Electromechanical system simulation parameter multi-working-condition calibration method

Abstract

The invention provides an electromechanical system simulation parameter multi-working-condition calibration method. The method comprises the following steps: constructing a plurality of objective functions by taking the highest consistency of simulation data output by an electromechanical system simulation model under each working condition and actual measurement data output by an actual electromechanical system as an objective; performing multi-objective optimization on the plurality of objective functions, and updating the experience knowledge base according to a multi-objective optimization result; performing non-dominated sorting and clustering on each solution in the experience knowledge base, and sorting each subspace obtained by clustering according to the degree of congestion to determine a plurality of target subspaces; constructing an agent model in each target subspace, carrying out Bayesian optimization, and updating an external archive and an experience knowledge base of multi-target optimization according to a Bayesian optimization result; and circulation is carried out according to the updated external archive and the experience knowledge base, so that a simulation parameter multi-working-condition calibration result is obtained. According to the method, the calculation cost can be reduced, the calculation efficiency can be improved, and meanwhile the universality, robustness and prediction precision of an electromechanical system simulation model are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of simulation model calibration, and in particular to a multi-operating condition calibration method for electromechanical system simulation parameters. Background Art

[0002] Electromechanical systems are widely used in manufacturing, automotive, aerospace, medical equipment, consumer electronics, energy systems and other fields. They are the cross-integration of mechanical engineering, electronic engineering, control engineering, computer science and information technology, and are highly integrated. Due to the high integration of electromechanical systems, most of the functional and performance tests need to be conducted with the help of simulation models. Therefore, it is necessary to establish an accurate electromechanical system simulation model.

[0003] The essence of the electromechanical system simulation model is the approximation of the actual electromechanical system. In order to establish an accurate electromechanical system simulation model, it is usually necessary to first evaluate the consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system. When the consistency is poor, the simulation parameters of the electromechanical system simulation model are adjusted to regain the simulation data, and then the consistency is evaluated again until the simulation data and the measured data achieve a high degree of consistency. This process is called the simulation parameter calibration of the electromechanical system simulation model.

[0004] In the process of calibrating the simulation parameters of the electromechanical system simulation model, the inventors found that the performance of the actual electromechanical system under different working conditions is usually variable, however, the traditional simulation parameter calibration method is usually calibrated based on a single working condition, which results in similar performance under multiple working conditions when the electromechanical system simulation model after calibration is used for experimental verification, which is inconsistent with the actual performance of the actual electromechanical system. That is, the accuracy and adaptability of the simulation parameter calibration method of the traditional electromechanical system simulation model under multiple working conditions are not high. Moreover, since the multi-working condition scenario also has the characteristics of high dimension, large data volume, and a wide and complex solution space of simulation parameters, the calibration of the simulation parameters of the electromechanical system simulation model based on multiple working conditions has the problems of high computational cost and low efficiency. Summary of the invention

[0005] The embodiment of the present invention provides a multi-condition calibration method for electromechanical system simulation parameters to solve the problem that it is difficult to simultaneously take into account the accuracy, adaptability, calculation cost and calculation efficiency of the simulation model when calibrating the current simulation parameters.

[0006] In a first aspect, an embodiment of the present invention provides a method for calibrating a multi-condition electromechanical system simulation parameter, comprising:

[0007] With the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition, multiple objective functions are constructed;

[0008] Taking each simulation parameter of the electromechanical system simulation model as a decision vector, multi-objective optimization is performed on the plurality of objective functions, and the experience knowledge base is updated according to the multi-objective optimization results;

[0009] Performing non-dominated sorting on each solution of the simulation parameters of the electromechanical system simulation model corresponding to the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets;

[0010] Clustering the Pareto optimal solution set and the other solution sets respectively, and recording each sub-solution set in the clustering result as a subspace;

[0011] sorting the subspaces according to the congestion degree of each subspace, and determining a plurality of target subspaces from the subspaces according to the sorting results;

[0012] In each of the target subspaces, a proxy model is constructed for each of the target functions, and Bayesian optimization is performed based on each of the proxy models with the expected hypervolume improvement as the acquisition function, and the external archive of multi-objective optimization and the empirical knowledge base are updated based on the Bayesian optimization results;

[0013] According to the updated external archive and the empirical knowledge base, the step of "performing multi-objective optimization on the multiple objective functions" and subsequent steps are re-executed until the termination condition is met, and the multi-condition calibration results of the simulation parameters of the electromechanical system simulation model are obtained according to the global optimal solution of the multi-objective optimization.

