Method and system for intelligent shape optimization of rotor structure of permanent magnet synchronous motor
Through the intelligent shape optimization method, the Latin hypercube design sample and Gaussian process model are used, combined with the multi-objective optimization algorithm, the problems of narrow optimization space and insufficient performance improvement capabilities in the rotor structure optimization method of permanent magnet synchronous motor are solved, and the motor performance is improved.
Patent Information
- Application Number
- CN202411425139.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-02-25
AI Technical Summary
The existing rotor structure optimization method of permanent magnet synchronous motors has the problem of narrow optimization space and insufficient ability to improve motor performance.
Using the intelligent shape optimization method, by establishing the initial Latin hypercube design sample, judging and processing interference, performing parallel motor electromagnetic finite element calculation, establishing a Gaussian process model, using a multi-objective optimization algorithm to generate candidate solution sets, updating the design sample and iteratively optimize.
It realizes multi-objective automatic optimization of the rotor structure of permanent magnet synchronous motor, improves motor performance, and is especially suitable for motor application scenarios such as mining tractors.
Smart Images
Figure CN119514050A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent manufacturing of motors, and in particular to a method and system for intelligently shape optimizing a permanent magnet synchronous motor rotor structure. Background Art
[0002] Automatic optimization of permanent magnet motors is a complex process that uses advanced software and algorithms to enhance the design of electric motors to maximize their efficiency and performance. The main goal is to adjust the geometry and other possible parameters of the motor to achieve the best performance indicators such as torque density, power density, efficiency, etc., while reducing weight and reducing cost impact. This approach is based on the principle that even small adjustments to the geometry of the motor can significantly improve performance. Intelligent shape optimization plays a vital role in the pursuit of more efficient, power-dense, and cost-effective motors. Unlike experienced motor design engineers, optimization algorithms can quickly evaluate hundreds or even thousands of design entities in a few hours, while manual evaluation of these design entities may take weeks or months. Improvements in motor design performance are achieved by gradually refining the design candidates with each iteration of the optimization algorithm. Traditional motor optimization methods usually require users to define the precise range of each design variable, which requires some preliminary research on the geometry of the motor to determine sufficient boundaries for the design variables. Too narrow a range increases the risk of optimality, while too broad a range leads to a broad search and may overlook the best design due to the large search space. Too wide an optimization variable range can also lead to problems such as a large number of designs having interfering geometric dimensions. Usually, users are required to define the precise range of each design variable, which requires some preliminary research on the geometric structure of the motor to determine sufficient boundaries for the design variables. Now, the geometric structure parameters are analyzed globally and a wide range of design variables are considered. However, existing methods have technical problems such as narrow optimization space and insufficient ability to improve motor performance. Summary of the invention
[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method and system for intelligent shape optimization of the rotor structure of a permanent magnet synchronous motor are provided. The present invention aims to solve the technical problems of existing rotor structure optimization methods such as narrow optimization space and insufficient ability to improve motor performance, thereby improving motor performance, and is particularly suitable for motor application scenarios such as mining tractors.
[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for intelligent shape optimization of a permanent magnet synchronous motor rotor structure comprises the following steps: S1, establishing an initial Latin hypercube design sample according to the geometric parameters of the rotor structure of the permanent magnet synchronous motor; S2, determining whether there is interference in the motor model constructed according to the current Latin hypercube design sample, wherein the interference refers to the intersection of the outer boundaries. If there is interference, re-establish the Latin hypercube design sample and jump to re-execute step S2; otherwise, jump to step S3; S3, performing electromagnetic finite element calculation of the parallel motor to calculate various performance indicators of the motor model; S4, judging whether the performance indicators of the motor model all meet the design goals. If they all meet the design goals, deriving the optimal motor model according to the current Latin hypercube design sample, ending and exiting; otherwise, jumping to step S5; S5, establishing a Gaussian process model for the objective function used to calculate the performance index of the motor model; S6, combined with the Gaussian process model, uses a multi-objective optimization algorithm to generate a candidate solution set; S7, select the next sampling point, update the Latin hypercube design sample, and jump to step S3.
[0005] Optionally, the geometric parameters of the rotor structure of the permanent magnet synchronous motor in step S1 include the permanent magnet height H , permanent magnet width W , permanent magnet magnetization angle θmag , current load angle θ , the gap between the two permanent magnets in the V-shaped pole Wb , the length of the narrow side of the quadrilateral structure on the stator side at the inner end of the two permanent magnets in the V-shaped pole Wp , the length of the narrow side of the quadrilateral structure on the stator side at the outer ends of the two permanent magnets in the V-shaped pole I , the outer gap width of the quadrilateral structure at the outer ends of the two permanent magnets in the V-shaped magnetic pole Wi , and the edge gap width of the two permanent magnets in the V-shaped pole Wr .
