Multi-target parameter optimization design method for V-shaped magnetic steel rotor of permanent magnet synchronous motor

Abstract

The invention relates to the technical field of permanent magnet synchronous motors, and particularly provides a multi-target parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor. The method comprises the steps that an optimal input parameter combination database is constructed, and a user inputs input parameters needing to be optimized through a terminal; determining an optimization target according to the input parameters, and defining output parameters according to the optimization target; sensitivity analysis is carried out, and the influence degree of the input parameters on the output parameters is evaluated; adjusting an optimization target according to the influence degree to obtain a standard input parameter combination; and constructing a V-shaped magnetic steel rotor simulation model, inputting the optimal input parameter combination into the V-shaped magnetic steel rotor simulation model for simulation, comparing a simulation result with a preset value, and performing adjustment according to a comparison result to obtain a final target parameter optimization scheme. Through simulation of the V-shaped magnetic steel rotor simulation model, the problems of low structural influence efficiency, cogging effect and energy waste are reduced, and the overall performance and reliability of the motor are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of permanent magnet synchronous machines, and in particular to a multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor. Background Art

[0002] With the rapid development of the power electronics industry, many high-performance semiconductor power devices have emerged one after another, and the advent of high-performance permanent magnet materials and the development of control technology have laid a solid foundation for the widespread application of permanent magnet synchronous motors. Compared with AC synchronous motors, stepper motors and DC brushed motors, permanent magnet synchronous motors have advantages that they do not have. Such motors can basically be replaced by permanent magnet synchronous motors in some occasions. Not only can it replace general permanent magnet DC brushed motors, but it can also be used as AC servo permanent magnet synchronous motors in many applications requiring high precision. Permanent magnet synchronous motors can achieve higher efficiency within a larger speed range. Therefore, permanent magnet synchronous motors have broad development prospects. Researching, developing and producing permanent magnet synchronous motors is a new trend.

[0003] Prior art 1, Chinese patent, application number: 202410629152.1 provides a method for optimizing the efficiency of a permanent magnet synchronous flat wire motor based on an improved Pelican algorithm. First, based on the influence of the proximity effect and skin effect of the conductor in the stator slot, an analytical model of the eddy current loss generated by the stator winding is established, and it is determined that the flat wire size, stator slot height, width and conductor fillet radius are important parameters affecting the eddy current loss. Secondly, a multi-physics field model of the motor is built to analyze the important parameters. Thirdly, an extreme learning machine is introduced to regress a fast calculation model for motor efficiency. Then, the Pelican optimization algorithm is improved through Circle mapping, and the important parameters of the efficiency model are optimized. Finally, the effectiveness of the design scheme is verified by analyzing the efficiency Map of the motor. Although the loss generated by the stator winding of the permanent magnet synchronous flat wire motor is greatly reduced and the motor efficiency is improved, the performance is reduced during high-speed operation.

[0004] Prior art 2, Chinese patent, application number: 202411015700.8 A harmonic suppression method for a permanent magnet synchronous motor drive system without electrolytic capacitor based on multi-port impedance optimization, belongs to the field of motor control technology. The present invention aims at the problem that active damping control will cause an increase in machine-side harmonics when used for grid-side current harmonic suppression of electrolytic capacitor-free motor systems. It includes calculating the machine-side port impedance control voltage and the grid-side port impedance control voltage; using the entropy weight TOPSIS method to calculate the optimal angle of the machine-grid port impedance control voltage, and synthesizing the machine-grid port impedance control voltage into a coordinated voltage; decomposing the coordinated voltage into the coordinated voltage d-axis component and the q-axis component, and then correspondingly superimposing them on the dq-axis voltage given, so as to obtain the controlled dq-axis voltage given; then obtaining the adjusted αβ-axis voltage given by the inverse Park transformation link, and then using SVPWM control to obtain the pulse control signal of the inverter. Although, the harmonic suppression of the machine-grid side of the drive system is achieved; however, the amount of magnetic steel is large and the efficiency is low.

[0005] Prior art three, Chinese patent, application number: 202411153078.7, relates to the field of wind power generation technology, and discloses a modeling and simulation method and system for a direct-drive permanent magnet wind turbine, including a data acquisition module and a modeling and simulation module. The modeling and simulation method and system for the direct-drive permanent magnet wind turbine collect data sets through the data acquisition module, the modeling and simulation module analyzes the detailed process of converting wind energy into mechanical energy and the total amount of mechanical energy into electrical energy, the simulation platform constructs and generates a direct-drive wind turbine model and a simulation model of the rectifier control system on the side of the permanent magnet synchronous wind turbine, the modeling and simulation module sets different wind conditions, and controls the model output control strategy and predicts the total amount of electrical energy. When the energy conversion model has a high degree of simulation and the environmental conditions match the wind condition mode, the modeling and simulation module runs the direct-drive permanent magnet wind turbine according to the simulation control strategy, compares the actual total amount of electrical energy produced with the predicted total amount of electrical energy produced, judges the degree of model simulation, and performs model optimization management. Although the control production strategy is more efficient; however, the problems of structural stiffness and electromagnetic noise are not solved.

[0006] At present, the existing technologies 1, 2 and 3 have the problems of performance degradation during high-speed operation, large amount of magnetic steel and low efficiency, and no solution to the problems of structural stiffness and electromagnetic noise. Therefore, the present invention provides a multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor. Summary of the invention

[0007] The main purpose of the present invention is to provide a multi-objective parameter optimization design method for a permanent magnet synchronous motor V-shaped magnetic steel rotor to solve the problems in the prior art such as performance degradation during high-speed operation, large amount of magnetic steel used and low efficiency, and failure to solve the problems of structural stiffness and electromagnetic noise.

