Vehicle electric drive assembly heat dissipation method, system, electronic device and storage medium

Abstract

The application discloses a heat dissipation method, system, electronic equipment and storage medium of a vehicle electric drive assembly. The heat dissipation method of the vehicle electric drive assembly comprises the following steps: obtaining a sample space with reasonable sample point distribution; selecting the highest temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure as research targets according to the sample space with reasonable sample point distribution, and constructing an electric drive assembly proxy model; optimizing the electric drive assembly proxy model through an incremental learning strategy to obtain a high-precision proxy model; taking the oil path structure of the motor as a design variable, taking the highest temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, and solving the high-precision proxy model by using a multi-objective optimization algorithm to obtain optimal solutions of different optimization algorithms. The application has high reliability, can significantly improve the heat dissipation effect of the electric drive assembly, provides theoretical support for the production and processing of an actual electric drive assembly heat dissipation system, and can also improve the internal heat dissipation of the motor and prolong the service life of the motor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, and more particularly to a heat dissipation method, system, electronic device and storage medium for a vehicle electric drive assembly. BACKGROUND

[0002] As a secondary energy source friendly to the environment, electric energy can replace traditional internal combustion engine fossil fuels, drive electric motors to output mechanical energy, and vigorously develop new energy vehicles, which is an important way to solve energy and environmental problems and is a key issue in national development planning.

[0003] The power system driving electric drive assembly has the characteristics of high power density, high efficiency, fast response speed and wide speed regulation range, and gradually becomes the core of the new energy vehicle driving electric drive assembly. It is one of the biggest difficulties in the development process to optimize the design of the heat dissipation system of the developed high-power electric drive assembly product, find the optimal electric drive assembly heat dissipation parameters, and obtain the best heat dissipation effect. The existing design technology often uses mature products on the market or a large number of performance development test data to optimize the structure, and less uses big data multi-objective optimization to establish a development model, so it is a technical problem that needs to be solved in the field. SUMMARY

[0004] Therefore, the present application provides a heat dissipation method for a vehicle electric drive assembly to solve the problem that the prior art less uses big data multi-objective optimization to establish a development model.

[0005] In a first aspect, the present application provides a heat dissipation method for a vehicle electric drive assembly, comprising:

[0006] obtaining a sample space with reasonable sample point distribution;

[0007] According to the sample space with reasonable sample point distribution, selecting the highest temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure as the research target, and constructing an electric drive assembly proxy model;

[0008] Optimizing the electric drive assembly proxy model through an incremental learning strategy to obtain a high-precision proxy model;

[0009] Taking the oil path structure of the electric motor as a design variable, and taking the highest temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, a multi-objective optimization algorithm is used to solve the high-precision proxy model to obtain the optimal solution of different optimization algorithms.

[0010] In a second aspect, the present application provides a heat dissipation system for a vehicle electric drive assembly, applied to the heat dissipation method for the vehicle electric drive assembly, comprising:

[0011] The acquisition module is configured to obtain a sample space with reasonable sample point distribution;

[0012] The construction module is configured to select the highest temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure as the research targets according to the sample point distribution reasonable sample space, and construct the electric drive assembly agent model;

[0013] The optimization module is configured to optimize the electric drive assembly agent model through an incremental learning strategy to obtain a high-precision agent model.

[0014] The calculation module is configured to take the oil circuit structure of the motor as a design variable, take the highest temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, utilize a multi-objective optimization algorithm to solve the high-precision agent model, and obtain optimal solutions of different optimization algorithms.

[0015] In a third aspect, the present application provides an electronic device, which comprises:

[0016] a memory configured to store a program; and

[0017] a processor configured to execute the heat dissipation method of the vehicle electric drive assembly by calling the program stored in the memory.

[0018] In a fourth aspect, the present application provides a computer readable storage medium, which is characterized by storing computer instructions, and the computer instructions are configured to make the computer execute the heat dissipation method of the vehicle electric drive assembly.

