Motor design method and computing device
By optimizing the thermal circuit model and stress field response surface model of the motor through a multi-objective optimization algorithm, the problem of mutual influence between thermal performance and structural performance in traditional motor design is solved, and the synchronous improvement of motor performance is achieved.
Patent Information
- Application Number
- CN202510832971.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-19
- Publication Date
- 2025-09-26
AI Technical Summary
Traditional motor design methods ignore the interaction between thermal and structural performance, resulting in poor motor performance in actual operation.
A multi-objective optimization algorithm is used to iteratively optimize the thermal circuit model and stress field response surface model to simultaneously improve the thermal performance and structural performance of the motor. By obtaining the optimization variables, optimization objectives and constraints of the motor, the thermal circuit model and stress field response surface model are established to optimize the design parameters.
The balance and optimization of the motor's thermal and structural performance are achieved, and the overall performance and reliability of the motor are improved.
Smart Images
Figure CN120706013A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of motor design, and in particular to a motor design method and computing device. Background Art
[0002] Thermal management and structural stability are two key issues in motor design, particularly in applications requiring high performance and reliability. The thermal efficiency and structural strength of a motor during operation directly impact its performance and lifespan. Traditional motor design approaches typically focus on addressing either thermal or structural performance issues, ignoring the interplay between thermal and structural performance, potentially leading to poor motor performance in actual operation. Summary of the Invention
[0003] The embodiments of the present application provide a motor design method and computing device, aiming to solve the problem of how to simultaneously improve the thermal performance and structural performance of a motor.
[0004] The first aspect of the embodiment of the present application provides a motor design method, which includes: obtaining the optimization variables, optimization targets and constraints of the motor; wherein the optimization variables include the initial design parameters of the motor, the optimization targets include thermal performance optimization targets and structural performance optimization targets, and the constraints include thermal performance constraints and structural performance constraints. A thermal circuit model is established based on the structure, cooling method, thermal conductivity and thermal radiation coefficient of the motor. A stress field response surface model is established based on the structural stress data of the motor. Based on the initial design parameters, thermal performance optimization targets, thermal performance constraints, structural performance optimization targets and structural performance constraints, a multi-objective optimization algorithm is used to optimize the thermal circuit model and the stress field response surface model to obtain the target design parameters of the motor.
[0005] In this embodiment, a multi-objective optimization algorithm is used to iteratively optimize the thermal circuit model and the stress field response surface model so that the target design parameters simultaneously meet the thermal performance constraints and the structural performance constraints, thereby simultaneously improving the thermal performance and structural performance of the motor.
[0006] In one embodiment, a multi-objective optimization algorithm is used to optimize a thermal circuit model and a stress field response surface model based on initial design parameters, a thermal performance optimization target, thermal performance constraints, a structural performance optimization target, and structural performance constraints to obtain target design parameters of the motor. This includes: optimizing the thermal circuit model based on the initial design parameters, the thermal performance optimization target, and the thermal performance constraints to obtain the thermal performance design parameters of the motor using a multi-objective optimization algorithm; and optimizing the stress field response surface model based on the thermal performance design parameters, the structural performance optimization target, and the structural performance constraints to obtain the target design parameters using a multi-objective optimization algorithm.
[0007] In another embodiment, a multi-objective optimization algorithm is used to optimize a thermal circuit model and a stress field response surface model based on initial design parameters, a thermal performance optimization target, thermal performance constraints, a structural performance optimization target, and structural performance constraints to obtain target design parameters of the motor. This includes: optimizing the stress field response surface model based on the initial design parameters, the structural performance optimization target, and the structural performance constraints to obtain the structural performance design parameters of the motor; and optimizing the thermal circuit model based on the structural performance design parameters, the thermal performance optimization target, and the thermal performance constraints to obtain the target design parameters.