[0006] Optionally, the function expression of the initial Latin hypercube design sample in step S1 is: , In the above formula, Design samples for the initial Latin hypercube, ~ These are the 1st to nth geometric parameters of the rotor structure of the permanent magnet synchronous motor.
[0007] Optionally, the performance indicators of the motor model in step S3 include part or all of the permanent magnet volume, average torque, torque ripple, motor efficiency, and motor weight of the motor model.
[0008] Optionally, in step S5, establishing a Gaussian process model for the objective function used to calculate the performance index of the motor model includes: performing Gaussian process regression for each objective function used to calculate the performance index of the motor model according to the following formula to obtain a Gaussian process model and a corresponding mean function and covariance function: , In the above formula, is the jth objective function, is the Gaussian process model of the jth objective function, is the mean function corresponding to the jth objective function, is the covariance function corresponding to the j-th objective function.
[0009] Optionally, in step S6, generating a candidate solution set by using a multi-objective optimization algorithm in combination with a Gaussian process model includes using a sampling function in a Gaussian process model of each objective function , the multi-objective optimization algorithm NSGA-II is used to generate the candidate solution set according to the following formula: , In the above formula, is the candidate solution set, ~ are the 1st to pth points on the Pareto front respectively, p is the index of the solution in the candidate solution set, represents the multi-objective optimization algorithm NSGA-II, ~ are the sampling functions in the Gaussian process model of the 1st to mth objective functions, and m is the number of objective functions.
[0010] Optionally, step S7 includes: S7.1, select the point that will produce the largest hypervolume increment as the next sampling point according to the following formula:
[0011] In the above formula, For the next sampling point, is the kth point on the Pareto front, is the candidate solution set, for The super volume increment is: , In the above formula, is the hypervolume function, is the Pareto frontier corresponding to the current data set, For the merge operation, is a reference point; S7.2, update the sample data set according to the following formula; , , In the above formula, Design samples for the updated Latin hypercube, For the current Latin Hypercube design sample, For the next sampling point, is the target value of the jth objective function after update, is the target value of the jth objective function, is the calculation result of the jth objective function based on the next sampling point, m is the number of objective functions; jump to step S3.
[0012] In addition, the present invention also provides a system for intelligent shape optimization of a permanent magnet synchronous motor rotor structure, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the method for intelligent shape optimization of a permanent magnet synchronous motor rotor structure.
[0013] In addition, the present invention also provides a computer-readable storage medium, in which a computer program or instruction is stored. The computer program or instruction is programmed or configured to execute the method of intelligent shape optimization of the permanent magnet synchronous motor rotor structure through a processor.
[0014] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the method of intelligent shape optimization of the permanent magnet synchronous motor rotor structure through a processor.
[0015] Compared with the prior art, the present invention mainly has the following advantages: the present invention includes establishing an initial Latin hypercube design sample according to the geometric parameters of the rotor structure of the permanent magnet synchronous motor; judging whether there is interference in the motor model constructed according to the current Latin hypercube design sample, and if there is interference, re-establishing the Latin hypercube design sample; performing electromagnetic finite element calculation of the parallel motor for each performance index of the motor model; judging whether the performance indexes of the motor model all meet the design goals, and if they all meet the design goals, deriving the optimal motor model according to the current Latin hypercube design sample, terminating and exiting; otherwise, establishing a Gaussian process model for the objective function used to calculate the performance index of the motor model; combining the Gaussian process model, generating a candidate solution set using a multi-objective optimization algorithm; selecting the next sampling point, updating the Latin hypercube design sample and iterating the performance index of the motor model calculated by electromagnetic finite element of the parallel motor. The present invention can realize multi-objective automatic optimization of the rotor structure of the permanent magnet synchronous motor, solve the technical problems of narrow optimization space and insufficient ability to improve motor performance in the existing rotor structure optimization method, improve motor performance, and is particularly suitable for motor application scenarios such as mining tractors. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.
[0017] Figure 2 Schematic diagram of geometric parameters of a motor in an embodiment of the present invention.
[0018] Figure 3 Graph showing the topological evolution of the rotor structure in an embodiment of the present invention.
[0019] Figure 4 These are optimized design diagrams of different motors corresponding to different design objectives in the embodiments of the present invention.
