ F 2 )

[0052] Among them, μ F and σ F represent the mean and standard deviation of the suction force distribution, respectively;

[0053] Step 42: Use the suction rapid calculation model to calculate the mean and standard deviation of the suction at point A and point B, and combine the decision parameters z * After inputting the suction quick calculation model, the output result is the average suction value of point A and point B:

[0054]

[0055] Step 43: At each decision parameter z i of The decision parameter combinations are uniformly sampled within the range, and each decision parameter combination sample is expressed as:

[0056]

[0057] in, represents the lth sample point of the i-th decision parameter;

[0058] Step 44: Use the normal distribution probability density function of the decision parameter for weighting and calculate the standard deviation of the suction force at point A and point B:

[0059]

[0060] Step 5: Objective function establishment and optimization problem dimensionality reduction:

[0061] Step 51: define the parameter optimization problem as:

[0062]

[0063] Step 52, reduce the dimension of the relay suction decision parameter optimization problem, and construct an integrated objective function expressed as:

[0064]

[0065] Step 6: Solving the Pareto optimal solution set and screening the optimal parameter combination:

[0066] Step 61: Randomly generate an initial particle swarm:

[0067]

[0068] in, and They represent the initial particle position and initial particle velocity, v max is the maximum speed limit constant, Uniform() means taking a random value within the range;

[0069] Step 62, the position and velocity of the particle are updated at each iteration as follows:

[0070]

[0071] in, and They represent the particle position and particle velocity at the tth iteration, w is the inertia weight constant, c 1 and c 2 is the learning factor constant, r 1 and r 2 is a random number uniformly distributed in the interval [0,1];

[0072] Step 63, set up an archive to store Pareto non-dominated solutions at all times, and stop after the set number of iterations. At this time, the archive is close to the Pareto optimal solution set;

[0073] Step 64: In the optimal solution set, the trade-off between the mean value and the standard deviation of the suction force at point A and point B is weighed according to the actual situation, and the desired optimal solution is screened out, which is the optimized decision parameter combination.

[0074] Compared with the prior art, the present invention has the following advantages:

[0075] The present invention determines the combination samples of decision parameters such as part size parameters and assembly parameters by random sampling, and uses the finite element simulation method to calculate the suction results of these decision parameter combinations; obtains a fast calculation model of suction by establishing multiple models and stacking them, and limits the standard deviation of each decision parameter itself by the processing technology in actual production, and calculates the standard deviation of suction under the influence of each decision parameter combination by combining the uniform sampling method under normal distribution with the fast calculation model; regards the parameter optimization problem as a multi-objective optimization problem, constructs the ratio of the suction standard deviation to the suction mean at the two key positions of the armature as the optimization objective function to reduce the dimension of the optimization problem, takes the decision parameter range in actual processing as a constraint, obtains the optimal solution set by the Pareto optimization method, and selects the optimal parameter combination according to the actual product situation. In summary, unlike other parameter optimization methods, the present invention establishes a fast calculation model of suction, takes into account the constraints in actual engineering applications, truly approaches the optimal parameter combination, reduces suction fluctuations while optimizing the suction mean, and has the advantages of good overall optimization effect, objective results, and low time and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 A flowchart of a multi-objective parameter optimization method for electromagnetic relays that takes into account both performance indicators and quality consistency;

[0077] Figure 2 Schematic diagram of the key positions of the relay armature. DETAILED DESCRIPTION

[0078] The technical solution of the present invention is further described below in conjunction with the accompanying drawings, but is not limited thereto. Any modification or equivalent replacement of the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention should be included in the protection scope of the present invention.