[0008] In another embodiment, based on the initial design parameters, thermal performance optimization objectives and thermal performance constraints, a multi-objective optimization algorithm is used to optimize the thermal circuit model to obtain the thermal performance design parameters of the motor, including: inputting the initial design parameters into the thermal circuit model to obtain the predicted temperature value of the motor. The first temperature change value of the motor is calculated based on the initial temperature value and the predicted temperature value of the motor. When the first temperature change value meets the first thermal performance constraint, the fluid movement of the motor is simulated to obtain the simulated temperature value of the motor. The second temperature change value of the motor is calculated based on the initial temperature value and the simulated temperature value. When the second temperature change value meets the second thermal performance constraint, the initial design parameters are saved, and the initial design parameters are the thermal performance design parameters. Among them, the first thermal performance constraint includes that the first temperature change value is less than or equal to the first temperature threshold; the second thermal performance constraint includes that the second temperature change value is less than or equal to the second temperature threshold.
[0009] In another embodiment, the method further includes: adjusting the initial design parameters based on the thermal performance optimization objective when the first temperature change value does not satisfy the first thermal performance constraint condition, and optimizing the thermal circuit model using a multi-objective optimization algorithm when the second temperature change value does not satisfy the second thermal performance constraint condition.
[0010] In another embodiment, a multi-objective optimization algorithm is used to optimize a stress field response surface model based on initial design parameters, structural performance optimization objectives, and structural performance constraints to obtain the structural performance design parameters of a motor. This includes inputting the initial design parameters into the stress field response surface model to obtain a stress distribution of the motor. When the stress distribution satisfies the structural performance constraints, the initial design parameters are saved and become the structural performance design parameters. The stress distribution includes stress values at multiple design points on the motor structure, and the structural performance constraints include ensuring that the stress value at each design point is greater than or equal to a stress threshold.
[0011] In another embodiment, the method further includes: when the stress distribution does not satisfy the structural performance constraint conditions, adjusting the initial design parameters based on the structural performance optimization goal, or optimizing the stress field response surface model using a multi-objective optimization algorithm.
[0012] In another embodiment, establishing a stress field response surface model based on structural stress data of a motor includes: obtaining structural stress data of the motor, the structural stress data being obtained by simulating the structural stress of the motor; establishing a neural network model; and training the neural network model based on the structural stress data of the motor. When a prediction error of the neural network model is less than or equal to an error threshold, saving the neural network model, whereby the neural network model becomes a stress field response surface model.
[0013] In another embodiment, the method further includes: when the prediction error of the neural network model is greater than an error threshold, optimizing the neural network model using a multi-objective optimization algorithm.
[0014] A second aspect of an embodiment of the present application provides a computing device comprising a memory and a processor, and implementing the method provided in the first aspect when the processor executes computer instructions stored in the memory.
[0015] A third aspect of an embodiment of the present application provides a computer-readable storage medium having computer instructions stored thereon, which implements the method provided in the first aspect when a processor executes the computer instructions.
[0016] A fourth aspect of an embodiment of the present application provides a computer program product, which includes computer instructions, and when a processor executes the computer instructions, implements the method provided in the first aspect.
[0017] It can be understood that the beneficial effects of the computing device provided in the second aspect, the computer-readable storage medium provided in the third aspect, and the computer program product provided in the fourth aspect of the embodiment of this application are roughly the same as the beneficial effects of the method provided in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 The present invention is a flowchart of a motor design method provided by an embodiment.
[0019] Figure 2 This is a schematic diagram of a thermal circuit model provided as an example.
[0020] Figure 3 It is a flowchart of establishing a stress field response surface model provided as an example.
[0021] Figure 4 The flowchart of obtaining the thermal performance design parameters of a motor is provided as an example.
[0022] Figure 5 The flowchart of obtaining target design parameters is provided as an example.