[0014] In a possible implementation, each simulation parameter of the electromechanical system simulation model is used as a decision vector, a plurality of objective functions are multi-objective optimized, and an experience knowledge base is updated according to the multi-objective optimization result, including:

[0015] Taking each simulation parameter of the electromechanical system simulation model as a decision vector, multi-objective optimization is performed on the plurality of objective functions to obtain an external archive after the multi-objective optimization;

[0016] The empirical knowledge base is updated according to the external archive.

[0017] In a possible implementation, the Pareto optimal solution set and the other solution sets are clustered respectively, and each sub-solution set in the clustering result is recorded as a subspace, including:

[0018] Obtaining the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained;

[0019] Determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets according to the number of iterations and the maximum number of iterations of the multi-objective optimization;

[0020] The Pareto optimal solution set is clustered according to the first number of clusters, the other solution sets are clustered according to the second number of clusters, and each sub-solution set in the clustering result is recorded as a subspace.

[0021] In a possible implementation, determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets according to the number of iterations and the maximum number of iterations of the multi-objective optimization includes:

[0022] Calculating the ratio of the number of iterations to the maximum number of iterations of the multi-objective optimization;

[0023] comparing the ratio with a first threshold and a second threshold, respectively;

[0024] The first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets are determined according to the comparison result.

[0025] In a possible implementation manner, after determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets, the method further includes:

[0026] Determine whether the first number of clusters is less than the number of solutions in the Pareto optimal solution set, and determine whether the second number of clusters is less than the number of solutions in the other solution set;

[0027] If the first number of clusters is less than the number of solutions in the Pareto optimal solution set, clustering the Pareto optimal solution set according to the first number of clusters;

[0028] If the first cluster number is greater than or equal to the number of solutions in the Pareto optimal solution set, clustering the Pareto optimal solution set according to the number of solutions in the Pareto optimal solution set;

[0029] If the second number of clusters is less than the number of solutions in the other solution sets, clustering the other solution sets according to the second number of clusters;

[0030] If the second cluster number is greater than or equal to the number of solutions in the other solution sets, clustering the other solution sets according to the number of solutions in the other solution sets.

[0031] In a possible implementation, sorting the subspaces according to the congestion degree of each subspace, and determining a plurality of target subspaces from the subspaces according to the sorting result, including:

[0032] Sorting the subspaces according to the congestion degree of each subspace to obtain a sorting result;

[0033] Obtaining the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained, and determining a dynamic congestion threshold according to the number of iterations and the maximum number of iterations of the multi-objective optimization;

[0034] Subspaces whose congestion degree is greater than the dynamic congestion degree threshold are screened from the sorting results to obtain a plurality of target subspaces.

[0035] In a possible implementation, subspaces whose congestion is greater than the dynamic congestion threshold are screened from the sorting results to obtain multiple target subspaces, including:

[0036] Filtering a subspace whose congestion degree is greater than the dynamic congestion degree threshold from the sorting results as a candidate subspace;

[0037] According to the crowding degree of the candidate subspaces, candidate subspaces with similar crowding degrees in the candidate subspaces are merged to obtain a plurality of target subspaces.

[0038] In a second aspect, an embodiment of the present invention provides a multi-condition calibration device for electromechanical system simulation parameters, comprising:

[0039] An objective function construction module is used to construct multiple objective functions with the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition;

[0040] A first optimization module is used to use each simulation parameter of the electromechanical system simulation model as a decision vector, perform multi-objective optimization on the plurality of objective functions, and update the experience knowledge base according to the multi-objective optimization results;

[0041] A non-dominated sorting module is used to perform non-dominated sorting on each solution of the simulation parameters of the electromechanical system simulation model corresponding to the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets;

[0042] A first subspace partitioning module is used to cluster the Pareto optimal solution set and the other solution sets respectively, and record each sub-solution set in the clustering result as a subspace;

[0043] A second subspace partitioning module is used to sort the subspaces according to the congestion degree of each subspace, and determine a plurality of target subspaces from the subspaces according to the sorting result;

[0044] A second optimization module is used to construct a proxy model for each objective function in each objective subspace, perform Bayesian optimization based on each proxy model with expected hypervolume improvement as an acquisition function, and update the external archive of multi-objective optimization and the empirical knowledge base based on the Bayesian optimization result;

[0045] A cyclic calibration module is used to re-execute the step of "performing multi-objective optimization on multiple objective functions" and subsequent steps according to the updated external archive and the empirical knowledge base until the termination condition is met, and obtain the multi-condition calibration results of the simulation parameters of the electromechanical system simulation model according to the global optimal solution of the multi-objective optimization.

