Optimization method and device of motor cooling structure, equipment and storage medium

Abstract

The invention provides an optimization method, device and equipment of a motor cooling structure and a storage medium, and the optimization method comprises the steps: carrying out an orthogonal test based on the size parameters, value ranges and value numbers of a plurality of specific cooling structures of a motor, and obtaining a plurality of test combinations; constructing a plurality of three-dimensional finite element models for the specific cooling structure, and simulating a plurality of target cooling structures in the motor by using the three-dimensional finite element models to obtain state parameter simulation results of the target cooling structures; constructing an order reduction model based on the simulation result, and determining an experimental value corresponding to each target cooling structure state parameter; and based on the experimental values and a preset optimization algorithm, determining the optimal value of the size parameter of each specific cooling structure, and adjusting the corresponding motor cooling structure. By adopting the technical scheme provided by the invention, the scheme optimization period is remarkably shortened, the development efficiency is improved, the large-scale refined design of the cooling structure is also realized, and the reliability and high efficiency of the cooling scheme are ensured.

Description

Technical Field

[0001] The present application relates to the technical field of motor cooling structure optimization, and in particular to a method, device, equipment and storage medium for optimizing a motor cooling structure. Background Art

[0002] The development of new energy vehicles has promoted the development of motors towards high precision, high power density and miniaturization, but it has also brought about the problem of a sharp increase in internal heat generation and insufficient effective heat dissipation space, resulting in excessive motor temperature, which seriously affects the motor life and operating safety. The automotive permanent magnet synchronous motor mainly adopts two cooling methods: water cooling and oil cooling. Among them, oil cooling has become the mainstream direction of current product development because its coolant directly contacts the winding and has a significant heat dissipation effect. At present, the cooling structure optimization for oil-cooled motors is mainly based on three-dimensional finite element simulation. First, engineers determine the key parameters in the motor model based on experience; then, set the boundary conditions related to oil cooling in the model; then, mesh the motor model; secondly, perform simulation calculations to obtain the temperature distribution of each motor component, the flow state of the coolant, and the pressure drop of the inlet and outlet oil ports; finally, analyze the results and determine the optimization plan.

[0003] However, due to the reliance on engineers’ experience and the extremely high computing power requirements of three-dimensional finite element simulation analysis, it is often only possible to make rough selection comparisons among a limited number of pre-set solutions. It is difficult to conduct extensive searches within the range of many possible parameter combinations, and it is impossible to obtain more efficient cooling solutions. Summary of the invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide an optimization method, device, equipment and storage medium for a motor cooling structure, which not only significantly shortens the solution optimization cycle and improves development efficiency, but also realizes large-scale and refined design of the cooling structure, ensuring the reliability and efficiency of the cooling solution.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, an embodiment of the present application provides a method for optimizing a motor cooling structure, the optimization method comprising:

[0007] Based on the size parameter of each specific cooling structure in the multiple specific cooling structures of the motor, the value range of each size parameter and the number of values ​​of the size parameter, an orthogonal test is performed to obtain multiple test combinations of the size parameters of each specific cooling structure;

[0008] Based on the multiple test combinations, construct multiple three-dimensional finite element models of specific cooling structures for the motor;

[0009] For multiple target cooling structures in the motor, use each of the multiple three-dimensional finite element models to perform simulation to obtain simulation results corresponding to the state parameters of each of the multiple target cooling structures of the motor;

[0010] Based on the simulation results, a reduced-order model for calculating state parameters of a target cooling structure is constructed;

[0011] Determining, based on the reduced-order model, an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures;

[0012] Based on the experimental values ​​and a preset optimization algorithm, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value.

[0013] Preferably, constructing multiple three-dimensional finite element models for a specific cooling structure of the motor based on the multiple test combinations includes:

[0014] Based on the multiple test combinations, construct multiple motor models;

[0015] extracting a fluid domain of a motor cooling structure of each motor model in a plurality of motor models;

[0016] Meshing the fluid domain, and setting parameters of a coolant flowing through the fluid domain for the meshed fluid domain;

[0017] Meshing the motor solid components in the motor model after extracting the fluid domain and setting the coolant parameters, and setting parameters corresponding to the motor solid components for the meshed motor solid components;

[0018] The motor model after setting the parameters corresponding to the motor solid components is determined as a three-dimensional finite element model for the specific cooling structure of the motor, and multiple three-dimensional finite element models for the specific cooling structure of the motor are constructed.