[0023] Figure 6 This is a schematic diagram of the structure of a computing device provided by an embodiment. DETAILED DESCRIPTION
[0024] It should be noted that in the embodiments of the present application, "multiple" refers to two or more than two. The terms "first", "second", "third", "fourth", etc. in the specification, claims, and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of the present application or the methods shown in the flowcharts include one or more steps for implementing the methods. Without departing from the scope of the claims, the execution order of the multiple steps can be interchanged with each other, and some of the steps can also be deleted.
[0025] In the embodiments of the present application, computing devices include, but are not limited to, smart phones, tablet computers, PDAs, laptop computers, intelligent robots, drones, personal digital assistants (PDAs), vehicle-mounted devices, mobile Internet devices (MIDs), wireless terminals in industrial control, wireless terminals in self-driving, and wireless terminals in transportation safety.
[0026] The motor design method of the embodiment of the present application can achieve a balance and optimization of the thermal performance and structural performance of the motor. The application scenarios of the motor include, but are not limited to, automobile manufacturing, aerospace, robotics, power generation equipment and household appliances. For example, in the automobile manufacturing scenario, the motor design method of the embodiment of the present application can balance the thermal efficiency and structural strength of the motor, thereby improving the performance and endurance of the entire vehicle. In the aerospace scenario, the motor design method of the embodiment of the present application can ensure the stable operation of the motor in extreme environments, thereby improving the reliability and safety of the motor.
[0027] The motor design method according to the embodiment of the present application is described in detail below.
[0028] Exemplarily, the motor design method is applied to a computing device, such as Figure 1 As shown, the motor design method includes the following steps: S101. Obtain optimization variables, optimization targets, and constraints of the motor, wherein the optimization variables include initial design parameters of the motor, the optimization targets include thermal performance optimization targets and structural performance optimization targets, and the constraints include thermal performance constraints and structural performance constraints.
[0029] In this embodiment, the motor's optimization variables, their value ranges, optimization objectives, and constraints can be customized as needed. The optimization variables and their value ranges are used to define the motor's design parameter combinations. The optimization objectives and constraints are used to adjust and optimize the motor's design parameters.
[0030] The design parameters of the motor include, but are not limited to, voltage, current, temperature, speed, and the size, number, and arrangement of its structural components. The structural components of the motor include, but are not limited to, the stator, rotor, windings, shaft, air gap, cooling slots, end caps, and housing.
[0031] S102: Establish a thermal circuit model based on the structure, cooling method, thermal conductivity and thermal radiation coefficient of the motor.
[0032] In this embodiment, the thermal circuit model is also called a thermal resistance network or thermal circuit model, which is used to simulate and analyze the temperature distribution, local maximum temperature points and heat transfer process during motor operation. The thermal circuit model models heat transfer mechanisms such as heat conduction, convection and radiation through electrical components such as resistors and capacitors. The thermal circuit model includes a heat source, thermal resistance, thermal capacitance and nodes. The heat source is equivalent to the power supply in the circuit, which is used to provide heat input. The thermal resistance is equivalent to the resistor in the circuit, which is used to represent the ability to hinder heat transfer. The thermal capacitance is equivalent to the capacitor in the circuit, which is used to represent the ability of an object to store heat. The node represents the junction between different parts, and each node has a temperature value. The node temperature is used to calculate the heat flow through each thermal resistance.
[0033] For example, Figure 2 As shown in the figure, the heat sources in the thermal circuit model include stator core loss, rotor core loss, copper wire loss, permanent magnet loss, and friction loss. The heat conduction paths in the thermal circuit model include stator to casing, winding to stator, stator to air gap, air gap to rotor, rotor to shaft, and shaft to end cap.
[0034] S103. Establish a stress field response surface model based on the structural stress data of the motor.
[0035] In this embodiment, the stress field response surface model is a mathematical model that describes the relationship between structural stress and input variables (such as load, geometric dimensions, material properties, etc.). It applies the response surface method to mechanical analysis to predict the stress distribution inside the structure under different conditions.
[0036] For example, Figure 3 As shown in Figure 2, establishing the stress field response surface model includes the following steps: S201 : Acquire structural stress data of the motor, and divide the structural stress data into training data and test data.