[0046] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0048] An embodiment of the present invention provides a multi-working condition calibration method for electromechanical system simulation parameters. The method first takes the highest consistency between the simulation data output by the electromechanical system simulation model under each working condition and the measured data output by the actual electromechanical system as the goal, constructs multiple objective functions, and uses each simulation parameter of the electromechanical system simulation model as a decision vector to perform multi-objective optimization on the multiple objective functions. The empirical knowledge base is updated according to the multi-objective optimization results, and population optimization information can be added to the empirical knowledge base. On this basis, by performing non-dominated sorting, clustering and congestion sorting on each solution in the empirical knowledge base, the empirical knowledge base can be divided into multiple target subspaces when the optimal solution cannot be determined under multiple working conditions. Then, in each target subspace, a proxy model is constructed for each objective function and Bayesian optimization is performed. The external archive of the multi-objective optimization is updated according to the Bayesian optimization results, thereby guiding the multi-objective optimization based on each proxy model. Through the collaborative optimization of multi-objective optimization and Bayesian optimization, the computational cost of simulation parameter calibration under multiple working conditions is reduced and the computational efficiency is improved. The optimized and calibrated electromechanical system simulation model can output more accurate simulation data under multiple working conditions, thereby improving the versatility, robustness and prediction accuracy of the electromechanical system simulation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0050] Figure 1It is a flow chart for implementing a multi-condition calibration method for electromechanical system simulation parameters provided by an embodiment of the present invention;

[0051] Figure 2 It is a block diagram of an implementation method of a multi-condition calibration method for electromechanical system simulation parameters provided by an embodiment of the present invention;

[0052] Figure 3 It is a structural schematic diagram of a multi-condition calibration device for electromechanical system simulation parameters provided by an embodiment of the present invention;

[0053] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0055] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0056] See also Figure 1 , which shows a flowchart of the implementation of the electromechanical system simulation parameter multi-condition calibration method provided by an embodiment of the present invention, which is described in detail as follows:

[0057] In step 101, a plurality of objective functions are constructed with the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition.

[0058] For example, assuming there are K working conditions, K objective functions can be constructed, each of which can be Where k = 1, 2, ..., K, ω k,i is the weight coefficient of the ith indicator under the kth working condition, s k,i is the consistency evaluation score of the i-th indicator under the k-th working condition.

[0059] In step 102, each simulation parameter of the electromechanical system simulation model is used as a decision vector, a multi-objective optimization is performed on a plurality of objective functions, and an experience knowledge base is updated according to the multi-objective optimization result.

[0060] Exemplarily, each simulation parameter of the electromechanical system simulation model can be used as a decision vector to perform multi-objective optimization on multiple objective functions to obtain an external archive after the multi-objective optimization; and the experience knowledge base can be updated based on the external archive.

[0061] Combination Figure 2 As shown, a multi-objective particle swarm optimization (MOPSO) can be used for multi-objective optimization.

[0062] When performing multi-objective optimization based on MOPSO, initialization is first performed to initialize the population size, the speed and position of each particle, the particle's historical optimal solution, external archives, the global optimal solution, and the empirical knowledge base.

[0063] The initialized global optimal solution can be selected randomly or according to specific rules from the initialized external archive.

[0064] Then, based on the initialized particle speed and position, combined with the speed update formula and the position update formula, the particle speed and position are updated using the initialized particle historical optimal solution and the initialized global optimal solution, and the fitness value corresponding to the particle update is calculated, that is, the values ​​of multiple objective functions corresponding to the particle update.

[0065] According to the corresponding fitness value after the particle is updated, the particle's historical optimal solution, external archive, and global optimal solution can be updated.

[0066] According to the updated external archive, the empirical knowledge base can be updated, so that the historical optimization information obtained from each multi-objective optimization can be added to the empirical knowledge base, so that each subspace can be explored more deeply based on the empirical knowledge base to ensure the diversity and global coverage of the solution.

[0067] In step 103, non-dominated sorting is performed on each solution of the simulation parameters of the electromechanical system simulation model corresponding to the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets.

[0068] Among them, non-dominated sorting is a sorting method in the field of multi-objective optimization. In multi-objective optimization problems, there is usually no solution that can optimize all objective functions at the same time. Therefore, it is necessary to find a set of solutions that are better than other solutions in one objective and at least not worse in other objectives. Such solutions are called Pareto optimal solutions or non-dominated solutions.

[0069] For example, if solution A is not worse than solution B in all objectives and is better than solution B in at least one objective, then solution A is called non-dominated solution B. Based on this, each solution of the simulation parameters corresponding to the electromechanical system simulation model in the empirical knowledge base can be non-dominated sorted to obtain the Pareto optimal solution set and other solution sets.

[0070] In step 104, the Pareto optimal solution set and other solution sets are clustered respectively, and each sub-solution set in the clustering result is recorded as a subspace.