[0079] The present invention provides a multi-objective parameter optimization design method for electromagnetic relays that takes into account both performance indicators and quality consistency. Figure 1 As shown, the following steps are included:

[0080] Step 1: Randomly sample and determine the decision parameter combination sample:

[0081] During the relay closing process, the relationship between the suction reaction force on the armature and the displacement of the armature is as follows: Figure 2 As shown in the figure, when the reaction force is considered to be fixed, the fluctuation of the suction force directly determines the fluctuation of the pull-in voltage. Therefore, in the parameter optimization design of the electromagnetic relay, in order to reduce the fluctuation of the product pull-in voltage index and thus improve the product quality consistency, the suction force of the batch product should be increased as much as possible, while reducing the standard deviation of the suction force. Take the two points A and B in the figure where the suction and reaction force curves are most likely to intersect, and define them as the key points of the armature position. Since the part size, assembly parameters, etc. of the relay show normal distribution fluctuations due to machining, the suction force at points A and B also shows normal distribution fluctuations. If the mean of the suction force distribution at points A and B can be made as large as possible and the standard deviation as small as possible, thereby reducing the probability that the suction force is less than the reaction force, it is possible to reduce the pull-in voltage fluctuation while optimizing the pull-in voltage performance index and improve the product quality consistency.

[0082] The influence of decision parameters such as part size and assembly parameters on the suction force of the electromagnetic system can be expressed as:

[0083]

[0084] Where x is the armature position, x A and x B Respectively represent the armature position point A and point B, F EMF (x A ,z) and F EMF (x B , z) represent the relationship between the suction of point A and point B affected by the decision parameters, z is the row vector representing the combination of decision parameters, z i represents the i-th decision parameter, and n represents the total number of decision parameters.

[0085] Affected by the processing technology, etc., each decision parameter obeys the normal distribution:

[0086]

[0087] in, and represent the mean and standard deviation of the normal distribution of the i-th decision parameter respectively.

[0088] Define the decision parameter space as [z i,min ,z i,max ], (i=1,2,...,n) n-dimensional hypercube, and for each decision parameter z i The value range is divided into M layers of equal width, and the width of each layer can be expressed as:

[0089]

[0090] The endpoints of layer j can be expressed as:

[0091] z i,j =z i,min +(j-1)·Δz i ,j=1,2,...,M

[0092] For each decision parameter z i , uniformly extract a sample point from each layer:

[0093]

[0094] Among them, U i,j is a random number uniformly drawn from the interval [0,1). The sampling results of each decision parameter are randomly arranged and combined to obtain the decision parameter combination training sample matrix:

[0095]

[0096] Among them, any k-th row of the matrix Z k,· They are all a combination of decision parameters.

[0097] Repeat the above operation to obtain the decision parameter combination test sample matrix T.

[0098] Step 2: Calculate the suction force of the parameter combination sample using the finite element simulation method:

[0099] The finite element simulation method is used to solve the suction force F of points A and B under the decision parameter combination of each row of the decision parameter combination training sample matrix Z and the decision parameter combination test sample matrix T. EMF (x A ,Z k,· ), F EMF (x A ,T k,· ) and F EMF (x B ,Z k,· ), F EMF (x B ,Tk,· ). Among them, the decision parameter combination training sample matrix and its output data set can be expressed as matrix X:

[0100]

[0101] Divide the matrix X into two matrices by row, including the training set X 1:h,· and validation set X h+1:M,· , where h = round(0.8M), round() means rounding to the nearest integer, that is, the training set accounts for 80% of the data set and is used to train the fast computing model; the validation set accounts for 20% of the data set and is used for validation during the model training process, real-time evaluation of the model generalization ability, and adaptive adjustment of hyperparameters. Similarly, the decision parameter combination test sample matrix and its output data set can be expressed as a matrix Y, which is used as a test set to evaluate the established fast computing model.

[0102]

[0103] Step 3: Establish a fast calculation model for suction force of multi-model stacking:

[0104] First, using the same data set, two basic models were established using two different methods, numbered as model 1 and model 2, denoted as C and 1 (x,z) and C 2 (x,z).

[0105] When training model 1, the main idea is to obtain the calculation result by weighted average of each known data point. The model weight to be determined is represented by λ a , the model is expressed as:

[0106]

[0107] Then, the model weight λ is solved by minimizing the covariance matrix a , we can list the matrix equation:

[0108]

[0109] Where Cov(,) represents the covariance. Solving it gives the model weight λ a and the Lagrangian constant μ. In addition, these covariance functions have hyperparameters such as length scale and noise variance. The best hyperparameters are determined by minimizing the prediction error using the validation set data. The prediction error can be expressed as:

[0110]

[0111] Among them, θ is the hyperparameter vector, C 1 (x,Zh+1:M,· ) is the output matrix of the validation set, and Cov() is the covariance matrix. Minimizing the error function can yield the optimal hyperparameters.