[0019] Preferably, constructing a reduced-order model for calculating state parameters of a target cooling structure based on the simulation results comprises:

[0020] Based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first validation set, and a first test set;

[0021] Standardizing the training set, validation set, and test set to obtain a second training set, a second validation set, and a second test set;

[0022] Based on the second training set, the second validation set, the second test set and the initial reduced order model, respectively, using the second training set to train the initial reduced order model, using the second validation set to validate the initial reduced order model during the training process, and using the second test set to test the trained and validated initial reduced order model;

[0023] Based on the results of the tests, a reduced-order model for calculating state parameters of the target cooling structure is constructed.

[0024] Preferably, determining the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusting the corresponding specific motor cooling structure based on the optimal value includes:

[0025] Based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure;

[0026] According to the optimal value corresponding to the state parameter of each target cooling structure, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value corresponding to the size parameter of each specific cooling structure.

[0027] In a second aspect, an embodiment of the present application further provides an optimization device for a motor cooling structure, the optimization device comprising:

[0028] A test combination determination module performs an orthogonal test based on a size parameter of each specific cooling structure in a plurality of specific cooling structures of the motor, a value range of each size parameter, and the number of values ​​of the size parameter, to obtain a plurality of test combinations of the size parameters of each specific cooling structure;

[0029] A three-dimensional finite element model building module is used to build multiple three-dimensional finite element models of a specific cooling structure for the motor based on the multiple test combinations;

[0030] A simulation result determination module, for multiple target cooling structures in the motor, using each of the multiple three-dimensional finite element models to perform simulation, and obtain a simulation result corresponding to a state parameter of each of the multiple target cooling structures of the motor;

[0031] A reduced-order model building module, based on the simulation results, builds a reduced-order model for calculating state parameters of a target cooling structure;

[0032] an experimental value determination module, which determines, based on the reduced-order model, an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures;

[0033] The adjustment module determines the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusts the corresponding specific motor cooling structure based on the optimal value.

[0034] Preferably, the three-dimensional finite element model building module is specifically used for:

[0035] Based on the multiple test combinations, construct multiple motor models;

[0036] extracting a fluid domain of a motor cooling structure of each motor model in a plurality of motor models;

[0037] Meshing the fluid domain, and setting parameters of a coolant flowing through the fluid domain for the meshed fluid domain;

[0038] Meshing the motor solid components in the motor model after extracting the fluid domain and setting the coolant parameters, and setting parameters corresponding to the motor solid components for the meshed motor solid components;

[0039] The motor model after setting the parameters corresponding to the motor solid components is determined as a three-dimensional finite element model for the specific cooling structure of the motor, and multiple three-dimensional finite element models for the specific cooling structure of the motor are constructed.

[0040] Preferably, the reduced-order model building module is specifically used for:

[0041] Based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first validation set, and a first test set;

[0042] Standardizing the training set, validation set, and test set to obtain a second training set, a second validation set, and a second test set;

[0043] Based on the second training set, the second validation set, the second test set and the initial reduced order model, respectively, using the second training set to train the initial reduced order model, using the second validation set to validate the initial reduced order model during the training process, and using the second test set to test the trained and validated initial reduced order model;

[0044] Based on the results of the tests, a reduced-order model for calculating state parameters of the target cooling structure is constructed.

[0045] Preferably, the adjustment module is specifically used for:

[0046] Based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure;

[0047] According to the optimal value corresponding to the state parameter of each target cooling structure, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value corresponding to the size parameter of each specific cooling structure.

[0048] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the method for optimizing the motor cooling structure described in the first aspect or any possible implementation manner of the first aspect.

[0049] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of optimizing the motor cooling structure described in the first aspect or any possible implementation manner of the first aspect are executed.