[0020] Figure 5 This is a distribution diagram of the magnetic field strength of the motor after optimization in an embodiment of the present invention.
[0021] Figure 6 This is a torque pulsation diagram of the optimized motor in the embodiment of the present invention. DETAILED DESCRIPTION
[0022] like Figure 1 As shown, the method for intelligent shape optimization of the permanent magnet synchronous motor rotor structure in this embodiment includes the following steps: S1, establishing an initial Latin hypercube design sample according to the geometric parameters of the rotor structure of the permanent magnet synchronous motor; S2, determining whether there is interference in the motor model constructed according to the current Latin hypercube design sample, wherein the interference refers to the intersection of the outer boundaries. If there is interference, re-establish the Latin hypercube design sample and jump to re-execute step S2; otherwise, jump to step S3; S3, performing electromagnetic finite element calculation of the parallel motor to calculate various performance indicators of the motor model; S4, judging whether the performance indicators of the motor model all meet the design goals. If they all meet the design goals, deriving the optimal motor model according to the current Latin hypercube design sample, ending and exiting; otherwise, jumping to step S5; S5, establishing a Gaussian process model for the objective function used to calculate the performance index of the motor model; S6, combined with the Gaussian process model, uses a multi-objective optimization algorithm to generate a candidate solution set; S7, select the next sampling point, update the Latin hypercube design sample, and jump to step S3.
[0023] It should be noted that different permanent magnet synchronous motors have different rotor structures, and thus different geometric parameters of the rotor structures of the permanent magnet synchronous motors. Even if the rotor structures of the permanent magnet synchronous motors are the same, the geometric parameters of the designs can be selected as needed to make the rotor structures of some permanent magnet synchronous motors different. For example, as an optional implementation, Figure 2 As shown, the geometric parameters of the rotor structure of the permanent magnet synchronous motor in step S1 of this embodiment include the permanent magnet height H , permanent magnet width W , permanent magnet magnetization angle θmag , current load angle θ , the gap between the two permanent magnets in the V-shaped pole Wb , the length of the narrow side of the quadrilateral structure on the stator side at the inner end of the two permanent magnets in the V-shaped pole Wp , the length of the narrow side of the quadrilateral structure on the stator side at the outer ends of the two permanent magnets in the V-shaped pole I , the outer gap width of the quadrilateral structure at the outer ends of the two permanent magnets in the V-shaped magnetic pole Wi , and the edge gap width of the two permanent magnets in the V-shaped pole Wr .
[0024] The function expression of the initial Latin hypercube design sample in step S1 of this embodiment is: , In the above formula, Design samples for the initial Latin hypercube, ~ are the 1st to nth geometric parameters of the rotor structure of the permanent magnet synchronous motor. The Latin hypercube design sample refers to a design sample obtained by randomly sampling from the design space of each geometric parameter of the rotor structure of the permanent magnet synchronous motor.
[0025] In step S2 of this embodiment, when determining whether there is interference in the motor model constructed according to the current Latin hypercube design sample, interference refers to the intersection of the outer boundaries. Because the given geometric parameters are not subject to geometric restrictions, the generated motor model will inevitably generate some interfering models. Such a motor model cannot be divided into grids, and then finite element calculation cannot be performed. In this embodiment, interference processing can ensure that the motor model can be smoothly calculated by finite element.
[0026] In step S3 of this embodiment, when performing electromagnetic finite element calculation of the parallel motor model for each performance index, for any j-th objective function among all objective functions, , which can generate the corresponding target value:
[0027] In the above formula, is the target value of the jth objective function, ~ Design performance indicators for samples of the 1st to nth Latin hypercubes; j =1,2, …, m ; m is the target equation index, i is the number of iterations, and n is the number of corresponding Latin hypercube design samples. In step S3 of this embodiment, the performance indicators of the motor model include part or all of the permanent magnet volume, average torque, torque ripple, motor efficiency, and motor weight of the motor model.