[0112] When training model No. 2, the main idea is to find the optimal hyperplane by minimizing the loss function. The model is expressed as:

[0113] C 2 (x,z a )=w·(x,Z a,· )+b

[0114] Among them, w is the weight vector to be determined, and b is the bias term to be determined. The coefficients to be determined can be determined by constructing and minimizing the objective function. The objective function and its constraints can be expressed as:

[0115]

[0116] Among them, ξ a and is a slack variable, c is a regularization parameter, and δ is an upper limit constant of the error, which is set according to the magnitude of the model output. By solving this minimization problem, the weight vector and the undetermined bias term of the model can be obtained. In addition, the regularization parameter of the model is optimized using the validation set, and the prediction error function of the model can be expressed as:

[0117]

[0118] The optimal hyperparameters can be obtained by minimizing the error function.

[0119] Then, in order to make the advantages and disadvantages of the two basic models complement each other under different inputs, so as to obtain an output effect closer to the real value, the two established basic models are stacked to train the final suction fast calculation model. The suction fast calculation model is expressed as:

[0120] C(x,z a )=β 1 C 1 (x,z a )+β 2 C 2 (x,z a )

[0121] Among them, β 1 and β 2 are the weight parameters of the two basic models. The optimal weight parameters can be solved by minimizing the prediction error. The prediction error of the suction rapid calculation model is expressed as:

[0122]

[0123] Among them, α is the regularization parameter, which is adjusted according to the actual performance of the model to prevent the model from overfitting. Minimizing the error function can solve the model weight parameter β 1 and β 2 .

[0124] The mean square error and goodness of fit of the suction rapid calculation model are calculated using the test sample matrix T, and the suction rapid calculation model is evaluated.

[0125] Step 4: Calculation of suction standard deviation with uniform sampling and introduction of normal distribution weights:

[0126] Since each decision parameter obeys the normal distribution, its fluctuation affects the suction force so that the suction force also obeys the normal distribution:

[0127] F EMF ~N(μ F ,σ F 2 )

[0128] Among them, μ F and σ F represent the mean and standard deviation of the suction force distribution, respectively.

[0129] The suction fast calculation model is used to calculate the mean and standard deviation of the suction at point A and point B, and the decision parameter combination z * After inputting the suction quick calculation model, the output result is the average suction value of point A and point B:

[0130]

[0131] At each decision parameter z i of The decision parameter combinations are uniformly sampled within the range, and each decision parameter combination sample is expressed as:

[0132]

[0133] in, represents the lth sample point of the ith decision parameter.

[0134] The normal distribution probability density function of the decision parameter is used for weighting and the standard deviation of the suction force at point A and point B is calculated:

[0135]

[0136] Step 5: Objective function establishment and optimization problem dimensionality reduction:

[0137] The parameter optimization problem is defined as:

[0138]

[0139] The goal is to maximize the mean suction force and minimize the standard deviation of point A and point B, which is a four-dimensional optimization problem. Since the target dimension is too high and the calculation is too complicated, it is necessary to reduce the dimension of the parameter optimization problem and construct the integrated objective function, which is expressed as:

[0140]

[0141] Among them, the constructed objective function is the ratio of the standard deviation of point A and point B to the suction. By minimizing this ratio, we can find the decision parameter combination that minimizes their respective standard deviations and maximizes their means.

[0142] Step 6: Solving the Pareto optimal solution set and screening the optimal parameter combination:

[0143] The Pareto optimization method is used to optimize the above parameter optimization problem. First, the initial particle swarm is randomly generated:

[0144]

[0145] in, and They represent the initial particle position and initial particle velocity, v max It is the maximum speed limit constant. Uniform() means taking a random value within the range.

[0146] The particle position and velocity updates at each iteration can be expressed as:

[0147]

[0148] in, and They represent the particle position and particle velocity at the tth iteration, w is the inertia weight constant, c 1 and c 2 is the learning factor constant. The former controls the degree of guidance to the individual optimal position, while the latter controls the degree of guidance to the global optimal position. 1 and r 2 is a random number uniformly distributed in the interval [0,1]. Set the archive to store Pareto non-dominated solutions at all times, and stop after the set number of iterations, at which point the archive is close to the Pareto optimal solution set.