[0050] An optimization method, device, equipment and storage medium for a motor cooling structure provided in an embodiment of the present application, first, based on the size parameters, value ranges and number of values ​​of multiple specific cooling structures of the motor, an orthogonal test is performed to obtain multiple test combinations. Then, multiple three-dimensional finite element models for specific cooling structures are constructed, and multiple target cooling structures in the motor are simulated using the three-dimensional finite element model to obtain simulation results of the state parameters of the target cooling structure. Next, a reduced-order model is constructed based on the simulation results, and the experimental values ​​corresponding to the state parameters of each target cooling structure are determined. Finally, based on the experimental values ​​and the preset optimization algorithm, the optimal values ​​of the size parameters of each specific cooling structure are determined, and the corresponding motor cooling structure is adjusted. In this way, not only the scheme optimization cycle is significantly shortened and the development efficiency is improved, but also the large-scale refined design of the cooling structure is realized, ensuring the reliability and efficiency of the cooling scheme. In this way, not only the scheme optimization cycle is significantly shortened and the development efficiency is improved, but also the large-scale refined design of the cooling structure is realized, ensuring the reliability and efficiency of the cooling scheme.

[0051] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A flow chart showing a method for optimizing a motor cooling structure provided by an embodiment of the present application is shown;

[0054] Figure 2 A schematic diagram showing a method for optimizing a motor cooling structure provided by an embodiment of the present application is shown;

[0055] Figure 3 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0056] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0057] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0058] In order to enable those skilled in the art to use the contents of this application, the following implementation methods are given in combination with the specific application scenario "optimization of motor cooling structure". For those skilled in the art, the general principles defined here can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0059] The following methods, devices, electronic devices or computer-readable storage media of the embodiments of the present application can be applied to any scenario requiring optimization of the motor cooling structure. The embodiments of the present application are not limited to specific application scenarios. Any scheme using the optimization method, device, equipment and storage medium of the motor cooling structure provided by the embodiments of the present application is within the protection scope of the present application.

[0060] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0061] The development of new energy vehicles has promoted the development of motors towards high precision, high power density and miniaturization, but it has also brought about the problem of a sharp increase in internal heat generation and insufficient effective heat dissipation space, resulting in excessive motor temperature, which seriously affects the motor life and operating safety. The automotive permanent magnet synchronous motor mainly adopts two cooling methods: water cooling and oil cooling. Among them, oil cooling has become the mainstream direction of current product development because its coolant directly contacts the winding and has a significant heat dissipation effect. At present, the cooling structure optimization for oil-cooled motors is mainly based on three-dimensional finite element simulation. First, engineers determine the key parameters in the motor model based on experience; then, set the boundary conditions related to oil cooling in the model; then, mesh the motor model; secondly, perform simulation calculations to obtain the temperature distribution of each component of the motor, the flow state of the coolant, and the pressure drop of the inlet and outlet oil ports; finally, analyze the results and determine the optimization plan. However, due to the reliance on the experience of engineers and the extremely high computing power requirements of three-dimensional finite element simulation analysis, it is often only possible to make a rough selection comparison among a limited number of pre-set schemes, and it is difficult to conduct a wide search within a wide range of possible parameter combinations, and it is impossible to obtain a more efficient cooling solution.

[0062] In response to the above problems, the embodiments of the present application provide an optimization method, device, equipment and storage medium for a motor cooling structure, which not only significantly shortens the solution optimization cycle and improves development efficiency, but also realizes large-scale and refined design of the cooling structure, ensuring the reliability and efficiency of the cooling solution.

[0063] To facilitate the understanding of the present application, the technical solution provided by the present application is described in detail below in conjunction with specific embodiments.

[0064] See also Figure 1 , Figure 1 A flow chart of a method for optimizing a motor cooling structure provided in an embodiment of the present application.

[0065] like Figure 1 As shown in , the optimization method includes:

[0066] Step S101, based on the size parameter of each specific cooling structure in multiple specific cooling structures of the motor, the value range of each size parameter and the number of values ​​of the size parameter, an orthogonal test is performed to obtain multiple test combinations of the size parameters of each specific cooling structure;

[0067] In the embodiment of the present application, as an example, the specific cooling structure of the present application includes: stator and winding oil spraying ports. The size parameters of the specific cooling structure of the present application include: stator oil channel depth, stator oil channel width, number of stator oil channels, winding oil spraying port diameter and number of winding oil spraying ports. Here, based on actual experience, the five parameters that have the greatest impact on the heat dissipation efficiency of the motor are extracted, and the five parameters are used as optimization targets.