[0008] In order to achieve the above object, the present invention adopts the following technical scheme: In one aspect of the present invention, a multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor is provided, comprising the following steps: Build an optimal input parameter combination database. Users input the input parameters to be optimized through the terminal. The optimization target is determined by the input parameters, and the output parameters are defined according to the optimization target. Perform sensitivity analysis to evaluate the impact of input parameters on output parameters. The input parameters include bridge spacing, bridge width, magnet thickness, magnet width, pole angle, and V-type expansion angle, etc. The output parameters include torque under no-load rated load and maximum speed load conditions; Adjust the optimization target according to the influence, calculate the fitness of the adjusted optimization target, screen out the standard identification parameters, and obtain the standard input parameter combination; retrieve the optimal input parameter combination database and build a V-type magnetic steel rotor simulation model; The optimal input parameter combination is input into the V-type magnetic steel rotor simulation model for simulation, and the simulation result is compared with the preset value. If it is greater than the preset value, it is adjusted according to the comparison result and the fitness calculation is re-performed; if it is less than the preset value, it is output.

[0009] In an optional implementation, evaluating the influence of input parameters on output parameters comprises the following steps: Build an optimal input parameter combination database. Users input the input parameters to be optimized through the terminal. The optimal input parameter combination database is retrieved according to the input parameters and calibrated. If the calibration meets the input parameters, the retrieved optimal input parameter combination data is output to the user. If not, it is transmitted to the defined variable device. Define variable devices to initialize input parameters, retrieve experimental data, and define input parameter ranges; change the value of each input parameter one by one while keeping other parameters unchanged, and record changes in output results after each change; Calculate the impact measure of each input parameter on the output result based on the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than the preset value.

[0010] In an optional implementation, recording the changes in the output results after each change includes the following steps: Retrieve historical experimental data and expert knowledge base to set the value range of input parameters; the input parameters include the torque of PMSM under no-load, rated speed with load and maximum load working conditions; The value of each input parameter is changed one by one while keeping other parameters unchanged to generate a sample set of output results; based on the sample set of output results, the impact measure of each input parameter change on the output result is calculated and quantified according to the impact measure; Quantitatively measure the impact of input parameters on output variance values, decompose the output variance into parts, and calculate the contribution value of each input parameter; adjust the input parameters based on the contribution value.

[0011] In an optional implementation manner, identifying key data whose output impact is greater than a preset value comprises the following steps: Calculate the impact measure of each input parameter on the output result based on the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than the preset value; The key data less than the preset value is judged as a low-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; the key data greater than the preset value is judged as a high-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; If the low-sensitivity parameters or high-sensitivity parameters do not reach the optimization target, the structure is adjusted and the sensitivity analysis of the structural parameters is recalculated.

[0012] In an optional implementation, screening out standard identification parameters comprises the following steps: Assign initial weights to input parameters, evaluate the impact, and adjust the weights based on the impact evaluation results; arrange the sensitivity indexes of output parameters in descending order, with smaller sensitivity indexes indicating smaller impacts and larger sensitivity indexes indicating greater impacts; Set the input parameter weights according to the arrangement order, divide the standard weight by the sum of all standard weights for normalization; calculate the impact value to get the comprehensive impact, assign different weights to the impact values ​​of different attributes; adjust the optimization target according to the weight; The adjusted optimization target is subjected to fitness calculation, standard identification parameters are screened out, and standard input parameter combinations are obtained; the optimal input parameter combination database is retrieved, and a V-type magnetic steel rotor simulation model is constructed.

[0013] In an optional implementation, constructing a V-shaped magnetic steel rotor simulation model comprises the following steps: The adjusted optimization target is adaptively calculated to obtain the objective function; the objective function value is calculated to evaluate the fitness of the parameter combination; the parameter combination whose fitness reaches the standard is selected, and the parameter combination is iteratively optimized to obtain the standard input parameter combination; Retrieving the optimal input parameter combination database, and building a V-type magnetic steel rotor simulation model according to the optimal input parameter combination database; obtaining a data set from the parameters in the standard input parameter combination, and preprocessing the data set; The preprocessed data set is divided into a training set, a validation set and a test set; the training set is used to train the V-type magnetic steel rotor simulation model; and the standard input parameter combination is input into the V-type magnetic steel rotor simulation model for simulation.

[0014] In an optional implementation, preprocessing the data set includes the following steps: Retrieve the optimal input parameter combination database and set the motor working conditions; the electrical working conditions include no load, rated load and maximum speed load, etc.; Remove noise, outliers and missing values ​​from the data set; standardize the data, merge data from different sources, and extract key features; The preprocessed data is divided into training set, validation set and test set, and the training set is used to train the V-type magnetic steel rotor simulation model.

[0015] In an optional implementation, performing simulation includes the following steps: Calculate the torque response of the motor under different working conditions, and compare the simulation result with the preset value. If the simulation result is greater than the preset value, it is judged that the parameter combination does not meet the standard; if the simulation result is less than the threshold, it is judged that the parameter combination meets the standard; Evaluate the comparison results of parameter combinations that do not meet the standards, make adjustments based on the evaluation, and recalculate the fitness; iterate in sequence until the parameter combination meets the standards; The parameter combinations that meet the standards are output to the cloud platform and stored in the optimal input parameter combination database; the cloud platform outputs the data to the user terminal and readjusts the V-type magnetic steel rotor simulation model based on the user terminal feedback.

[0016] In an optional implementation, recalculating the fitness includes the following steps: According to the simulation results and fitness function, the input parameters are adjusted using the optimization algorithm; the rotor structure is determined to eliminate interference and select parameters; The first parameter distribution is checked for consistency with the second parameter distribution. If they are inconsistent, the first parameter distribution is readjusted. If they are consistent, the first parameter distribution and the second parameter distribution are further checked for consistency with the third parameter distribution. If any parameter distribution is inconsistent, the inconsistent parameter distribution is readjusted. Iterate in sequence until all parameter decoupling is completed. The first parameter distribution is decoupled from the second parameter distribution; the first parameter distribution, the second parameter distribution and the third parameter distribution are decoupled; and they are iterated in sequence; The parameters that complete the full parameter decoupling are determined as the optimal parameter combination, and the optimal parameter combination is re-input into the V-type magnetic steel rotor simulation model, and the simulation is re-performed until the parameter combination meets the standards.