[0149] In the optimal solution set, the trade-off between the mean and standard deviation of the suction between point A and point B is weighed according to the actual situation, and the required optimal solution is screened out, which is the optimized decision parameter combination.

[0150] Therefore, the multi-objective parameter optimization design of electromagnetic relay considering both performance index and quality consistency is completed.

[0151] Example:

[0152] A certain type of relay uses the method of the present invention to optimize the suction parameters:

[0153] According to the actual situation of product processing technology, there are 4 adjustable suction decision parameters of the electromagnetic system, that is, n = 4, which are armature width, yoke length, core radius and base plate width. According to the statistical results of the actual test of the machining tolerance of each part, combined with the structural size limit of the electromagnetic system, the standard deviation and value range of the four decision parameters are shown in Table 1:

[0154] Table 1 Standard deviation and value range of suction decision parameters of a certain type of relay

[0155]

[0156] Before and after the optimization using the method of the present invention, the decision parameter values ​​of the product, the mean and standard deviation of the suction force at point A and point B are shown in Table 2:

[0157] Table 2 Data comparison of a certain type of relay before and after optimization

[0158]

[0159] It can be seen that after using the method of the present invention, the mean suction force of a certain model of relay is significantly improved at point A and point B, and the standard deviation of suction force is significantly reduced at point A and point B, indicating that the method of the present invention can effectively reduce the standard deviation of suction force while ensuring that the mean suction force only increases and does not decrease, while ensuring performance indicators and quality consistency, and has a good optimization effect.