[0071] In this embodiment, on the basis of multi-objective optimization, considering that the objective function of the electromechanical system simulation model is usually not differentiable, therefore, considering building a proxy model to assist in multi-objective optimization. At the same time, considering that as the experience knowledge base is updated, the number of samples in the experience knowledge base will gradually increase, which will lead to a sharp increase in the computational cost and computational complexity of building the proxy module, it is considered that after dividing the experience knowledge base into the Pareto optimal solution set and other solution sets, the computational cost and computational complexity of building the proxy model can be reduced by dividing the Pareto optimal solution set and other solution sets into subspaces.

[0072] Among them, when dividing the subspace, since this embodiment is a multi-objective optimization, it is difficult to determine the optimal solution that optimizes multiple objectives in the Pareto optimal solution set and other solution sets, that is, it is difficult to divide the Pareto optimal solution set and other solution sets into subspaces layer by layer based on the optimal solution. Therefore, it is considered to divide the Pareto optimal solution set and other solution sets into subspaces according to similarity by clustering. For example, Figure 2 As shown, the Pareto optimal solution set and other solution sets can be clustered based on K-Means clustering, and each sub-solution set in the clustering result can be recorded as a subspace.

[0073] This embodiment divides the Pareto optimal solution set and other solution sets into multiple subspaces by clustering, which helps to distinguish different optimization areas and provide focused search opportunities for each area.

[0074] In step 105, the subspaces are sorted according to the congestion degree of each subspace, and a plurality of target subspaces are determined from the subspaces according to the sorting result.

[0075] In this embodiment, after obtaining multiple subspaces, in order to effectively identify the key areas in the solution space, the key areas are optimized in depth first. Considering the fact that the solutions in the Pareto optimal solution set are usually more sparse than the solutions in other solution sets, these subspaces can be sorted according to the degree of congestion (that is, the degree of sparsity) to ensure that the subspaces of the Pareto optimal solution set are given priority in the subsequent optimization process.

[0076] By determining multiple target subspaces through this embodiment, it is possible to effectively distinguish and prioritize the subspaces of the Pareto optimal solution set, ensuring that high-quality solutions are explored first, while reducing the training time of subsequent proxy models and improving parallel processing capabilities. This not only optimizes the exploration efficiency of the solution space, but also improves the overall solution efficiency through localized processing, significantly improving the performance of multi-condition optimization.

[0077] In step 106, within each target subspace, a proxy model is constructed for each target function, and Bayesian optimization is performed based on each proxy model with the expected hypervolume improvement as the acquisition function, and the external archive and experience knowledge base of the multi-objective optimization are updated based on the Bayesian optimization results.

[0078] Combination Figure 2 ,After dividing the subspace and determining the target subspace, the expected hypervolume improvement (EHI) can be used as the acquisition function in each target subspace to guide the search process and optimize the proxy model by maximizing the increment of the Pareto hypervolume.

[0079] Among them, EHI is a measure of the average increase in the hypervolume of the Pareto frontier that may be brought about by selecting a new sampling point. The hypervolume index is a measure of multi-objective optimization performance that comprehensively reflects the quality and distribution of the Pareto frontier of multi-objective optimization. The hypervolume index refers to the volume composed of the area between the Pareto frontier and a reference point. The larger the hypervolume index, the closer the Pareto frontier is to the true optimal solution.

[0080] In this embodiment, in each target subspace, a proxy model is constructed for each objective function. According to each proxy model, Bayesian optimization is performed with the expected hypervolume improvement as the acquisition function, and then the expected hypervolume improvement is evaluated by the proxy model to further optimize the Pareto frontier. Through EHI, the sampling strategy is dynamically adjusted to ensure that the new sampling points can effectively expand the Pareto optimal solution set and improve the overall optimization efficiency.

[0081] In step 107, based on the updated external archive and empirical knowledge base, the step of "performing multi-objective optimization on multiple objective functions" and subsequent steps are re-executed until the termination condition is met, and the multi-condition calibration results of the simulation parameters of the electromechanical system simulation model are obtained based on the global optimal solution of the multi-objective optimization.

[0082] Combination Figure 2 After updating the external archive and empirical knowledge base of multi-objective optimization according to the Bayesian optimization results, through continuous iterative sampling and updating, potential new points can be continuously introduced into the Pareto optimal solution set, thereby effectively promoting the search for the global optimal solution, thereby improving the calibration efficiency and effect of the electromechanical system simulation model under multiple working conditions, overcoming the limitations of traditional simulation parameter calibration methods in multi-objective optimization scenarios, and significantly improving the global search capability and solution quality of the optimization process.