[0017] The present invention constructs an optimal input parameter combination database, and the user can input the parameters to be optimized, determine the optimization target and define the output parameters; evaluate the influence of the input parameters on the output parameters according to the sensitivity analysis, identify the key parameters and make adjustments. This helps to reduce the size of the design space and accelerate the optimization process; the present invention adjusts the optimization target according to the influence, performs fitness calculation, screens out the standard identification parameters, and obtains the standard input parameter combination. The optimal input parameter combination is input into the V-shaped magnetic steel rotor simulation model for simulation, and the simulation result is compared with the preset value. If the simulation result is greater than the preset value, it is adjusted according to the comparison result and the fitness calculation is performed again; if it is less than the preset value, the result is output; through sensitivity analysis, researchers can identify the input parameters that have the greatest impact on the model prediction results, and optimize the parameter settings based on this; response surface analysis is used to evaluate the influence of input parameters on output parameters, identify key parameters and make adjustments. This helps to reduce the size of the design space and accelerate the optimization process. Significantly improve the efficiency and performance of motor design, reduce design time and cost, and ensure the accuracy and reliability of the design. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 A flowchart of the steps of the multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor provided in Embodiment 1 of the present invention; Figure 2 A flowchart of the steps of evaluating the influence of input parameters on output parameters provided in Example 2 of the present invention; Figure 3 A flowchart of the steps for recording the changes in the output results after each change provided in Embodiment 3 of the present invention; Figure 4 A flowchart of the steps of identifying key data whose output impact is greater than a preset value provided in Embodiment 4 of the present invention; Figure 5 A flowchart of the steps for screening standard identification parameters provided in Example 5 of the present invention; Figure 6 A flowchart of the steps of constructing a V-shaped magnetic steel rotor simulation model provided in Example 6 of the present invention; Figure 7 A flowchart of the steps of preprocessing a data set provided in Example 7 of the present invention; Figure 8 A flowchart of the steps of performing simulation provided in Embodiment 8 of the present invention; Fig. 9A flowchart of the steps of recalculating fitness provided in Embodiment 9 of the present invention; Fig.10 This is a schematic diagram of the functional modules of the multi-objective parameter optimization design system for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor provided in Embodiment 10 of the present invention; Fig.11 is a block diagram of an electronic device provided in Embodiment 11 of the present invention; Fig.12 This is a block diagram of the computer-readable storage medium provided in Example 12 of the present invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0020] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0021] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or, "connection" can be a direct connection, or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense, for example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, and can also be understood as electrical connection between different components in a circuit structure through physical lines such as copper foil or wires on a printed circuit board (PCB) that can transmit electrical signals to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an air-spaced / non-contact manner, for example, two components are electrically connected by capacitive coupling to transmit electrical signals.

[0022] In the embodiments of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change of the orientation of the components in the drawings.

[0023] Embodiments of the present invention may be used in modern machine tools, new energy vehicles, industrial applications, household appliances, and the aerospace field.

[0024] The key technical features of the embodiments of the present invention are described as follows: The present invention defines input and output variables and their ranges, adopts the experimental design (DoE) method to generate a series of sampling points, and uses the response surface method to visualize the relationship between input and output variables; evaluates the sensitivity of output parameters to changes in input parameters and identifies key parameters; applies a multi-objective optimization algorithm to determine the optimal values ​​of input parameters; adjusts the optimization target according to the influence, and calculates the fitness of the adjusted optimization target; screens out standard identification parameters and obtains standard input parameter combinations; retrieves the optimal input parameter combination database and constructs a V-type magnetic steel rotor simulation model; inputs the optimal input parameter combination into the V-type magnetic steel rotor simulation model for simulation; compares the simulation results with the preset values, and if greater than the preset values, adjusts according to the comparison results and recalculates the fitness; if less than the preset values, outputs; uses a global sensitivity analysis method (such as the Sobol method) to quantify the influence of a single parameter and the interaction effect between parameters on the model output.

[0025] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor, comprising the following steps: Step S100: construct an optimal input parameter combination database, the user inputs the input parameters to be optimized through the terminal; the optimization target is determined by the input parameters, and the output parameters are defined according to the optimization target; a sensitivity analysis is performed to evaluate the influence of the input parameters on the output parameters; The input parameters include bridge spacing, bridge width, magnet thickness, magnet width, pole angle, and V-type expansion angle, etc. The output parameters include torque under no-load rated load and maximum speed load conditions; Step S200: adjusting the optimization target according to the influence, performing fitness calculation on the adjusted optimization target, screening out standard identification parameters, and obtaining a standard input parameter combination; retrieving the optimal input parameter combination database, and constructing a V-type magnetic steel rotor simulation model; Step S300: Input the optimal input parameter combination into the V-type magnetic steel rotor simulation model for simulation, compare the simulation result with the preset value, if it is greater than the preset value, adjust it according to the comparison result and recalculate the fitness; if it is less than the preset value, output it.

[0026] In the above embodiment, step S100 in this embodiment builds an optimal input parameter combination database, and the user inputs the input parameters to be optimized through the terminal. These input parameters include bridge spacing, bridge width, magnet thickness, magnet width, polar angle, and V-type expansion angle; the optimization target is determined according to the input parameters, and the output parameters are defined, such as torque under no load, rated load, and maximum speed load conditions. Then a sensitivity analysis is performed to evaluate the influence of the input parameters on the output parameters. Through sensitivity analysis, it is possible to identify which input parameters have the greatest impact on the output results, thereby helping to optimize the design process and improve the accuracy and reliability of the model; this embodiment can clarify the optimization target by defining the output parameters, providing a basis for subsequent simulation and optimization. Step S200 adjusts the optimization target according to the influence, performs fitness calculation, screens out standard identification parameters, and obtains a standard input parameter combination; retrieves the optimal input parameter combination database and builds a V-type magnetic steel rotor simulation model; this embodiment adjusts the optimization target and performs fitness calculation to more accurately select the input parameter combination that has the greatest impact on the output results, thereby improving the performance of the simulation model. Building a simulation model helps to further verify and optimize the design to ensure that the final result meets expectations. In step S300, the optimal input parameter combination is input into the V-shaped magnetic steel rotor simulation model for simulation, and the simulation result is compared with the preset value; if the simulation result is greater than the preset value, it is adjusted according to the comparison result and the fitness calculation is re-performed; if it is less than the preset value, it is output; through simulation verification, it can be ensured that the design meets the expected performance requirements. If the simulation result does not reach the preset value, the input parameters can be adjusted and re-optimized to ensure the reliability and effectiveness of the final design. This method can effectively reduce design errors and improve the overall performance of the motor.