[0037] The structural stress data is obtained by simulating the structural stress of the motor. Finite Element Analysis (FEA) can be used to simulate the structural stress of the motor.
[0038] S202. Determine the topological structure of the neural network model.
[0039] The topological structure includes the number of neurons in the input layer, the number of neurons in the hidden layer, and the number of neurons in the output layer.
[0040] S203. Generate an initial population based on the parameters of the neural network model.
[0041] The parameters of the neural network model include weights and error thresholds. The initial population is a group of individuals (solutions) that are randomly generated or selected according to a certain strategy.
[0042] S204: Establish a neural network model based on the topological structure and parameters of the neural network model.
[0043] S205: Train the neural network model according to the training data.
[0044] S206: Test the neural network model according to the test data.
[0045] S207: Determine whether the prediction error of the neural network model is greater than an error threshold.
[0046] If yes, execute steps S208 - S211 ; if no, execute step S212 .
[0047] S208. Optimize the neural network model using a multi-objective optimization algorithm.
[0048] Among them, the multi-objective optimization algorithm includes the NSGA3 algorithm. The NSGA3 algorithm can handle complex optimization problems with multiple competing objectives.
[0049] S209: Perform crossover and mutation operations on the initial population to obtain new individuals.
[0050] The crossover operation selects two individuals (parents) from a population and then exchanges some of their genetic information in a specific manner to create a new individual (offspring). The mutation operation randomly changes the position or value of certain genes on an individual's chromosome. Crossover and mutation operations are used to explore the solution space and find optimal or near-optimal solutions to optimization problems.
[0051] S210. Evaluate the fitness of the new individuals to generate a new population.
[0052] Among them, fitness evaluation is used to screen out individuals with higher fitness.
[0053] S211. Determine whether the current number of iterations is equal to the maximum number of iterations.
[0054] If yes, execute step S212; if no, return to execute step S205.
[0055] S212. Save the neural network model, which is a stress field response surface model.
[0056] In this embodiment, when the prediction error of the neural network model is greater than an error threshold, a multi-objective optimization algorithm is used to optimize the neural network model until the prediction error is less than or equal to the error threshold, or the current iteration count equals the maximum iteration count. When the prediction error of the neural network model is less than or equal to the error threshold, the neural network model is used as a stress field response surface model. The accuracy of the stress field response surface model is ensured by iteratively optimizing the neural network model.
[0057] S104. Based on the initial design parameters, thermal performance optimization objectives, thermal performance constraints, structural performance optimization objectives, and structural performance constraints, a multi-objective optimization algorithm is used to optimize the thermal circuit model and the stress field response surface model to obtain target design parameters of the motor.
[0058] In one embodiment, a multi-objective optimization algorithm is first used to optimize the thermal circuit model based on initial design parameters, thermal performance optimization objectives, and thermal performance constraints to obtain the thermal performance design parameters of the motor. Then, a multi-objective optimization algorithm is used to optimize the stress field response surface model based on the thermal performance design parameters, structural performance optimization objectives, and structural performance constraints to obtain the target design parameters.
[0059] For example, Figure 4 As shown, obtaining the thermal performance design parameters of the motor includes the following steps: S301 : Input the initial design parameters into the thermal circuit model to obtain the predicted temperature value of the motor.
[0060] S302 : Calculate a first temperature change value of the motor according to the initial temperature value and the predicted temperature value of the motor.
[0061] The first temperature change value is the difference between the predicted temperature value and the initial temperature value.
[0062] S303: Determine whether the first temperature change value satisfies a first thermal performance constraint condition.
[0063] If yes, execute steps S304 - S306 ; if no, execute step S309 and return to execute step S301 .
[0064] The first thermal performance constraint condition includes that the first temperature change value is less than or equal to a first temperature threshold.
[0065] S304: Simulate the fluid movement of the motor to obtain a simulated temperature value of the motor.