[0083] The embodiment of the present invention first takes the highest consistency between the simulation data output by the electromechanical system simulation model under each working condition and the measured data output by the actual electromechanical system as the goal, constructs multiple objective functions, and takes each simulation parameter of the electromechanical system simulation model as a decision vector, performs multi-objective optimization on the multiple objective functions, and updates the empirical knowledge base according to the multi-objective optimization results, and can add population optimization information to the empirical knowledge base. On this basis, by performing non-dominated sorting, clustering and crowding sorting on each solution in the empirical knowledge base, the empirical knowledge base can be divided into multiple target subspaces when the optimal solution cannot be determined under multiple working conditions, and then in each target subspace, a proxy model is constructed for each objective function and Bayesian optimization is performed, and the external archive of the multi-objective optimization is updated according to the Bayesian optimization results, thereby guiding the multi-objective optimization based on each proxy model, and then through the collaborative optimization of multi-objective optimization and Bayesian optimization, the computational cost of simulation parameter calibration under multiple working conditions is reduced and the computational efficiency is improved, and the optimized and calibrated electromechanical system simulation model can output more accurate simulation data under multiple working conditions, thereby improving the versatility, robustness and prediction accuracy of the electromechanical system simulation model.

[0084] In one embodiment, the Pareto optimal solution set and other solution sets are clustered respectively, and each sub-solution set in the clustering result is recorded as a subspace, which may include:

[0085] The number of iterations corresponding to the multi-objective optimization is obtained when the multi-objective optimization result is obtained; according to the number of iterations and the maximum number of iterations of the multi-objective optimization, the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to other solution sets are determined; the Pareto optimal solution set is clustered according to the first number of clusters, and the other solution sets are clustered according to the second number of clusters, and each sub-solution set in the clustering result is recorded as a subspace.

[0086] In this embodiment, considering that the number of samples in the empirical knowledge base will gradually increase with the iterative process of multi-objective optimization, in order to avoid the overall multi-objective optimization process from falling into the local optimum and accelerate the convergence speed, the current optimization stage can be evaluated by the number of iterations corresponding to the current multi-objective optimization and the maximum number of iterations of the multi-objective optimization, and different cluster numbers are determined for the Pareto optimal solution set and other solution sets at different optimization stages. For example, in the early stage of the optimization stage, a relatively small number of clusters is determined for the Pareto optimal solution set, and a relatively large number of clusters is determined for other solution sets, so as to obtain more subspaces on other solution sets, so as to expand the search range in the early stage of the optimization stage. In the late stage of the optimization stage, a relatively large number of clusters can be determined for the Pareto optimal solution set, and a relatively small number of clusters can be determined for other solution sets, so as to reduce the number of subspaces as a whole, and obtain more subspaces on the Pareto optimal solution set, so as to strengthen the search for the Pareto optimal solution set and focus on the subspace with higher confidence.

[0087] Exemplarily, the ratio of the number of iterations to the maximum number of iterations of the multi-objective optimization can be calculated; the ratio is compared with the first threshold and the second threshold, respectively; and the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets are determined based on the comparison results.

[0088] In this embodiment, by calculating the ratio of the number of iterations to the maximum number of iterations and comparing the ratio with the first threshold and the second threshold, it is possible to determine whether the current multi-objective optimization is in the early optimization stage, the middle optimization stage, or the late optimization stage, and then determine different numbers of clusters based on the different optimization stages of the current multi-objective optimization.

[0089] The first threshold and the second threshold can be selected according to actual conditions, and this embodiment does not limit this. For example, the first threshold can be 1 / 2, and the second threshold can be 2 / 3. Alternatively, the first threshold can be 2 / 3, and the second threshold can be 4 / 5, and so on.

[0090] Exemplarily, after determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets, the method may further include:

[0091] It is determined whether the number of the first clusters is less than the number of solutions in the Pareto optimal solution set, and it is determined whether the number of the second clusters is less than the number of solutions in the other solution sets.

[0092] If the first cluster number is less than the number of solutions in the Pareto optimal solution set, the Pareto optimal solution set is clustered according to the first cluster number.

[0093] If the first cluster number is greater than or equal to the number of solutions in the Pareto optimal solution set, the Pareto optimal solution set is clustered according to the number of solutions in the Pareto optimal solution set.

[0094] If the second cluster number is less than the number of solutions in other solution sets, the other solution sets are clustered according to the second cluster number.

[0095] If the second cluster number is greater than or equal to the number of solutions in other solution sets, the other solution sets are clustered according to the number of solutions in the other solution sets.

[0096] In this embodiment, the case where the number of samples in the empirical knowledge base is small is further considered. At this time, the number of solutions in the corresponding Pareto optimal solution set and the number of solutions in other solution sets are also relatively small. In order to fully explore the Pareto optimal solution set and other solution sets, when clustering in the initial stage, each solution in the Pareto optimal solution can be regarded as a class, or each solution in other solution sets can be regarded as a class.