Claims

1. A multi-objective parameter optimization design method for electromagnetic relays that takes into account both performance indicators and quality consistency, characterized in that The method comprises the following steps: Step 1: Randomly sample and determine the decision parameter combination sample: Step 11, take two points A and B where the suction reaction force curve is most likely to intersect, and define them as the key points of the armature position; Step 12: The influence of the decision parameters on the suction force of the electromagnetic system is expressed as: Where x is the armature position, x A and x B Respectively represent the armature position point A and point B, F EMF (x A ,z) and F EMF (x B , z) represent the relationship between the suction of point A and point B affected by the decision parameters, z is the row vector representing the combination of decision parameters, z i represents the i-th decision parameter, and n represents the total number of decision parameters; Step 13: Define the decision parameter space as [z i,min ,z i,max ] n-dimensional hypercube, i = 1, 2, ..., n, z i,min and z i,max Represent the minimum and maximum values ​​of the i-th decision parameter, respectively. For each decision parameter z i Divide its value range into M layers of equal width; Step 14: For each decision parameter z i , uniformly extract a sample point from each layer: Among them, U i,j is a random number uniformly drawn from the interval [0,1); Step 15: Randomly arrange and combine the sampling results of each decision parameter to obtain the decision parameter combination training sample matrix: Among them, any k-th row of the matrix Z k,· They are all a combination of decision parameters; Step 16: Repeat steps 13 to 15 to obtain the decision parameter combination test sample matrix: in, It represents the test sample point randomly selected from the Mth layer for the nth decision parameter; Step 2: Calculate the suction force of the parameter combination sample using the finite element simulation method: Step 21: Using the finite element simulation calculation method, solve the suction force F of point A and point B under the decision parameter combination of each row of the decision parameter combination training sample matrix Z and the decision parameter combination test sample matrix T. EMF (x A ,Z k,· ), F EMF (x A ,T k,· ) and F EMF (x B ,Z k,· ), F EMF (x B ,T k,· ); Step 22: The decision parameter combination training sample matrix Z and its output data set are represented as matrix X. The matrix X is divided into two matrices by row, including the training set X 1:h,· and validation set X h+1:M,· , where the training set is used to train the fast computing model; the validation set is used to verify the model during training, evaluate the generalization ability of the model in real time, and adaptively adjust the hyperparameters; Step 23, the decision parameter combination test sample matrix T and its output data set are represented as a matrix Y, which itself is used as a test set to evaluate the established fast calculation model; Step 3: Establish a fast calculation model for suction force of multi-model stacking: Step 31: Using the same data set, two basic models are established using two different methods, numbered as model 1 and model 2, and represented as C1(x,z) and C2(x,z) respectively; Step 32: When training model 1, the calculation result is obtained by weighted average of each known data point. The model weight to be determined is represented by λ a , the model is expressed as: Solve the model weight λ by minimizing the covariance matrix a , list the matrix equation: Among them, Cov(,) represents the covariance, and the model weight λ is obtained by solving a and the Lagrange constant μ, and determine the best hyperparameters by minimizing the prediction error using the validation set data; Step 33, when training model No. 2, the optimal hyperplane is found by minimizing the loss function. The model is expressed as: C2(x,z a )=w (x,Z a,· )+b Among them, w is the undetermined weight vector, b is the undetermined bias term, and the undetermined coefficients are determined by constructing and minimizing the objective function. The objective function and its constraints are expressed as: Among them, ξ a and is the slack variable, c is the regularization parameter, and δ is the error upper limit constant. By solving this minimization problem, we can obtain the undetermined weight vector and undetermined bias term of the model. We can use the validation set to optimize the regularization parameter of the model and determine the optimal hyperparameter. Step 34: stack the two established basic models to train the final suction rapid calculation model, which is expressed as: C(x,z a )=β1C1(x,z a )+β2C2(x,z a ) Among them, β1 and β2 are the weight parameters of the two basic models, and the optimal weight parameters are solved by minimizing the prediction error; Step 35, using the decision parameter combination test sample matrix T to calculate the mean square error and goodness of fit of the suction rapid calculation model, and evaluate the suction rapid calculation model; Step 4: Calculation of suction standard deviation with uniform sampling and introduction of normal distribution weights Step 41: Since each decision parameter obeys the normal distribution, its fluctuation affects the suction force so that the suction force also obeys the normal distribution: F EMF ~N(μ F ,s F 2 ) Among them, μ F and σ F represent the mean and standard deviation of the suction force distribution, respectively; Step 42: Use the suction rapid calculation model to calculate the mean and standard deviation of the suction at point A and point B, and combine the decision parameters z * After inputting the suction quick calculation model, the output result is the average suction value of point A and point B: Step 43: At each decision parameter z i of The decision parameter combinations are uniformly sampled within the range, and each decision parameter combination sample is expressed as: in, represents the lth sample point of the i-th decision parameter; Step 44: Use the normal distribution probability density function of the decision parameter for weighting and calculate the standard deviation of the suction force at point A and point B: Step 5: Objective function establishment and optimization problem dimensionality reduction: Step 51: Define the parameter optimization problem as: Step 52, reduce the dimension of the relay suction decision parameter optimization problem, and construct an integrated objective function expressed as: Step 6: Solving the Pareto optimal solution set and screening the optimal parameter combination: Step 61: Randomly generate an initial particle swarm: in, and They represent the initial particle position and initial particle velocity, v max is the maximum speed limit constant, Uniform() means taking a random value within the range; Step 62, the position and velocity of the particle are updated at each iteration as follows: in, and They represent the particle position and particle velocity at the tth iteration, respectively, w is the inertia weight constant, c1 and c2 are learning factor constants, r1 and r2 are random numbers uniformly distributed in the interval [0,1]; Step 63, set up an archive to store Pareto non-dominated solutions at all times, and stop after the set number of iterations. At this time, the archive is close to the Pareto optimal solution set; Step 64: In the optimal solution set, the trade-off between the mean value and the standard deviation of the suction force at point A and point B is weighed according to the actual situation, and the desired optimal solution is screened out, which is the optimized decision parameter combination.

2. The electromagnetic relay multi-objective parameter optimization design method considering both performance indicators and quality consistency according to claim 1 is characterized in that In step 13, the width of each layer is expressed as: The endpoints of the jth layer are represented as: z i,j =z i,min +(j-1)·Δz i ,j=1,2,…,M。 3. The electromagnetic relay multi-objective parameter optimization design method considering both performance indicators and quality consistency according to claim 1 is characterized in that In step 22, the matrix X is expressed as:

4. The electromagnetic relay multi-objective parameter optimization design method considering both performance indicators and quality consistency according to claim 1 is characterized in that In step 23, the matrix Y is expressed as:

Images