[0068] As an example, a value range of the dimension parameter of each specific cooling structure is set, and the number of levels of the dimension parameter of each specific cooling structure is set. According to the value range and the number of levels, an orthogonal table is selected, and an orthogonal test is performed on the dimension parameters of multiple specific cooling structures to obtain multiple representative test combinations. Here, the number of levels is the number of values ​​of the dimension parameter.

[0069] Step S102: constructing multiple three-dimensional finite element models for a specific cooling structure of the motor based on the multiple test combinations.

[0070] Here, the number of test combinations corresponds to the number of 3D finite element models. In each 3D finite element model, the size parameter values ​​of each specific cooling structure are different, and the rest of the settings remain the same. As an example, if there are five test combinations, five 3D finite element models are constructed.

[0071] Regarding step S102, in specific implementation, as an example, the following steps may be included:

[0072] First, a plurality of motor models are constructed based on the plurality of test combinations.

[0073] Then, a fluid domain of a motor cooling structure of each of the plurality of motor models is extracted.

[0074] Subsequently, the fluid domain is meshed, and the parameters of the coolant flowing through the fluid domain are set for the meshed fluid domain. Here, the fluid domain is meshed to determine the boundary layer and the mesh size, and the mesh is generated.

[0075] Secondly, meshing is performed on the motor solid components in the motor model after extracting the fluid domain and setting the coolant parameters, and parameters corresponding to the motor solid components are set for the meshed motor solid components. Here, the parameters corresponding to the motor solid components include: contact surface setting parameters, contact thermal resistance heat value, and heat source loading parameters.

[0076] Finally, each motor model after setting the parameters corresponding to the motor solid component is determined as a three-dimensional finite element model for the specific cooling structure of the motor, and multiple three-dimensional finite element models for the specific cooling structure of the motor are constructed.

[0077] Step S103 , for multiple target cooling structures in the motor, use each of the multiple three-dimensional finite element models to perform simulation, and obtain simulation results corresponding to the state parameters of each of the multiple target cooling structures of the motor.

[0078] As an example, the target cooling structure of the motor includes: stator, winding and winding oil spray port. The state parameters of the target cooling structure of the motor include: maximum winding temperature, average winding temperature, maximum stator temperature, average stator temperature and inlet and outlet pressure drop of the winding oil spray port. Here, the maximum temperature parameter is retrieved from the simulation results of each three-dimensional finite element model to ensure that the maximum temperature limit is not exceeded during motor operation; the average temperature parameter is retrieved to ensure that the overall temperature of the motor is as evenly distributed as possible; the inlet and outlet pressure drop of the winding oil spray port is retrieved to ensure that the cooling scheme can take into account the flow resistance characteristics and make the flow resistance as small as possible while meeting the heat dissipation requirements.

[0079] Step S104: constructing a reduced-order model for calculating state parameters of a target cooling structure based on the simulation results.

[0080] Here, the order reduction method selected in the reduced-order model may include but is not limited to: neural network fitting and state-space equations. As an example, the order reduction method selected in this application is neural network fitting. The input of the reduced-order model is set to the size parameters of each specific cooling structure in a plurality of specific cooling structures, and the output is set to the state parameters of each target cooling structure in a plurality of target cooling structures. In actual engineering analysis and research, multiple groups of test combinations are often involved. When the three-dimensional finite element model is used for multiple groups of test combinations, there is a problem of slow calculation speed. The main purpose of building a reduced-order model is to solve the problem of slow calculation speed. By building a reduced-order model, the computing power can be improved, thereby more efficiently coping with the computing tasks related to multiple groups of test combinations.

[0081] Regarding step S104, in specific implementation, as an example, the following steps may be included:

[0082] First, based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first validation set, and a first test set. Here, as an example, the first training set ratio is 60%, the first validation set ratio is 20%, and the first test set ratio is 20%.