[0097] In one embodiment, sorting the subspaces according to the congestion degree of each subspace, and determining a plurality of target subspaces from the subspaces according to the sorting results may include:

[0098] The subspaces are sorted according to the congestion of each subspace to obtain the sorting result; the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained, and the dynamic congestion threshold is determined according to the number of iterations and the maximum number of iterations of the multi-objective optimization; the subspaces whose congestion is greater than the dynamic congestion threshold are screened from the sorting result to obtain multiple target subspaces.

[0099] In this embodiment, in order to further determine the appropriate target subspace at different optimization stages, different dynamic congestion thresholds are determined according to different optimization stages based on the different numbers of clusters determined before clustering. For example, in the early stage of the optimization stage, a relatively small threshold can be determined so that each proxy model can fully explore as many target subspaces as possible. In the later stage of the optimization stage, a relatively large threshold can be determined for targeted exploration.

[0100] Optionally, subspaces whose congestion is greater than a dynamic congestion threshold are filtered from the sorting results to obtain multiple target subspaces, which may include:

[0101] The subspaces whose congestion is greater than the dynamic congestion threshold are selected from the sorting results as candidate subspaces; according to the congestion of the candidate subspaces, the candidate subspaces with similar congestion in each candidate subspace are merged to obtain multiple target subspaces.

[0102] In this embodiment, considering that after clustering the Pareto optimal solution set and other solution sets respectively, sub-solution sets with similar sparsity may be stored in the Pareto optimal solution set and other solution sets, that is, there are subspaces with similar congestion. Therefore, after screening the candidate subspaces through the dynamic congestion threshold, the candidate subspaces with similar congestion can also be merged to reduce the number of proxy models that need to be constructed.

[0103] In order to avoid excessive increase in computational cost or impact on computational efficiency when merging candidate subspaces, only candidate subspaces whose congestion is greater than a maximum congestion threshold may be merged to avoid excessive number of samples in the merged candidate subspaces affecting computational efficiency.

[0104] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0105] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0106] Figure 3 The schematic diagram of the structure of the electromechanical system simulation parameter multi-condition calibration device provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0107] like Figure 3 As shown, the multi-condition calibration device for electromechanical system simulation parameters includes: an objective function construction module 31, a first optimization module 32, a non-dominated sorting module 33, a first subspace division module 34, a second subspace division module 35, a second optimization module 36 and a cyclic calibration module 37.

[0108] An objective function construction module 31 is used to construct multiple objective functions with the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition;

[0109] A first optimization module 32 is used to use each simulation parameter of the electromechanical system simulation model as a decision vector, perform multi-objective optimization on the plurality of objective functions, and update the experience knowledge base according to the multi-objective optimization results;

[0110] A non-dominated sorting module 33 is used to perform non-dominated sorting on each solution of the simulation parameters of the electromechanical system simulation model in the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets;

[0111] A first subspace partitioning module 34 is used to cluster the Pareto optimal solution set and the other solution sets respectively, and record each sub-solution set in the clustering result as a subspace;

[0112] A second subspace division module 35 is used to sort the subspaces according to the congestion degree of each subspace, and determine a plurality of target subspaces from the subspaces according to the sorting result;

[0113] A second optimization module 36 is used to construct a proxy model for each objective function in each objective subspace, perform Bayesian optimization based on each proxy model with the expected hypervolume improvement as the acquisition function, and update the external archive of multi-objective optimization and the empirical knowledge base based on the Bayesian optimization result;

[0114] The cyclic calibration module 37 is used to re-execute the step of "performing multi-objective optimization on multiple objective functions" and subsequent steps according to the updated external archive and the empirical knowledge base until the termination condition is met, and obtain the multi-condition calibration results of the simulation parameters of the electromechanical system simulation model according to the global optimal solution of the multi-objective optimization.

[0115] The embodiment of the present invention first takes the highest consistency between the simulation data output by the electromechanical system simulation model under each working condition and the measured data output by the actual electromechanical system as the goal, constructs multiple objective functions, and takes each simulation parameter of the electromechanical system simulation model as a decision vector, performs multi-objective optimization on the multiple objective functions, and updates the empirical knowledge base according to the multi-objective optimization results, and can add population optimization information to the empirical knowledge base. On this basis, by performing non-dominated sorting, clustering and crowding sorting on each solution in the empirical knowledge base, the empirical knowledge base can be divided into multiple target subspaces when the optimal solution cannot be determined under multiple working conditions, and then in each target subspace, a proxy model is constructed for each objective function and Bayesian optimization is performed, and the external archive of the multi-objective optimization is updated according to the Bayesian optimization results, thereby guiding the multi-objective optimization based on each proxy model, and then through the collaborative optimization of multi-objective optimization and Bayesian optimization, the computational cost of simulation parameter calibration under multiple working conditions is reduced and the computational efficiency is improved, and the optimized and calibrated electromechanical system simulation model can output more accurate simulation data under multiple working conditions, thereby improving the versatility, robustness and prediction accuracy of the electromechanical system simulation model.