[0066] Among them, computational fluid dynamics (CFD) can be used to simulate the fluid movement of the motor.
[0067] S305 : Calculate a second temperature change value of the motor according to the initial temperature value and the simulated temperature value.
[0068] The second temperature change value is the difference between the simulated temperature value and the initial temperature value.
[0069] S306: Determine whether the second temperature change value satisfies a second thermal performance constraint condition.
[0070] If yes, execute step S307; if no, execute step S308 and return to execute step S301.
[0071] The second thermal performance constraint condition includes that the second temperature change value is less than or equal to a second temperature threshold.
[0072] S307 , saving initial design parameters, where the initial design parameters are thermal performance design parameters.
[0073] S308. Optimize the thermal circuit model using a multi-objective optimization algorithm.
[0074] Among them, the multi-objective optimization algorithm includes the NSGA3 algorithm.
[0075] S309: Adjust initial design parameters based on thermal performance optimization objectives.
[0076] In this embodiment, when the first temperature change value does not satisfy the first thermal performance constraint, the initial design parameters are adjusted based on the thermal performance optimization objective. When the second temperature change value does not satisfy the second thermal performance constraint, a multi-objective optimization algorithm is used to optimize the thermal circuit model. When the first temperature change value satisfies the first thermal performance constraint and the second temperature change value satisfies the second thermal performance constraint, the initial design parameters are used as the thermal performance design parameters. By optimizing the initial design parameters or the thermal circuit model, the accuracy and reliability of the thermal performance design parameters are ensured.
[0077] For example, after obtaining the thermal performance design parameters, as shown in FIG. Figure 5 As shown, obtaining the target design parameters includes the following steps: S401. Inputting thermal performance design parameters into a stress field response surface model to obtain the stress distribution of the motor.
[0078] The stress distribution includes stress values at several design points on the motor structure.
[0079] S402: Determine whether the stress distribution satisfies the structural performance constraint conditions.
[0080] If yes, execute step S403; if no, execute step S404 and return to execute step S401.
[0081] Among them, the structural performance constraint condition includes that the stress value of each design point is greater than or equal to the stress threshold.
[0082] S403 : Save the thermal performance design parameters, which are target design parameters.
[0083] S404. Adjust thermal performance design parameters based on the structural performance optimization objective, or optimize the stress field response surface model using a multi-objective optimization algorithm.
[0084] Among them, the multi-objective optimization algorithm includes the NSGA3 algorithm.
[0085] In this embodiment, when the stress distribution does not meet the structural performance constraints, the thermal performance design parameters are adjusted based on the structural performance optimization objective, or a multi-objective optimization algorithm is used to optimize the stress field response surface model. When the stress distribution meets the structural performance constraints, the thermal performance design parameters are used as the target design parameters. The accuracy and reliability of the target design parameters are ensured by optimizing the thermal performance design parameters or the stress field response surface model. Because the target design parameters meet both the thermal and structural performance constraints, the thermal and structural performance of the motor are simultaneously improved.
[0086] In another embodiment, a multi-objective optimization algorithm is first used to optimize a stress field response surface model based on initial design parameters, structural performance optimization objectives, and structural performance constraints to obtain the structural performance design parameters of the motor. Then, a multi-objective optimization algorithm is used to optimize a thermal circuit model based on the structural performance design parameters, thermal performance optimization objectives, and thermal performance constraints to obtain the target design parameters.
[0087] It is understood that the specific implementation method for obtaining structural performance design parameters can be found in Figure 5 The process shown in FIG. 1 and the specific implementation method of obtaining the target design parameters after obtaining the structural performance design parameters can be found in FIG. Figure 4 The process shown will not be repeated here.
[0088] S105 : Generate a target population based on the target design parameters, and perform non-dominated sorting on the individuals in the target population to obtain non-dominated individuals.