[0027] Embodiment 2: like Figure 2 As shown, based on Example 1, the process of evaluating the influence of input parameters on output parameters in step S100 provided in this embodiment of the present invention specifically includes the following steps: Step S101: construct an optimal input parameter combination database, and the user inputs the input parameters to be optimized through the terminal; retrieve the optimal input parameter combination database according to the input parameters and perform calibration; if the calibration meets the input parameters, the retrieved optimal input parameter combination data is output to the user; if not, it is transmitted to the variable definition device; Step S102: define the variable device to initialize the input parameters, retrieve the experimental data, and define the input parameter range; change the value of each input parameter one by one while keeping other parameters unchanged, and record the changes in the output results after each change; Step S103: Calculate the impact metric of each input parameter on the output result according to the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than a preset value; Among them, the impact measure of each input parameter on the output result is calculated. Assume that there is an output function ,in is the input parameter, is the output parameter; it is described using Taylor expansion At a certain point Changes in the neighborhood; In the formula, Represents the output parameter, which represents the output result of the system. Indicates that the output function is at point The value at Indicates i An input parameter represents an input variable of the system. Indicates i Input parameters at point of Represents the output function For i Input parameters The partial derivative of The value at Represents the output function f For i and j The second-order partial derivatives of the input parameters are at the point The value at Indicates at point Nearby, each input parameter The change of output The linear effect of Indicates at point Nearby, the nonlinear influence of the interaction between input parameters on the output \( y \); describe the impact of changes in input parameters on the output results, including linear and nonlinear parts, so as to more accurately evaluate the influence of each input parameter.

[0028] In the above embodiment, step S101 in this embodiment builds an optimal input parameter combination database, and the user inputs the input parameters to be optimized through the device; the optimal input parameter combination database is retrieved according to the input parameters and calibrated; if the calibration meets the input parameters, the retrieved optimal input parameter combination data is output to the user; if not, it is transmitted to the variable definition device; the accuracy of the input parameters is ensured by calibration, thereby improving the prediction accuracy and reliability of the model. Step S102 The variable definition device initializes the input parameters, retrieves the experimental data, and defines the input parameter range; the value of each input parameter is changed one by one, while keeping other parameters unchanged, and the change of the output result after each change is recorded; by systematically changing the value of the input parameter, the output result of the model is observed and recorded, thereby evaluating the impact of each input parameter on the output result. Step S103 Calculate the impact measure of each input parameter on the output result according to the change of the output result, analyze the impact of each input parameter on the output parameter, and identify the key data whose output impact is greater than the preset value; by calculating the impact measure of each input parameter on the output result, identify the key variables that have the greatest impact on the output result, thereby optimizing the model and decision support. This embodiment ensures the accuracy and optimization of input parameters by constructing and calling the optimal input parameter combination database, thereby improving the prediction accuracy of the model; by systematically changing the values ​​of input parameters, observing and recording the output results of the model, evaluating the impact of each input parameter on the output results, and identifying key variables; by calculating the impact measure of each input parameter on the output results, identifying the key variables that have the greatest impact on the output results, thereby optimizing the model and decision support.

[0029] Embodiment 3: like Figure 3 As shown, based on Example 2, the process of recording the change of the output result after each change in step S102 provided in the embodiment of the present invention specifically includes the following steps: Step S1021: retrieve historical experimental data and expert knowledge base, and set the value range of input parameters; wherein the input parameters include the torque of the PMSM under no-load, rated speed with load, and maximum load working conditions; Step S1022: changing the value of each input parameter one by one while keeping other parameters unchanged, generating an output result sample set; calculating the impact metric of each input parameter change on the output result based on the output result sample set, and quantifying according to the impact metric; Step S1023: quantitatively measure the impact of input parameters on output variance values, decompose the output variance into parts, and calculate the contribution value of each input parameter; adjust the input parameters according to the contribution value.

[0030] In the above embodiment, step S1021 of this embodiment extracts information from historical experimental data and expert knowledge base, and sets the value range of input parameters; the input parameters include the torque of PMSM under different working conditions, such as no load, rated speed with load and maximum load; this embodiment can ensure the accuracy and effectiveness of subsequent analysis by setting a reasonable input parameter value range, and provide basic data support for parameter estimation and optimization. Step S1022 generates multiple output result sample sets by changing the values ​​of input parameters one by one, and calculates the impact measure of each input parameter change on the output result. This method is called the one-time change (OAT) method, which is a commonly used sensitivity analysis method; this embodiment can identify which parameters have the greatest impact on the output result by quantifying the impact of each input parameter on the output result, thereby helping to optimize and adjust these key parameters and improve system performance. Step S1023 uses variance decomposition techniques, such as the Sobol index, to quantitatively measure the contribution of input parameters to output variance. This method can decompose the total variance into the contribution of each input parameter and calculate the contribution value of each input parameter; by decomposing the output variance and calculating the contribution value of each input parameter, we can more accurately understand the specific impact of each parameter on the system performance, thereby guiding further parameter optimization and adjustment and improving the overall performance and reliability of the system.

[0031] Embodiment 4: like Figure 4 As shown, based on Example 2, the process of identifying key data with an output impact greater than a preset value in step S103 provided in the embodiment of the present invention specifically includes the following steps: Step S1031: Calculate the impact metric of each input parameter on the output result according to the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than a preset value; Step S1032: The key data less than the preset value is judged as a low-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; the key data greater than the preset value is judged as a high-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; Step S1033: If the low sensitivity parameter or the high sensitivity parameter does not reach the optimization target, the structure is adjusted and the sensitivity analysis of the structure parameters is recalculated.