[0116] In a possible implementation, the first optimization module 32 can be used to use each simulation parameter of the electromechanical system simulation model as a decision vector to perform multi-objective optimization on the multiple objective functions to obtain an external archive after multi-objective optimization; and update the experience knowledge base based on the external archive.

[0117] In one possible implementation, the first subspace partitioning module 34 can be used to obtain the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained; determine the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets based on the number of iterations and the maximum number of iterations of the multi-objective optimization; cluster the Pareto optimal solution set according to the first number of clusters, cluster the other solution sets according to the second number of clusters, and record each sub-solution set in the clustering result as a subspace.

[0118] In one possible implementation, the first subspace partitioning module 34 can be used to calculate the ratio of the number of iterations to the maximum number of iterations of the multi-objective optimization; compare the ratio with the first threshold and the second threshold, respectively; and determine the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets based on the comparison results.

[0119] In a possible implementation, the first subspace partitioning module 34 can also be used to determine whether the first number of clusters is less than the number of solutions in the Pareto optimal solution set, and to determine whether the second number of clusters is less than the number of solutions in the other solution sets; if the first number of clusters is less than the number of solutions in the Pareto optimal solution set, the Pareto optimal solution set is clustered according to the first number of clusters; if the first number of clusters is greater than or equal to the number of solutions in the Pareto optimal solution set, the Pareto optimal solution set is clustered according to the number of solutions in the Pareto optimal solution set; if the second number of clusters is less than the number of solutions in the other solution sets, the other solution sets are clustered according to the second number of clusters; if the second number of clusters is greater than or equal to the number of solutions in the other solution sets, the other solution sets are clustered according to the number of solutions in the other solution sets.

[0120] In a possible implementation, the second subspace partitioning module 35 can be used to sort the subspaces according to the congestion of each subspace to obtain a sorting result; obtain the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained, and determine the dynamic congestion threshold based on the number of iterations and the maximum number of iterations of the multi-objective optimization; and filter the subspaces whose congestion is greater than the dynamic congestion threshold from the sorting result to obtain multiple target subspaces.

[0121] In a possible implementation, the second subspace partitioning module 35 can be used to filter out subspaces whose congestion is greater than the dynamic congestion threshold from the sorting results as candidate subspaces; and according to the congestion of the candidate subspaces, merge the candidate subspaces with similar congestion in each of the candidate subspaces to obtain multiple target subspaces.

[0122] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned electromechanical system simulation parameter multi-condition calibration method embodiments are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 3 Functions of the modules / units 31 to 37 are shown.

[0123] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41 and executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 may be divided into Figure 3 Modules / units 31 to 37 are shown.

[0124] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0125] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0126] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0127] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0128] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can 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 the present invention.

[0130] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned electromechanical system simulation parameter multi-condition calibration method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0133] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A multi-condition calibration method for electromechanical system simulation parameters, characterized in that: include: With the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition, multiple objective functions are constructed; Taking each simulation parameter of the electromechanical system simulation model as a decision vector, multi-objective optimization is performed on the plurality of objective functions, and the experience knowledge base is updated according to the multi-objective optimization results; Performing non-dominated sorting on each solution of the simulation parameters of the electromechanical system simulation model corresponding to the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets; Clustering the Pareto optimal solution set and the other solution sets respectively, and recording each sub-solution set in the clustering result as a subspace; sorting the subspaces according to the congestion degree of each subspace, and determining a plurality of target subspaces from the subspaces according to the sorting results; In each of the target subspaces, a proxy model is constructed for each of the target functions, and Bayesian optimization is performed based on each of the proxy models with the expected hypervolume improvement as the acquisition function, and the external archive of multi-objective optimization and the empirical knowledge base are updated based on the Bayesian optimization results; According to the updated external archive and the empirical knowledge base, the step of "performing multi-objective optimization on the plurality of objective functions" and subsequent steps are re-executed until the termination condition is met, and the multi-condition calibration result of the simulation parameters of the electromechanical system simulation model is obtained according to the global optimal solution of the multi-objective optimization.

2. The electromechanical system simulation parameter multi-condition calibration method according to claim 1, characterized in that: Taking each simulation parameter of the electromechanical system simulation model as a decision vector, performing multi-objective optimization on the plurality of objective functions, and updating the experience knowledge base according to the multi-objective optimization results, including: Taking each simulation parameter of the electromechanical system simulation model as a decision vector, multi-objective optimization is performed on the plurality of objective functions to obtain an external archive after the multi-objective optimization; The empirical knowledge base is updated according to the external archive.