[0083] Then, standardize the training set, validation set, and test set respectively to obtain a second training set, a second validation set, and a second test set. Here, since each size parameter has differences in nature, dimension, order of magnitude, and availability, if the original values of the size parameters are directly used for analysis, the effect of the size parameters with a higher order of magnitude will be amplified. Therefore, it is necessary to perform data standardization on all parameters of the first training set, the first validation set, and the first test set. Among them, as an example, data standardization is calculated based on the maximum and minimum values corresponding to the size parameters of each specific cooling structure. For the size parameters of one specific cooling structure, the specific calculation formula is: x = (x - x min ) / (x max - x min ), where x min is the minimum value of the size parameter, x max is the maximum value of the size parameter, and x is the size parameter to be standardized.

[0084] Subsequently, based on the second training set, the second validation set, the second test set, and the initial reduced-order model, use the second training set to train the initial reduced-order model, use the second validation set to validate the initial reduced-order model during the training process, and use the second test set to test the initial reduced-order model after training and validation. Here, following the above example, the initial reduced-order model of this application is a BP neural network, and the weights and thresholds of the initial reduced-order model are set. The input parameters of the initial reduced-order model are the size parameters of five specific cooling structures: the depth of the stator oil duct, the width of the stator oil duct, the number of stator oil ducts, the diameter of the winding oil injection port, and the number of winding oil injection ports. The outputs of the initial reduced-order model are the highest temperature of the winding, the average temperature of the winding, the highest temperature of the stator, the average temperature of the stator, and the pressure drop at the inlet and outlet of the winding oil injection port. Before training the initial reduced-order model, first, determine the number of hidden layers and the number of nodes of the initial reduced-order model. Here, selecting multiple hidden layers helps to improve the generalization ability and prediction accuracy of the model. Considering the computational resource limitations of the motor controller, the number of hidden layers is determined to be 1 layer, and the number of nodes in the hidden layer is selected according to the following formula: k < n - 1 and where k is the number of neuron nodes in the hidden layer, n is the number of neuron nodes in the input layer, m is the number of neuron nodes in the output layer, and α is a constant between 1 and 10. In this application, the number of nodes is selected as 4. Then, determine the activation function and the training function. Here, in this application, the Sigmoid function is selected as the activation function of the hidden layer, and the linear function is used for the output layer; in terms of the training function, the momentum backpropagation and the gradient descent training function traingdx with a dynamic adaptive learning rate are selected. During the process of using the second test set to test the initial reduced-order model after training and validation, relative error, average relative error, and root mean square error are introduced to evaluate the model and discriminate the model performance.

[0085] Finally, based on the test results, a reduced-order model for calculating the state parameters of the target cooling structure is constructed. Here, following the above example, if the relative error, the average relative error, and the root mean square error are all within their respective preset error ranges, a reduced-order model for calculating the state parameters of the target cooling structure is constructed, and if at least one of the relative error, the average relative error, and the root mean square error is not within their respective preset error ranges, the weights and thresholds of the initial reduced-order model are adjusted, and the initial reduced-order model is retrained, verified, and tested until the relative error, the average relative error, and the root mean square error are all within their respective preset error ranges, and a reduced-order model for calculating the state parameters of the target cooling structure is constructed.

[0086] Step S105 : determining an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures based on the reduced-order model.

[0087] Here, the value range and sampling interval of the state parameter of each specific cooling structure are set. As an example, the lower limit of the winding oil spraying port diameter is set to 0.5mm, the upper limit of the diameter is set to 3mm, and the sampling interval is set to 0.1mm. Specifically, the state parameter of each specific cooling structure is calculated using the reduced-order model to obtain the experimental value corresponding to the state parameter of each target cooling structure in the multiple target cooling structures.

[0088] Step S106, determining the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusting the corresponding specific motor cooling structure based on the optimal value.

[0089] Regarding step S106, in specific implementation, as an example, the following steps may be included:

[0090] Firstly, based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure.