[0019] Compared with the prior art, the heat dissipation method, system, electronic device and storage medium of the vehicle electric drive assembly provided by the present application at least achieve the following beneficial effects:

[0020] The application provides a vehicle electric drive assembly heat dissipation method, system, electronic equipment and storage medium, the vehicle electric drive assembly heat dissipation method comprises the following steps: obtaining a sample space with reasonable sample point distribution; selecting the highest temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure as research targets according to the sample space with reasonable sample point distribution, and constructing an electric drive assembly proxy model; the electric drive assembly proxy model is optimized through an incremental learning strategy to obtain a high-precision proxy model; the oil circuit structure of the motor is taken as a design variable, the highest temperature of the electric drive assembly and the cooling liquid pressure are taken as optimization targets, a multi-objective optimization algorithm is used to solve the high-precision proxy model, and the optimal solution of different optimization algorithms is obtained, through the above scheme, the high-precision proxy model is optimized through the incremental learning strategy, so that the precision of the high-precision proxy model is obviously improved, and the R-square value in the final evaluation index can reach 0.983, which can truly reflect the actual physical condition; then, the high-precision proxy model is solved by using different multi-objective optimization algorithms, and the Pareto optimal solution of different multi-objective optimization algorithms is obtained, the optimal solution of different multi-objective optimization algorithms is obtained through the utopia point method, and it is verified that the optimal solution has high reliability and can significantly improve the heat dissipation effect of the electric drive assembly, thereby providing theoretical support for the production and processing of the actual electric drive assembly heat dissipation system; in addition, since the service life of the induction motor is greatly affected by the highest working temperature of the electric drive assembly, improving the internal heat dissipation of the motor can improve the service life of the motor.

[0021] Of course, it is not necessary for any product implementing the present application to achieve all the above technical effects simultaneously.

[0022] Other features of the present application, and their advantages, will become apparent in the non-limiting detailed description of exemplary embodiments of the present application, taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0024] Figure 1 is a flowchart of a vehicle electric drive assembly heat dissipation method provided by the application;

[0025] Figure 2 is a structural schematic diagram of a vehicle electric drive assembly heat dissipation device provided by the application;

[0026] Figure 3 is a sectional schematic diagram of a vehicle electric drive assembly heat dissipation device provided by the application;

[0027] Figure 4 is a sample point distribution diagram of a BBD provided by the application;

[0028] Figure 5A sample point distribution graph of a CCD is provided in the present application;

[0029] Figure 6 A sample point distribution graph of a LHS is provided in the present application;

[0030] Figure 7 A sample point distribution graph of an OFS is provided in the present application;

[0031] Figure 8 A real sampling sample point distribution graph is provided in the present application;

[0032] Figure 9 A precision bar graph of an electric drive assembly heat dissipation parameter (cooling oil pressure) under different agent models is provided in the present application;

[0033] Figure 10 A precision bar graph of an electric drive assembly heat dissipation parameter (cooling water pressure) under different agent models is provided in the present application;

[0034] Figure 11 A precision bar graph of an electric drive assembly heat dissipation parameter (maximum temperature of the electric drive assembly) under different agent models is provided in the present application;

[0035] Figure 12 A flow chart of a high-precision agent model is provided in the present application;

[0036] Figure 13 A high-precision agent model precision improvement graph is provided in the present application;

[0037] Figure 14 A different multi-objective algorithm optimal solution set is provided in the present application;

[0038] Figure 15 An electric drive assembly temperature isotherm curve cloud chart (side view of an initial scheme) is provided in the present application;

[0039] Figure 16 An electric drive assembly temperature isotherm curve cloud chart (front view of an initial scheme) is provided in the present application;

[0040] Figure 17 An electric drive assembly temperature isotherm curve cloud chart (side view of an optimal scheme) is provided in the present application;

[0041] Figure 18 An electric drive assembly temperature isotherm curve cloud chart (side view of an optimal scheme) is provided in the present application;

[0042] Figure 19 An electric drive assembly temperature isotherm curve cloud chart (temperature label) is provided in the present application;

[0043] Figure 20These are photos of the experimental process provided in the experimental verification of this invention;

[0044] Figure 21 This is the experimental result curve provided by the present invention in the experimental verification;

[0045] Figure 22 This is a schematic diagram of the structure of a heat dissipation optimization frame for an electric drive assembly provided by the present invention;

[0046] Figure 23 This is a schematic diagram of the cooling system of a vehicle electric drive assembly provided by the present invention. Detailed Implementation

[0047] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0048] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0049] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0050] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0051] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0052] Example 1