3. The electromechanical system simulation parameter multi-condition calibration method according to claim 1, characterized in that: The Pareto optimal solution set and the other solution sets are clustered respectively, and each sub-solution set in the clustering result is recorded as a subspace, including: Obtaining the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained; Determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets according to the number of iterations and the maximum number of iterations of the multi-objective optimization; The Pareto optimal solution set is clustered according to the first number of clusters, the other solution sets are clustered according to the second number of clusters, and each sub-solution set in the clustering result is recorded as a subspace.

4. The electromechanical system simulation parameter multi-condition calibration method according to claim 3, characterized in that: Determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets according to the number of iterations and the maximum number of iterations of the multi-objective optimization, including: Calculating the ratio of the number of iterations to the maximum number of iterations of the multi-objective optimization; comparing the ratio with a first threshold and a second threshold, respectively; The first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets are determined according to the comparison result.

5. The electromechanical system simulation parameter multi-condition calibration method according to claim 3, characterized in that: After determining the first number of clusters corresponding to the Pareto optimal solution set and the second number of clusters corresponding to the other solution sets, the method further includes: Determine whether the first number of clusters is less than the number of solutions in the Pareto optimal solution set, and determine whether the second number of clusters is less than the number of solutions in the other solution set; If the first number of clusters is less than the number of solutions in the Pareto optimal solution set, clustering the Pareto optimal solution set according to the first number of clusters; If the first cluster number is greater than or equal to the number of solutions in the Pareto optimal solution set, clustering the Pareto optimal solution set according to the number of solutions in the Pareto optimal solution set; If the second number of clusters is less than the number of solutions in the other solution sets, clustering the other solution sets according to the second number of clusters; If the second cluster number is greater than or equal to the number of solutions in the other solution sets, clustering the other solution sets according to the number of solutions in the other solution sets.

6. The electromechanical system simulation parameter multi-condition calibration method according to claim 1, characterized in that: The subspaces are sorted according to the congestion degree of each subspace, and a plurality of target subspaces are determined from the subspaces according to the sorting results, including: Sorting the subspaces according to the congestion degree of each subspace to obtain a sorting result; Obtaining the number of iterations corresponding to the multi-objective optimization when the multi-objective optimization result is obtained, and determining a dynamic congestion threshold according to the number of iterations and the maximum number of iterations of the multi-objective optimization; Subspaces whose congestion degree is greater than the dynamic congestion degree threshold are screened from the sorting results to obtain a plurality of target subspaces.

7. The electromechanical system simulation parameter multi-condition calibration method according to claim 6, characterized in that: The subspaces whose congestion is greater than the dynamic congestion threshold are screened from the sorting results to obtain multiple target subspaces, including: Filtering a subspace whose congestion degree is greater than the dynamic congestion degree threshold from the sorting results as a candidate subspace; According to the crowding degree of the candidate subspaces, candidate subspaces with similar crowding degrees in the candidate subspaces are merged to obtain a plurality of target subspaces.

8. A multi-condition calibration device for electromechanical system simulation parameters, characterized in that: include: An objective function construction module is used to construct multiple objective functions with the goal of achieving the highest consistency between the simulation data output by the electromechanical system simulation model and the measured data output by the actual electromechanical system under each working condition; A first optimization module is used to use each simulation parameter of the electromechanical system simulation model as a decision vector, perform multi-objective optimization on the plurality of objective functions, and update the experience knowledge base according to the multi-objective optimization results; A non-dominated sorting module is used to perform non-dominated sorting on each solution of the simulation parameters of the electromechanical system simulation model corresponding to the empirical knowledge base to obtain a Pareto optimal solution set and other solution sets; A first subspace partitioning module is used to cluster the Pareto optimal solution set and the other solution sets respectively, and record each sub-solution set in the clustering result as a subspace; A second subspace partitioning module is used to sort the subspaces according to the congestion degree of each subspace, and determine a plurality of target subspaces from the subspaces according to the sorting result; A second optimization module is used to construct a proxy model for each objective function in each objective subspace, perform Bayesian optimization based on each proxy model with expected hypervolume improvement as an acquisition function, and update the external archive of multi-objective optimization and the empirical knowledge base based on the Bayesian optimization result; A cyclic calibration module is used to re-execute the step of "performing multi-objective optimization on multiple objective functions" and subsequent steps according to the updated external archive and the empirical knowledge base, until the termination condition is met, and obtain the multi-condition calibration result of the simulation parameters of the electromechanical system simulation model according to the global optimal solution of the multi-objective optimization.

9. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images