[0091] Here, the optimization algorithm may include but is not limited to: grid search method, random search method, genetic algorithm, particle swarm optimization algorithm, gradient descent method, Bayesian optimization algorithm, and simulated annealing algorithm. The above optimization algorithms can all be applied to this application, and this application does not limit the optimization algorithm. The preset target optimization function of this application is the optimization target of the preset optimization algorithm. Continuing with the above example, the preset target optimization function includes: the average winding temperature is less than the preset winding temperature average min(T(wdg) Average 、The average stator temperature is less than the preset stator temperature average min(T(stator) Average, the inlet and outlet pressure drop of the winding oil spray port is less than the preset inlet and outlet pressure drop of the winding oil spray port min(p), the maximum temperature of the winding is less than the preset maximum temperature of the winding max(T(wdg) and the maximum temperature of the stator is less than the preset maximum temperature of the stator max(T(stator). Here, the average winding temperature and the average stator temperature are set as optimization targets, aiming to make the cooling scheme achieve as uniform heat dissipation as possible; the inlet and outlet pressure drop of the winding oil spray port is taken as the optimization target, aiming to reduce the flow resistance and thus reduce the power consumption of the oil pump. In this application, the maximum winding temperature and the maximum stator temperature must be less than 150°C.

[0092] Specifically, the number of sample points for optimization is set to be no less than 4,000, and the experimental values ​​corresponding to the state parameters of each target cooling structure are optimized with the preset target optimization function as the target, and the sample points whose outputs meet the conditions of the preset target optimization function are confirmed as the Pareto frontier. Based on the cooling scheme of the Pareto frontier, the five dimensions of the maximum temperature of the winding, the average temperature of the winding, the maximum temperature of the stator, the average temperature of the stator, and the inlet and outlet pressure drop of the winding oil spray port are comprehensively considered. By comparing the performance of each scheme in the Pareto frontier in the five dimensions, the scheme with the best comprehensive performance is selected.

[0093] Then, according to the optimal value corresponding to the state parameter of each target cooling structure, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value corresponding to the size parameter of each specific cooling structure.

[0094] As an example, suppose there is a solution on the Pareto frontier, with an average winding temperature of 90°C, a maximum winding temperature of 110°C, an average stator temperature of 85°C, a maximum stator temperature of 105°C, and an inlet and outlet pressure drop of 0.3MPa at the winding oil spraying port. This solution performs well in five dimensions. The stator oil channel depth h = 3mm, stator oil channel width d1 = 1.25mm, number of stator oil channels n = 4, winding oil spraying port diameter d2 = 1.75mm, and number of winding oil spraying ports m = 3 corresponding to this solution are determined as the final cooling solution.

[0095] An embodiment of the present application provides an optimization method for a motor cooling structure. Through the method, not only the solution optimization cycle is significantly shortened and the development efficiency is improved, but also a large-scale refined design of the cooling structure is achieved, ensuring the reliability and efficiency of the cooling solution.

[0096] Based on the same application concept, the embodiment of the present application also provides an optimization device for the motor cooling structure corresponding to the optimization method for the motor cooling structure provided in the above embodiment. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the optimization method for the motor cooling structure in the above embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0097] See also Figure 2 , Figure 2 A schematic diagram of the structure of an optimization device for a motor cooling structure provided in an embodiment of the present application.

[0098] like Figure 2 As shown in , the optimization device 210 includes:

[0099] The test combination determination module 211 performs an orthogonal test based on the size parameter of each specific cooling structure in the multiple specific cooling structures of the motor, the value range of each size parameter and the number of values ​​of the size parameter to obtain multiple test combinations of the size parameters of each specific cooling structure;

[0100] A three-dimensional finite element model building module 212 is configured to build a plurality of three-dimensional finite element models for a specific cooling structure of the motor based on the plurality of test combinations;

[0101] A simulation result determination module 213, for multiple target cooling structures in the motor, uses each of the multiple three-dimensional finite element models to perform simulation, and obtains simulation results corresponding to the state parameters of each of the multiple target cooling structures in the motor;

[0102] A reduced-order model building module 214 builds a reduced-order model for calculating state parameters of a target cooling structure based on the simulation results;

[0103] An experimental value determination module 215 determines, based on the reduced-order model, an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures;

[0104] The adjustment module 216 determines the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusts the corresponding specific motor cooling structure based on the optimal value.