[0089] In this embodiment, non-dominated sorting determines which individuals in a population are non-dominated based on their performance under multiple objective functions. This means that no other individual can improve at least one objective without degrading another objective. For example, if there is no way for two solutions A and B to improve the other objective without compromising the other objective, then the two solutions are said to be non-dominated.
[0090] S106. Generate Pareto frontier based on non-dominated individuals.
[0091] In this embodiment, every solution on the Pareto front is a non-dominated solution.
[0092] S107: Determine whether the current number of iterations is equal to the maximum number of iterations.
[0093] If yes, execute step S108; if no, return to execute step S105.
[0094] S108. Verify the Pareto front using finite element analysis.
[0095] In the above embodiment, a multi-objective optimization algorithm is used to iteratively optimize the thermal circuit model and the stress field response surface model, ensuring that the target design parameters simultaneously meet both thermal and structural performance constraints. This improves both the thermal and structural performance of the motor. Furthermore, the accuracy and reliability of the optimization results are ensured by verifying the Pareto frontier.
[0096] The various functions or steps performed by the computing device in the above embodiments may also be applied to a chip, a computer-readable storage medium, or a computer program product.
[0097] For example, Figure 6 As shown, the computing device 100 includes a processor 110 , an external memory interface 120 , and an internal memory 121 .
[0098] The processor 110 is used to execute the various functions or steps performed by the computing device in the above embodiments. The processor 110 includes, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), a neural-network processing unit (NPU), and an application processor (AP).
[0099] The external memory interface 120 is used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the computing device. The external memory card communicates with the processor 110 through the external memory interface 120 to implement data storage.
[0100] The internal memory 121 is used to store computer executable program code, which includes instructions. The processor 110 executes the various functions or steps performed by the computing device in the above-mentioned embodiment by running the instructions stored in the internal memory 121. The internal memory 121 includes a program storage area and a data storage area. The program storage area can store an operating system, at least one APP required for a function, etc. The data storage area can store data created during the use of the computing device. The internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, a flash memory device, and a universal flash storage (UFS).
[0101] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the computing device. In other embodiments, the computing device may include more or fewer components than shown, or combine or split some components, or arrange the components differently.
[0102] The chip includes a processor and an interface circuit, the processor and the interface circuit being electrically connected. The interface circuit can read computer instructions stored in the memory and send the computer instructions to the processor. When the processor executes the computer instructions, the various functions or steps performed by the computing device in the above embodiments are implemented.
[0103] The computer-readable storage medium stores computer instructions, and when the processor executes the computer instructions, the various functions or steps performed by the computing device in the above embodiments are implemented.
[0104] Computer-readable storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer.
[0105] The computer program product includes computer instructions, and when a processor executes the computer instructions, the various functions or steps performed by the computing device in the above embodiments are implemented.
[0106] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the relevant technical field without departing from the purpose of the present application.
Claims
1. A motor design method, characterized in that: The method comprises: Obtaining optimization variables, optimization targets, and constraints of the motor; wherein the optimization variables include initial design parameters of the motor, the optimization targets include thermal performance optimization targets and structural performance optimization targets, and the constraints include thermal performance constraints and structural performance constraints; Establishing a thermal circuit model according to the structure, cooling method, thermal conductivity and thermal radiation coefficient of the motor; Establishing a stress field response surface model based on the structural stress data of the motor; Based on the initial design parameters, the thermal performance optimization target, the thermal performance constraints, the structural performance optimization target and the structural performance constraints, a multi-objective optimization algorithm is used to optimize the thermal circuit model and the stress field response surface model to obtain the target design parameters of the motor.
2. The method according to claim 1, wherein The method of optimizing the thermal circuit model and the stress field response surface model using a multi-objective optimization algorithm based on the initial design parameters, the thermal performance optimization target, the thermal performance constraints, the structural performance optimization target, and the structural performance constraints to obtain target design parameters of the motor includes: Based on the initial design parameters, the thermal performance optimization target and the thermal performance constraint conditions, the thermal circuit model is optimized using the multi-objective optimization algorithm to obtain the thermal performance design parameters of the motor; Based on the thermal performance design parameters, the structural performance optimization target and the structural performance constraint conditions, the stress field response surface model is optimized using the multi-objective optimization algorithm to obtain the target design parameters.