[0032] In the above embodiment, step S1031 in this embodiment identifies key data by calculating the impact measure of each input parameter on the output result. This step uses the sensitivity analysis method to evaluate the degree of influence of input parameter changes on the model output; through sensitivity analysis, this embodiment can identify key parameters that have a greater impact on the output, thereby helping to optimize the design and improve the performance and reliability of the system. Step S1032 divides the parameters into two categories of low sensitivity and high sensitivity, and judges the optimization target separately. By distinguishing between low-sensitivity and high-sensitivity parameters, resources and calculations can be more effectively concentrated on key parameters, thereby improving the efficiency of the optimization design. Step S1033 If the low-sensitivity or high-sensitivity parameters do not reach the optimization target, the structure is adjusted and recalculated to ensure the optimization effect of the final structural parameters; by understanding the impact of each parameter on the output result, decision makers in this embodiment can make more informed decisions and improve the robustness and stability of the model.

[0033] Embodiment 5: like Figure 5 As shown, based on Example 1, the process of screening out the standard identification parameters in step S200 provided in the embodiment of the present invention specifically includes the following steps: Step S201: assigning initial weights to input parameters, evaluating the impact, and adjusting the weights according to the impact evaluation results; arranging the sensitivity indexes of the output parameters in descending order, with the smaller the sensitivity index, the smaller the impact, and the larger the sensitivity index, the greater the impact; Step S202: setting the input parameter weights according to the arrangement order, dividing the standard weight by the sum of all standard weights for normalization; calculating the influence value to obtain the comprehensive influence degree, assigning different weights to the influence values ​​of different attributes; adjusting the optimization target according to the weight; Step S203: performing fitness calculation on the adjusted optimization target, screening out standard identification parameters, and obtaining a standard input parameter combination; retrieving the optimal input parameter combination database, and constructing a V-type magnetic steel rotor simulation model.

[0034] In the above embodiment, step S201 in this embodiment assigns initial weights to input parameters, evaluates the influence, and adjusts the weights according to the evaluation results; in addition, the sensitivity index of the output parameter is arranged in order from large to small, the smaller the sensitivity index, the smaller the influence, and the larger the sensitivity index, the greater the influence; this embodiment identifies the parameters that have a greater impact on the optimization target through sensitivity analysis, thereby simplifying the subsequent optimization process and improving efficiency. This helps to focus resources and attention on key parameters during the optimization process, thereby improving the overall optimization effect. Step S202 sets the input parameter weights according to the arrangement order and performs normalization processing; the influence value is calculated to obtain the comprehensive influence, and the influence values ​​of different attributes are assigned different weights, and then the optimization target is adjusted according to the weight; through normalization processing and calculation of the comprehensive influence, the contribution of each parameter to the optimization target can be more accurately reflected, thereby achieving more accurate optimization target adjustment; this embodiment can effectively balance the relationship between multiple targets and ensure the rationality and effectiveness of the optimization process. Step S203 performs fitness calculation on the adjusted optimization target, screens out standard identification parameters, and obtains a standard input parameter combination; retrieves the optimal input parameter combination database and constructs a V-type magnetic steel rotor simulation model; this embodiment can find the optimal input parameter combination through fitness calculation and screening of standard identification parameters, and then construct an efficient V-type magnetic steel rotor simulation model.

[0035] Embodiment 6: like Figure 6 As shown, based on Example 5, the process of constructing the V-shaped magnetic steel rotor simulation model in step S203 provided in the embodiment of the present invention specifically includes the following steps: Step S2031: adaptively calculate the adjusted optimization target to obtain the objective function; calculate the objective function value to evaluate the fitness of the parameter combination; select the parameter combination whose fitness reaches the standard, iteratively optimize the parameter combination, and obtain the standard input parameter combination; Step S2032: retrieve the optimal input parameter combination database, and construct a V-type magnetic steel rotor simulation model according to the optimal input parameter combination database; obtain a data set from the parameters in the standard input parameter combination, and pre-process the data set; Step S2033: Divide the preprocessed data set into a training set, a validation set and a test set; train the V-type magnetic steel rotor simulation model with the training set; input the standard input parameter combination into the V-type magnetic steel rotor simulation model for simulation.

[0036] In the above embodiment, step S2031 in this embodiment performs adaptive calculation on the adjusted optimization target, obtains the objective function, and calculates the objective function value to evaluate the fitness of the parameter combination. Then select the parameter combination whose fitness reaches the standard, and perform iterative optimization on these parameter combinations, and finally obtain the standard input parameter combination; this embodiment can effectively improve the adaptability and performance of the parameter combination through adaptive calculation and iterative optimization, thereby providing high-quality input parameters for the construction of subsequent simulation models. This helps to improve the accuracy and reliability of the simulation model. Step S2032 retrieves the optimal input parameter combination database, constructs a V-type magnetic steel rotor simulation model according to the optimal input parameter combination database, extracts a data set from the standard input parameter combination, and preprocesses the data set; this embodiment uses the optimal input parameter combination database to ensure that the initial setting of the simulation model is more reasonable, thereby improving the accuracy and reliability of the simulation results; in addition, the preprocessing of the data set helps to improve the data quality and provide more effective data support for model training and verification. Step S2033 divides the preprocessed data set into a training set, a validation set, and a test set, uses the training set to train the V-type magnetic steel rotor simulation model, and inputs the standard input parameter combination into the simulation model for simulation; this embodiment can effectively improve the generalization ability and accuracy of the model by reasonably dividing the data set and performing model training; at the same time, using the standard input parameter combination for simulation helps to verify the performance of the model in actual applications and ensure the stability and reliability of the model under different conditions.

[0037] Embodiment 7: like Figure 7 As shown, based on Example 6, the process of preprocessing the data set in step S2032 provided in this embodiment of the present invention specifically includes the following steps: Step S20321: retrieve the optimal input parameter combination database and set the motor working conditions; wherein the electrical working conditions include no load, rated load, and maximum speed load, etc.; Step S20322: remove noise, outliers and missing values ​​from the data set; standardize the data, merge data from different sources, and extract key features; Step S20323: Divide the preprocessed data into a training set, a validation set, and a test set, and use the training set to train the V-type magnetic steel rotor simulation model.