[0105] Preferably, the three-dimensional finite element model building module 212 is specifically used for:

[0106] Based on the multiple test combinations, multiple motor models are constructed; the fluid domain of the motor cooling structure of each motor model in the multiple motor models is extracted; the fluid domain is meshed, and the coolant parameters flowing through the fluid domain are set for the meshed fluid domain; the motor solid components in the motor model after the fluid domain is extracted and the coolant parameters are set, and the parameters corresponding to the motor solid components are set for the meshed motor solid components; the motor model after the parameters corresponding to the motor solid components are set is determined as a three-dimensional finite element model of a specific cooling structure for the motor, and multiple three-dimensional finite element models of the specific cooling structure for the motor are constructed.

[0107] Preferably, the reduced-order model building module 214 is specifically used for:

[0108] Based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first verification set and a first test set; the training set, the verification set and the test set are standardized to obtain a second training set, a second verification set and a second test set; based on the second training set, the second verification set, the second test set and the initial reduced-order model, the initial reduced-order model is trained using the second training set, the initial reduced-order model during the training process is verified using the second verification set, and the initial reduced-order model after training and verification is tested using the second test set; based on the test results, a reduced-order model for calculating the state parameters of the target cooling structure is constructed.

[0109] Preferably, the adjustment module 216 is specifically used for:

[0110] Based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure; according to the optimal values ​​corresponding to the state parameters of each target cooling structure, the optimal values ​​corresponding to the size parameters of each specific cooling structure are determined, and the corresponding specific motor cooling structure is adjusted based on the optimal values ​​corresponding to the size parameters of each specific cooling structure.

[0111] An embodiment of the present application provides an optimization device for a motor cooling structure. Through the device, not only the solution optimization cycle is significantly shortened and the development efficiency is improved, but also a large-scale refined design of the cooling structure is achieved, ensuring the reliability and efficiency of the cooling solution.

[0112] See also Figure 3 , Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0113] like Figure 3As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0114] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 The steps of the method for optimizing the motor cooling structure in the method embodiment shown, and the specific implementation methods can be found in the method embodiment, which will not be repeated here.

[0115] The present application also provides a computer-readable storage medium on which a computer program is stored. The computer program can be executed as described above when the processor runs it. Figure 1 The steps of the motor bearing fault detection method in the method embodiment shown and the specific implementation method thereof can be referred to the method embodiment, which will not be described in detail here.

[0116] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] 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.

[0118] In addition, each functional unit in each embodiment of the present application 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.

[0119] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0120] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for optimizing a motor cooling structure, characterized in that: The optimization method comprises: Based on the size parameter of each specific cooling structure in the multiple specific cooling structures of the motor, the value range of each size parameter and the number of values ​​of the size parameter, an orthogonal test is performed to obtain multiple test combinations of the size parameters of each specific cooling structure; Based on the multiple test combinations, construct multiple three-dimensional finite element models of specific cooling structures for the motor; For multiple target cooling structures in the motor, use each of the multiple three-dimensional finite element models to perform simulation to obtain simulation results corresponding to the state parameters of each of the multiple target cooling structures of the motor; Based on the simulation results, a reduced-order model for calculating state parameters of a target cooling structure is constructed; Determining, based on the reduced-order model, an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures; Based on the experimental values ​​and a preset optimization algorithm, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value.

2. The method for optimizing the motor cooling structure according to claim 1, characterized in that: The method of constructing multiple three-dimensional finite element models of a specific cooling structure for the motor based on the multiple test combinations includes: Based on the multiple test combinations, construct multiple motor models; extracting a fluid domain of a motor cooling structure of each motor model in a plurality of motor models; Meshing the fluid domain, and setting parameters of a coolant flowing through the fluid domain for the meshed fluid domain; Meshing the motor solid components in the motor model after extracting the fluid domain and setting the coolant parameters, and setting parameters corresponding to the motor solid components for the meshed motor solid components; The motor model after setting the parameters corresponding to the motor solid components is determined as a three-dimensional finite element model for the specific cooling structure of the motor, and multiple three-dimensional finite element models for the specific cooling structure of the motor are constructed.