[0028] In step S5 of this embodiment, the Gaussian process model is established for the objective function used to calculate the performance index of the motor model, including: performing Gaussian process regression on each objective function used to calculate the performance index of the motor model according to the following formula to obtain a Gaussian process model and a corresponding mean function and covariance function: , In the above formula, is the jth objective function, is the Gaussian process model of the jth objective function, is the mean function corresponding to the jth objective function, is the covariance function corresponding to the jth objective function, ” represents Gaussian process regression. It should be noted that Gaussian process regression and the sampling functions in the Gaussian process model mentioned below are existing regression methods, so their implementation details are not described in detail here. It should be noted that the multi-objective optimization algorithm in step S6 can be selected according to actual needs. For example, as an optional implementation, in step S6 of this embodiment, the multi-objective optimization algorithm is used to generate a candidate solution set in combination with the Gaussian process model, including using the sampling function in the Gaussian process model of each objective function , the multi-objective optimization algorithm NSGA-II is used to generate the candidate solution set according to the following formula: , In the above formula, is the candidate solution set, ~ are the 1st to pth points on the Pareto front respectively, p is the index of the solution in the candidate solution set, represents the multi-objective optimization algorithm NSGA-II, ~ are the sampling functions in the Gaussian process model of the 1st to mth objective functions, respectively, and m is the number of objective functions. It should be noted that the use of the multi-objective optimization algorithm NSGA-II to generate a candidate solution set is an existing well-known method, so its implementation details are not described in detail here.
[0029] Step S7 of this embodiment includes: S7.1, select the point that will produce the largest hypervolume increment as the next sampling point according to the following formula:
[0030] In the above formula, For the next sampling point, is the kth point on the Pareto front, is the candidate solution set, for The super volume increment is: , In the above formula, is the hypervolume function, is the Pareto frontier corresponding to the current data set, For the merge operation, is the reference point; it should be noted that the hypervolume function is a well-known function, which represents the target space volume dominated by the Pareto front. It is a common indicator for measuring the quality of the solution set. The larger the hypervolume, the larger the area (volume) covered by the solution set in the target space, that is, the better the solution set. Therefore, its implementation details will not be described in detail here. S7.2, update the sample data set according to the following formula; , , In the above formula, Design samples for the updated Latin hypercube, For the current Latin Hypercube design sample, For the next sampling point, is the target value of the jth objective function after update, is the target value of the jth objective function, is the calculation result of the jth objective function based on the next sampling point, m is the number of objective functions; jump to step S3.
[0031] Figure 3 is a topological evolution diagram of the rotor structure in this embodiment, which lists the initial (first) Latin hypercube design sample, the second Latin hypercube design sample and the final Latin hypercube design sample (the optimal structure of the rotor structure). Figure 3 The changes in the geometric parameters of the rotor structure of the permanent magnet synchronous motor are shown. Figure 4 Optimized design diagrams of different motors corresponding to different design objectives in this embodiment, Figure 4 It expresses the relationship between different initial motor sample geometric parameters (initial Latin hypercube design samples), different Pareto motor sample geometric parameters (points on the Pareto frontier), and the sample geometric parameters corresponding to the set design goals (optimal structure of the rotor structure). Figure 5 is a magnetic field intensity distribution diagram of the optimal structure of the rotor structure of the motor after optimization in this embodiment, Figure 6 This is the torque pulsation diagram of the optimal structure of the motor rotor structure after optimization in this embodiment.
[0032] To summarize, the method of this embodiment includes establishing an initial Latin hypercube design sample according to the geometric parameters of the rotor structure of the permanent magnet synchronous motor; judging whether there is interference in the motor model constructed according to the current Latin hypercube design sample, and if there is interference, re-establishing the Latin hypercube design sample; performing parallel motor electromagnetic finite element calculation of various performance indicators of the motor model; judging whether the performance indicators of the motor model all meet the design goals, and if they all meet the design goals, deriving the optimal motor model according to the current Latin hypercube design sample, terminating and exiting; otherwise, establishing a Gaussian process model for the objective function used to calculate the performance indicators of the motor model; combining the Gaussian process model, using a multi-objective optimization algorithm to generate a candidate solution set; selecting the next sampling point, updating the Latin hypercube design sample and iterating the performance indicators of the motor model calculated by the parallel motor electromagnetic finite element. The method of this embodiment can realize multi-objective automatic optimization of the rotor structure of the permanent magnet synchronous motor, solve the technical problems of the existing rotor structure optimization method such as narrow optimization space and insufficient ability to improve motor performance, improve motor performance, and is particularly suitable for motor application scenarios such as mining tractors.
[0033] In addition, this embodiment also provides a system for intelligent shape optimization of a permanent magnet synchronous motor rotor structure, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the method for intelligent shape optimization of a permanent magnet synchronous motor rotor structure.
[0034] In addition, this embodiment also provides a computer-readable storage medium, in which a computer program or instruction is stored. The computer program or instruction is programmed or configured to execute the method of intelligent shape optimization of the permanent magnet synchronous motor rotor structure through a processor.
[0035] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the method of intelligent shape optimization of the permanent magnet synchronous motor rotor structure through a processor.
[0036] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0037] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.