[0038] In the above embodiment, step S20321 in this embodiment retrieves the optimal input parameter combination from the database, and sets the working conditions of the motor according to these parameters. These working conditions include electrical working conditions, such as no load, rated load, and maximum speed load, etc.; by setting reasonable motor working conditions, this embodiment can ensure that the motor can operate stably under different load conditions and improve the performance and reliability of the motor. Step S20322 removes noise, outliers, and missing values ​​from the data to improve data quality; converts the data to a unified scale for subsequent analysis and modeling; extracts key features from the preprocessed data to better describe the operating status of the motor; through data cleaning and standardization, inconsistencies in the data can be eliminated, and the training effect and prediction accuracy of the model can be improved. Feature extraction helps to identify the most relevant and informative features for analysis, thereby improving model performance. Step S20323 divides the preprocessed data into a training set, a validation set, and a test set, wherein the training set is used for model training, the validation set is used for model evaluation and hyperparameter tuning, and the test set is used for final evaluation of model performance; the V-shaped magnetic steel rotor simulation model is trained using the training set data to simulate the behavior of the motor under different working conditions; this embodiment can ensure that the model can fully learn the characteristics of the data during the training process and accurately evaluate the generalization ability of the model in the verification and testing stages through reasonable data segmentation. This helps to improve the accuracy and reliability of the simulation model.

[0039] Embodiment 8: like Figure 8 As shown, based on Example 1, the simulation process in step S300 provided in this embodiment of the present invention specifically includes the following steps: Step S301: Calculate the torque response of the motor under different working conditions, compare the simulation result with the preset value, if the simulation result is greater than the preset value, then it is determined that the parameter combination does not meet the standard; if the simulation result is less than the threshold, then it is determined that the parameter combination meets the standard; Step S302: Evaluate the comparison results of the parameter combinations that do not meet the standards, make adjustments based on the evaluation, and recalculate the fitness; iterate in sequence until the parameter combination meets the standards; Step S303: Output the parameter combination that meets the standard to the cloud platform and store it in the optimal input parameter combination database; the cloud platform outputs the data to the user terminal and readjusts the V-type magnetic steel rotor simulation model according to the feedback from the user terminal.

[0040] In the above embodiment, step S301 in this embodiment calculates the torque response of the motor under different working conditions, and compares the simulation result with the preset value; if the simulation result is greater than the preset value, it is judged that the parameter combination does not meet the standard; if the simulation result is less than the threshold, it is judged that the parameter combination meets the standard; this embodiment quickly screens out parameter combinations that do not meet the standard by comparing the simulation results and the preset values, thereby improving the design efficiency and accuracy; ensuring that inappropriate parameter combinations can be adjusted in time during the motor design process to avoid wasting resources. Step S302 evaluates the parameter combination that does not meet the standard, adjusts it according to the evaluation results, and recalculates the fitness. Through the iterative process, until the parameter combination meets the standard; this embodiment gradually adjusts the parameter combination to meet the design requirements through iterative optimization, ensuring that the final parameter combination can meet the expected performance standards. Step S303 outputs the parameter combination that meets the standard to the cloud platform and stores it in the optimal input parameter combination database; the cloud platform outputs the data to the user terminal and readjusts the V-shaped magnetic steel rotor simulation model according to the feedback from the user terminal. This embodiment realizes the sharing and dynamic adjustment of parameter optimization results through the integration of the cloud platform and the user feedback mechanism, thereby improving the flexibility and response speed of the design process; at the same time, the feedback from the user terminal further optimizes the simulation model, making the design closer to actual application needs.

[0041] Embodiment 9: like Fig. 9 As shown, based on Example 8, the process of recalculating the fitness in step S302 provided in the embodiment of the present invention specifically includes the following steps: Step S3021: According to the simulation results and the fitness function, use the optimization algorithm to adjust the input parameters; determine the rotor structure to eliminate interference and select parameters; Step S3022: the first parameter distribution and the second parameter distribution are checked for consistency. If they are inconsistent, the first parameter distribution is readjusted; if they are consistent, the first parameter distribution and the second parameter distribution are further checked for consistency with the third parameter distribution; if any parameter distribution is inconsistent, the inconsistent parameter distribution is readjusted; iterate in sequence until full parameter decoupling is completed; The first parameter distribution is decoupled from the second parameter distribution; the first parameter distribution, the second parameter distribution and the third parameter distribution are decoupled; and they are iterated in sequence; Step S3023: Determine the parameters that complete the full parameter decoupling as the optimal parameter combination, re-input the optimal parameter combination into the V-type magnetic steel rotor simulation model, and re-simulate until the parameter combination meets the standard.

[0042] In the above embodiment, in step S3021 of this embodiment, the optimization algorithm is used to adjust the input parameters according to the simulation results and the fitness function, and the rotor structure is determined to eliminate interference and select parameters; in this embodiment, the performance and efficiency of the system can be improved by adjusting the parameters through the optimization algorithm. For example, the particle swarm optimization algorithm (PSO) is often used for PID controller parameter optimization, and the system performance can be significantly improved by dynamically adjusting the parameters. In addition, the optimization algorithm can find the optimal parameter combination in combination with the simulation model, thereby improving the overall performance of the system. Step S3022 performs a consistency check on the parameter distribution, and if it is inconsistent, the parameter distribution is readjusted; if it is consistent, the consistency check is continued with other parameter distributions until the full parameter decoupling is completed; in this embodiment, the coordination between the parameter distributions is ensured through consistency check and iterative adjustment, and mutual interference is avoided, and finally the full parameter decoupling is achieved. This helps to optimize the system design and improve the stability and reliability of the system. Step S3023 determines the parameters that complete the full parameter decoupling as the optimal parameter combination, and re-enters it into the simulation model for simulation until the parameter combination meets the standard; The optimal parameter combination finally determined can ensure the best performance of the system in practical applications. For example, in motor design, by optimizing the rotor structure and parameters, the efficiency and performance of the motor can be significantly improved. In addition, this optimization method helps to reduce flux leakage and increase the main flux, thereby improving the overall performance of the motor.