3. The method according to claim 1, wherein The method of optimizing the thermal circuit model and the stress field response surface model using a multi-objective optimization algorithm based on the initial design parameters, the thermal performance optimization target, the thermal performance constraints, the structural performance optimization target, and the structural performance constraints to obtain target design parameters of the motor includes: Based on the initial design parameters, the structural performance optimization target and the structural performance constraint conditions, the stress field response surface model is optimized using the multi-objective optimization algorithm to obtain the structural performance design parameters of the motor; Based on the structural performance design parameters, the thermal performance optimization target and the thermal performance constraint conditions, the multi-objective optimization algorithm is used to optimize the thermal circuit model to obtain the target design parameters.
4. The method according to claim 2, wherein The step of optimizing the thermal circuit model based on the initial design parameters, the thermal performance optimization target, and the thermal performance constraint conditions using the multi-objective optimization algorithm to obtain the thermal performance design parameters of the motor includes: Inputting the initial design parameters into the thermal circuit model to obtain a predicted temperature value of the motor; Calculating a first temperature change value of the motor according to the initial temperature value of the motor and the predicted temperature value; When the first temperature change value satisfies a first thermal performance constraint condition, simulating the fluid movement of the motor to obtain a simulated temperature value of the motor; Calculating a second temperature change value of the motor according to the initial temperature value and the simulated temperature value; When the second temperature change value satisfies a second thermal performance constraint condition, saving the initial design parameters, where the initial design parameters are the thermal performance design parameters; The first thermal performance constraint condition includes that the first temperature change value is less than or equal to a first temperature threshold; and the second thermal performance constraint condition includes that the second temperature change value is less than or equal to a second temperature threshold.
5. The method according to claim 4, wherein The method further comprises: When the first temperature change value does not satisfy the first thermal performance constraint condition, adjusting the initial design parameters based on the thermal performance optimization goal; When the second temperature change value does not satisfy the second thermal performance constraint condition, the multi-objective optimization algorithm is used to optimize the thermal circuit model.
6. The method according to claim 3, wherein The method of optimizing the stress field response surface model based on the initial design parameters, the structural performance optimization target, and the structural performance constraint conditions using the multi-objective optimization algorithm to obtain the structural performance design parameters of the motor includes: Inputting the initial design parameters into the stress field response surface model to obtain the stress distribution of the motor; When the stress distribution satisfies the structural performance constraint condition, saving the initial design parameters, where the initial design parameters are the structural performance design parameters; The stress distribution includes stress values of several design points on the structure of the motor; and the structural performance constraint condition includes that the stress value of each of the design points is greater than or equal to a stress threshold.
7. The method according to claim 6, wherein The method further comprises: When the stress distribution does not satisfy the structural performance constraint condition, the initial design parameters are adjusted based on the structural performance optimization objective, or the stress field response surface model is optimized using the multi-objective optimization algorithm.
8. The method according to any one of claims 1 to 7, wherein The step of establishing a stress field response surface model according to the structural stress data of the motor includes: Acquiring structural stress data of the motor, wherein the structural stress data is obtained based on simulating the structural stress of the motor; Build a neural network model; Training the neural network model based on the structural stress data of the motor; When the prediction error of the neural network model is less than or equal to the error threshold, the neural network model is saved, and the neural network model is the stress field response surface model.
9. The method according to claim 8, wherein The method further comprises: When the prediction error of the neural network model is greater than the error threshold, the multi-objective optimization algorithm is used to optimize the neural network model.
10. A computing device, characterized in that The device comprises a memory and a processor, and when the processor executes computer instructions stored in the memory, the method according to any one of claims 1 to 9 is implemented.