3. The method for optimizing the motor cooling structure according to claim 1, characterized in that: The step of constructing a reduced-order model for calculating state parameters of a target cooling structure based on the simulation results comprises: Based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first validation set, and a first test set; Standardizing the training set, validation set, and test set to obtain a second training set, a second validation set, and a second test set; Based on the second training set, the second validation set, the second test set and the initial reduced order model, respectively, using the second training set to train the initial reduced order model, using the second validation set to validate the initial reduced order model during the training process, and using the second test set to test the trained and validated initial reduced order model; Based on the results of the tests, a reduced-order model for calculating state parameters of the target cooling structure is constructed.

4. The method for optimizing the motor cooling structure according to claim 1, characterized in that: The step of determining the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusting the corresponding specific motor cooling structure based on the optimal value, includes: Based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure; According to the optimal value corresponding to the state parameter of each target cooling structure, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value corresponding to the size parameter of each specific cooling structure.

5. An optimization device for a motor cooling structure, characterized in that: The optimization device comprises: A test combination determination module performs an orthogonal test based on a size parameter of each specific cooling structure in a plurality of specific cooling structures of the motor, a value range of each size parameter, and the number of values ​​of the size parameter, to obtain a plurality of test combinations of the size parameters of each specific cooling structure; A three-dimensional finite element model building module is used to build multiple three-dimensional finite element models of a specific cooling structure for the motor based on the multiple test combinations; A simulation result determination module, for multiple target cooling structures in the motor, using each of the multiple three-dimensional finite element models to perform simulation, and obtain a simulation result corresponding to a state parameter of each of the multiple target cooling structures of the motor; A reduced-order model building module, based on the simulation results, builds a reduced-order model for calculating state parameters of a target cooling structure; an experimental value determination module, which determines, based on the reduced-order model, an experimental value corresponding to a state parameter of each target cooling structure in the plurality of target cooling structures; The adjustment module determines the optimal value corresponding to the size parameter of each specific cooling structure based on the experimental value and a preset optimization algorithm, and adjusts the corresponding specific motor cooling structure based on the optimal value.

6. The device for optimizing the cooling structure of a motor according to claim 5, characterized in that: The three-dimensional finite element model building module is specifically used for: Based on the multiple test combinations, construct multiple motor models; extracting a fluid domain of a motor cooling structure of each motor model in a plurality of motor models; Meshing the fluid domain, and setting parameters of a coolant flowing through the fluid domain for the meshed fluid domain; Meshing the motor solid components in the motor model after extracting the fluid domain and setting the coolant parameters, and setting parameters corresponding to the motor solid components for the meshed motor solid components; The motor model after setting the parameters corresponding to the motor solid components is determined as a three-dimensional finite element model for the specific cooling structure of the motor, and multiple three-dimensional finite element models for the specific cooling structure of the motor are constructed.

7. The device for optimizing the cooling structure of a motor according to claim 5, characterized in that: The reduced-order model building module is specifically used for: Based on the simulation results, a data set is generated, and the data set is divided according to a preset ratio to obtain a first training set, a first validation set, and a first test set; Standardizing the training set, validation set, and test set to obtain a second training set, a second validation set, and a second test set; Based on the second training set, the second validation set, the second test set and the initial reduced order model, respectively, using the second training set to train the initial reduced order model, using the second validation set to validate the initial reduced order model during the training process, and using the second test set to test the trained and validated initial reduced order model; Based on the results of the tests, a reduced-order model for calculating state parameters of the target cooling structure is constructed.

8. The device for optimizing the cooling structure of a motor according to claim 5, characterized in that: The adjustment module is specifically used for: Based on a preset optimization algorithm and a preset target optimization function, the experimental values ​​are optimized, and the optimized experimental values ​​are screened to obtain the optimal values ​​corresponding to the state parameters of each target cooling structure; According to the optimal value corresponding to the state parameter of each target cooling structure, the optimal value corresponding to the size parameter of each specific cooling structure is determined, and the corresponding specific motor cooling structure is adjusted based on the optimal value corresponding to the size parameter of each specific cooling structure.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the method for optimizing the motor cooling structure as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for optimizing the cooling structure of a motor according to any one of claims 1 to 4 are executed.

Images