[0043] Embodiment 10: like Fig.10 As shown, based on Embodiments 1 to 9, a multi-objective parameter optimization design system for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor provided by an embodiment of the present invention comprises: Standard database module 1: Build the optimal input parameter combination database. Users input the input parameters to be optimized through the terminal; determine the optimization target based on the input parameters, and define the output parameters based on the optimization target; perform sensitivity analysis to evaluate the impact of input parameters on output parameters; The input parameters include bridge spacing, bridge width, magnet thickness, magnet width, pole angle, and V-type expansion angle, etc. The output parameters include torque under no-load rated load and maximum speed load conditions; Simulation model module 2: adjust the optimization target according to the influence, calculate the fitness of the adjusted optimization target, screen out the standard identification parameters, and obtain the standard input parameter combination; retrieve the optimal input parameter combination database and build a V-type magnetic steel rotor simulation model; Evaluation Optimization Module 3: Input the optimal input parameter combination into the V-type magnetic steel rotor simulation model for simulation, and compare the simulation result with the preset value. If it is greater than the preset value, adjust it according to the comparison result and recalculate the fitness; if it is less than the preset value, output it; Among them, the expression comparing the simulation result with the preset value is: In the formula, Represents the total error between the simulation result and the preset value, Indicates a The actual value of the simulation output parameter, Indicates a The preset values ​​of the simulation output parameters, Indicates a The weight factors of the simulation output parameters, Indicates a A nonlinear function of the simulation output parameters, n represents the total number of simulation output parameters, represents the relative error of each output parameter, Indicates b The weight factors of the fuzzy logic parameters, Indicates b A nonlinear function of fuzzy logic parameters, m Represents the total number of fuzzy logic parameters. For example, temperature, humidity, pressure, etc. can all be fuzzy logic parameters. Represents the relative error of each fuzzy logic parameter. This part is used to calculate the relative error of each fuzzy logic parameter. This equation further increases the complexity of comparing simulation results with preset values ​​by introducing fuzzy logic parameters and multi-level weight adjustment.

[0044] In the above embodiment, the standard database module 1 in this embodiment defines the input and output variables and their ranges, uses the experimental design (DoE) method to generate a series of sampling points, and uses the response surface method to visualize the relationship between the input and output variables; performs sensitivity analysis to evaluate the sensitivity of the output parameters to the changes in the input parameters; and applies a multi-objective optimization algorithm to determine the optimal values ​​of the input parameters; this embodiment can find the optimal input parameter combination under multiple working conditions through multi-objective optimization design, thereby improving the motor performance; and through sensitivity analysis, it can identify key parameters, optimize the experimental design, reduce unnecessary computing costs, and improve the prediction ability of the model; and through the multi-objective optimization algorithm, it can determine the optimal values ​​of the input parameters, thereby optimizing the motor design and improving the performance. The simulation model module 2 performs fitness calculation on the adjusted optimization target, selects standard identification parameters, and obtains a standard input parameter combination; this embodiment introduces a sensitivity index to evaluate the influence of design parameters on the optimization target, and uses the minimum and maximum change values ​​to measure; a response surface model is constructed to fit the approximate expression of the predicted optimization parameters; this embodiment can select parameters that have a greater impact on the optimization target through fitness calculation and parameter hierarchical optimization design, thereby simplifying the optimization process and improving efficiency; through the response surface model, the approximate expression of the optimization parameters can be accurately predicted, thereby improving the accuracy of the optimization design; through parameter hierarchical optimization design, the efficiency of the optimization design process can be significantly improved. The optimal evaluation module 3 retrieves the optimal input parameter combination database and constructs a V-type magnetic steel rotor simulation model; this embodiment compares the simulation result with the preset value. If it is greater than the preset value, it is adjusted according to the comparison result and the fitness calculation is re-performed; if it is less than the preset value, the optimal input parameter combination is output; this embodiment verifies the effectiveness of the optimal input parameter combination through the simulation model to ensure its performance in practical applications; and through fitness calculation and comparison, it can make necessary adjustments according to the simulation results to ensure that the output results meet the preset requirements; and by outputting the optimal input parameter combination, it can provide the best parameter configuration for practical applications, thereby improving the motor performance.

[0045] Fig.11 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0046] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer executable instructions therein, for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0047] The central processing unit / microprocessor / main control chip 4 may include but is not limited to, for example, one or more processors or microprocessors.

[0048] The storage medium 5 may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disk, floppy disk, solid state drive, removable disk, CD‑ROM, DVD‑ROM, Blu-ray disc, etc.).

[0049] In addition, the electronic device may also include (but not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (eg, keyboard, mouse, speaker, etc.).

[0050] The central processing unit / microprocessor / main control chip etc. 4 can communicate with external devices ( 8 , 9 etc.) through the I / O bus 7 via a wired or wireless network (not shown).

[0051] The storage medium 5 may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when executed by the central processing unit / microprocessor / main control chip 4.

[0052] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0053] Fig.12 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0054] like Fig.12 As shown, instructions are stored on a non-transitory computer-readable storage medium 11, and the instructions are, for example, computer-readable instructions 10. When the computer-readable instructions 10 are executed by the processor, the various methods described above can be executed. Non-transitory computer-readable storage media include, but are not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0055] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, 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.

[0056] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0058] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the various embodiments of the method of the present invention through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program code.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor, characterized in that: The multi-objective parameter optimization design method of the V-shaped magnetic steel rotor of the permanent magnet synchronous motor comprises the following steps: Build an optimal input parameter combination database. Users input the input parameters to be optimized through the terminal. The optimization target is determined by the input parameters, and the output parameters are defined according to the optimization target. Perform sensitivity analysis to evaluate the impact of input parameters on output parameters. The input parameters include bridge pitch, bridge width, magnet thickness, magnet width, pole angle, and V-type expansion angle; the output parameters include torque under no-load rated load and maximum speed load conditions; Adjust the optimization target according to the influence, calculate the fitness of the adjusted optimization target, screen out the standard identification parameters, and obtain the standard input parameter combination; retrieve the optimal input parameter combination database and build a V-type magnetic steel rotor simulation model; The optimal input parameter combination is input into the V-type magnetic steel rotor simulation model for simulation, and the simulation result is compared with the preset value. If it is greater than the preset value, it is adjusted according to the comparison result and the fitness calculation is re-performed; if it is less than the preset value, it is output.

2. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 1, characterized in that: Evaluating the impact of input parameters on output parameters includes the following steps: Build an optimal input parameter combination database. Users input the input parameters to be optimized through the terminal. The optimal input parameter combination database is retrieved according to the input parameters and calibrated. If the calibration meets the input parameters, the retrieved optimal input parameter combination data is output to the user. If not, it is transmitted to the defined variable device. Define variable devices to initialize input parameters, retrieve experimental data, and define input parameter ranges; change the value of each input parameter one by one, and record the changes in output results after each change; Calculate the impact measure of each input parameter on the output result based on the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than the preset value.

3. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 2, characterized in that: Record the changes in the output results after each change, including the following steps: Retrieve historical experimental data and expert knowledge base to set the value range of input parameters; the input parameters include the torque of PMSM under no-load, rated speed with load and maximum load working conditions; Change the value of each input parameter one by one to generate a sample set of output results; Based on the output result sample set, calculate the impact measure of each input parameter change on the output result, and quantify it according to the impact measure; Quantitatively measure the impact of input parameters on output variance, decompose the output variance into parts, and calculate the contribution of each input parameter; Adjust input parameters based on contribution values.

4. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 2, characterized in that: Identifying key data whose output impact is greater than a preset value includes the following steps: Calculate the impact measure of each input parameter on the output result based on the change of the output result, analyze the impact of each input parameter on the output parameter, and identify key data whose output impact is greater than the preset value; The key data less than the preset value is judged as a low-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; the key data greater than the preset value is judged as a high-sensitivity parameter, and a calculation is performed to determine whether the optimization target is achieved. If the optimization target is achieved, it is determined as the final structural parameter; If the low-sensitivity parameters or high-sensitivity parameters do not reach the optimization target, the structure is adjusted and the sensitivity analysis of the structural parameters is recalculated.

5. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 1, characterized in that: Screening out standard identification parameters includes the following steps: Assign initial weights to input parameters, evaluate the impact, and adjust the weights based on the impact evaluation results; arrange the sensitivity indexes of output parameters in descending order, with smaller sensitivity indexes indicating smaller impacts and larger sensitivity indexes indicating greater impacts; Set the input parameter weights according to the arrangement order, divide the standard weight by the sum of all standard weights for normalization; calculate the impact value to get the comprehensive impact, assign different weights to the impact values ​​of different attributes; adjust the optimization target according to the weight; The adjusted optimization target is subjected to fitness calculation, standard identification parameters are screened out, and standard input parameter combinations are obtained; the optimal input parameter combination database is retrieved, and a V-type magnetic steel rotor simulation model is constructed.

6. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 5, characterized in that: Building a V-shaped magnetic steel rotor simulation model includes the following steps: The adjusted optimization target is adaptively calculated to obtain the objective function; the objective function value is calculated to evaluate the fitness of the parameter combination; the parameter combination whose fitness reaches the standard is selected, and the parameter combination is iteratively optimized to obtain the standard input parameter combination; Retrieving the optimal input parameter combination database, and building a V-type magnetic steel rotor simulation model according to the optimal input parameter combination database; obtaining a data set from the parameters in the standard input parameter combination, and preprocessing the data set; The preprocessed data set is divided into a training set, a validation set and a test set; the training set is used to train the V-type magnetic steel rotor simulation model; and the standard input parameter combination is input into the V-type magnetic steel rotor simulation model for simulation.

7. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 6, characterized in that: The dataset is preprocessed, including the following steps: Retrieving the optimal input parameter combination database and setting the motor working conditions; wherein the electrical working conditions include no load, rated load and maximum speed load; Remove noise, outliers and missing values ​​from the data set; standardize the data, merge data from different sources, and extract key features; The preprocessed data is divided into training set, validation set and test set, and the training set is used to train the V-type magnetic steel rotor simulation model.

8. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 1, characterized in that: The simulation includes the following steps: Calculate the torque response of the motor under different working conditions, and compare the simulation result with the preset value. If the simulation result is greater than the preset value, it is judged that the parameter combination does not meet the standard; if the simulation result is less than the threshold, it is judged that the parameter combination meets the standard; Evaluate the comparison results of parameter combinations that do not meet the standards, make adjustments based on the evaluation, and recalculate the fitness; iterate in sequence until the parameter combination meets the standards; The parameter combinations that meet the standards are output to the cloud platform and stored in the optimal input parameter combination database; the cloud platform outputs the data to the user terminal and readjusts the V-type magnetic steel rotor simulation model based on the user terminal feedback.

9. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 8, characterized in that: Recalculate the fitness, including the following steps: According to the simulation results and fitness function, the input parameters are adjusted using the optimization algorithm; the rotor structure is determined to eliminate interference and select parameters; The first parameter distribution is checked for consistency with the second parameter distribution. If they are inconsistent, the first parameter distribution is readjusted. If they are consistent, the first parameter distribution and the second parameter distribution are further checked for consistency with the third parameter distribution. If any parameter distribution is inconsistent, the inconsistent parameter distribution is readjusted. Iterate in sequence until all parameter decoupling is completed. The parameters that complete the full parameter decoupling are determined as the optimal parameter combination, and the optimal parameter combination is re-input into the V-type magnetic steel rotor simulation model, and the simulation is re-performed until the parameter combination meets the standards.

10. The multi-objective parameter optimization design method for a V-shaped magnetic steel rotor of a permanent magnet synchronous motor according to claim 9, characterized in that: in, The first parameter distribution is decoupled from the second parameter distribution; the first parameter distribution, the second parameter distribution and the third parameter distribution are decoupled; and the steps are iterated in sequence.

Images