Claims
1. A method for intelligent shape optimization of permanent magnet synchronous motor rotor structure, characterized in that: The steps include: S1, establishing an initial Latin hypercube design sample according to the geometric parameters of the rotor structure of the permanent magnet synchronous motor; S2, determining whether there is interference in the motor model constructed according to the current Latin hypercube design sample, wherein the interference refers to the intersection of the outer boundaries. If there is interference, re-establishing the Latin hypercube design sample and jumping to re-execute step S2; Otherwise, jump to step S3; S3, performing electromagnetic finite element calculation of the parallel motor to calculate various performance indicators of the motor model; S4, judging whether the performance indicators of the motor model all meet the design goals. If they all meet the design goals, deriving the optimal motor model according to the current Latin hypercube design sample, and ending and exiting; Otherwise, jump to step S5; S5, establishing a Gaussian process model for the objective function used to calculate the performance index of the motor model; S6, combined with the Gaussian process model, uses a multi-objective optimization algorithm to generate a candidate solution set; S7, select the next sampling point, update the Latin hypercube design sample, and jump to step S3.
2. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 1, characterized in that: The geometric parameters of the rotor structure of the permanent magnet synchronous motor in step S1 include the permanent magnet height H , permanent magnet width W , permanent magnet magnetization angle θ mag , current load angle θ , the gap between the two permanent magnets in the V-shaped pole Wb , the length of the narrow side of the quadrilateral structure on the stator side at the inner end of the two permanent magnets in the V-shaped pole Wp , the length of the narrow side of the quadrilateral structure on the stator side at the outer ends of the two permanent magnets in the V-shaped pole I , the outer gap width of the quadrilateral structure at the outer ends of the two permanent magnets in the V-shaped magnetic pole Wi , and the edge gap width of the two permanent magnets in the V-shaped pole Wr .
3. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 1, characterized in that: The function expression of the initial Latin hypercube design sample in step S1 is: ， In the above formula, Design samples for the initial Latin hypercube, ~ These are the 1st to nth geometric parameters of the rotor structure of the permanent magnet synchronous motor.
4. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 1, characterized in that: The performance indicators of the motor model in step S3 include part or all of the permanent magnet volume, average torque, torque ripple, motor efficiency, and motor weight of the motor model.
5. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 1, characterized in that: In step S5, the Gaussian process model is established for the objective function used to calculate the performance index of the motor model, including: performing Gaussian process regression for each objective function used to calculate the performance index of the motor model according to the following formula to obtain a Gaussian process model and a corresponding mean function and covariance function: ， In the above formula, is the jth objective function, is the Gaussian process model of the jth objective function, is the mean function corresponding to the jth objective function, is the covariance function corresponding to the j-th objective function.
6. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 5, characterized in that: In step S6, a multi-objective optimization algorithm is used in combination with a Gaussian process model to generate a candidate solution set, including using the sampling function in the Gaussian process model of each objective function. , the multi-objective optimization algorithm NSGA-II is used to generate the candidate solution set according to the following formula: ， In the above formula, is the candidate solution set, ~ are the 1st to pth points on the Pareto front respectively, p is the index of the solution in the candidate solution set, represents the multi-objective optimization algorithm NSGA-II, ~ are the sampling functions in the Gaussian process model of the 1st to mth objective functions, and m is the number of objective functions.
7. The method for intelligent shape optimization of permanent magnet synchronous motor rotor structure according to claim 6, characterized in that: Step S7 includes: S7.1, select the point that will produce the largest hypervolume increment as the next sampling point according to the following formula: In the above formula, is the next sampling point, is the kth point on the Pareto front, is the candidate solution set, for The super volume increment is: ， In the above formula, is the hypervolume function, is the Pareto frontier corresponding to the current data set, For the merge operation, is a reference point; S7.2, update the sample data set according to the following formula; ， ， In the above formula, Design samples for the updated Latin hypercube, For the current Latin Hypercube design sample, is the next sampling point, is the target value of the jth objective function after update, is the target value of the jth objective function, is the calculation result of the jth objective function based on the next sampling point, m is the number of objective functions; jump to step S3.
8. A system for intelligent shape optimization of permanent magnet synchronous motor rotor structure, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the method for intelligent shape optimization of the permanent magnet synchronous motor rotor structure as described in any one of claims 1 to 7.
9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the method for intelligent shape optimization of the permanent magnet synchronous motor rotor structure as claimed in any one of claims 1 to 7 through a processor.
10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the method for intelligent shape optimization of the permanent magnet synchronous motor rotor structure as claimed in any one of claims 1 to 7 through a processor.