[0053] Reference Figures 1-21 As shown, Figure 1 This is a schematic flowchart of a heat dissipation method for a vehicle electric drive assembly provided by the present invention; Figure 2 This is a schematic diagram of the structure of a vehicle electric drive assembly cooling device provided by the present invention; Figure 3 This is a cross-sectional schematic diagram of a vehicle electric drive assembly cooling device provided by the present invention; Figure 4 This invention provides a sample point distribution map of BBD. Figure 5 This invention provides a sample point distribution map of a CCD. Figure 6 This invention provides a sample point distribution map of an LHS (Local Hash Table). Figure 7 This is a sample point distribution map of OFS provided by the present invention;Figure 8 is a real sampling sample point distribution diagram provided by the present application; Figure 9 is a precision bar chart of the electric drive assembly heat dissipation parameter (cooling oil pressure) under different agent models provided by the present application; Figure 10 is a precision bar chart of the electric drive assembly heat dissipation parameter (cooling water pressure) under different agent models provided by the present application; Figure 11 is a precision bar chart of the electric drive assembly heat dissipation parameter (maximum temperature of the electric drive assembly) under different agent models provided by the present application; Figure 12 is a flow chart of a high-precision agent model provided by the present application; Figure 13 is a precision improvement diagram of a high-precision agent model provided by the present application; Figure 14 is an optimal solution set of different multi-objective algorithms provided by the present application; Figure 15 is an electric drive assembly temperature isotherm cloud chart (side view of the initial scheme) provided by the present application; Figure 16 is an electric drive assembly temperature isotherm cloud chart (front view of the initial scheme) provided by the present application; Figure 17 is an electric drive assembly temperature isotherm cloud chart (side view of the optimal scheme) provided by the present application; Figure 18 is an electric drive assembly temperature isotherm cloud chart (side view of the optimal scheme) provided by the present application; Figure 19 is an electric drive assembly temperature isotherm cloud chart (temperature label) provided by the present application; Figure 20 is an experimental process photo in experimental verification provided by the present application; Figure 21 is an experimental result curve in experimental verification provided by the present application; the embodiment provides a heat dissipation method of a vehicle electric drive assembly, comprising:

[0054] S1, a sample point distribution reasonable sample space is obtained;

[0055] First, the corresponding heat dissipation design variables of the electric drive assembly are obtained, and the heat dissipation design variables include the oil inner diameter, the nozzle size, the water channel connection width, the oil inlet diameter, the oil inlet depth, the cooling oil flow rate and the cooling water flow rate; second, the heat dissipation design variables are sampled by using an experimental design method, and a sample point distribution reasonable sample space is selected, and optionally, the sample point distribution reasonable sample space can be a sample point distribution optimal sample space;

[0056] Specifically, in combination with Figure 2 and Figure 3As shown, when building the electric drive assembly agent model, first, the key parameters affecting the heat dissipation study need to be determined. Through the study of electric drive assembly parameters and heat dissipation system, it can be found that liquid flow, water jacket structure and oil path structure have great influence on electric drive assembly heat dissipation system. Considering the actual heat dissipation research value and product processing capacity, the oil inner diameter r, nozzle size c, waterway connection width b, oil inlet diameter R, oil inlet depth L, cooling oil flow rate and cooling water flow rate are selected as design variables, and the upper and lower limits of the design variables [L, R, r, b, h, , ] are designed as [18, 6, 15, 24, 10, 0.5, 0.2] and [22, 9, 25, 28, 20, 1.5, 0.8] respectively, which are obtained according to the influence factor analysis and the corresponding actual product processing capacity. In order to clearly express the influence of design variables on electric drive assembly heat dissipation, the highest temperature of electric drive assembly, cooling water pressure and cooling oil pressure are selected as the research objectives of electric drive assembly heat dissipation, which are directly related to heat dissipation capacity and cost.

[0057] After determining the corresponding heat dissipation design variables, experimental design is needed to sample the design variables. The commonly used experimental design methods include response surface experimental design (Box-Behnken Design Sampling, BBD), central combination experimental design sampling (Central Combination Design Sampling, CCD), Latin hypercube experimental design sampling (Latin Hypercube Design Sampling, LHS) and optimal space-filling experimental design (Optimal Space-Filling Design Sampling, OSF) design, etc. The introduction and characteristics of the corresponding methods are shown in Table 1.

[0058] Table 1 Experimental design method

[0059]

[0060] The samples of the above four sampling methods are as follows Figures 4-7The analysis shows that the distribution of BBD and CCD is not as good as LHS and OSF, that is, the sampling points of BBD and CCD cannot effectively fill the sample space. At the same time, the sampling points of LHS and OSF can effectively fill the sample space. In order to evaluate the adaptability of these two sampling methods to this problem, the coordinates exchange algorithm is introduced. First, assume that the sampling result is:

[0061]

[0062] The definition of evaluation index G is shown in the formula, and the smaller the G value, the better the uniformity and spatial distribution of the sampling result.

[0063]

[0064] Through calculation, G(LHS) = 1542.64, G(OSF) =1673.18. Therefore, it can be found that LHS is more adaptable to this problem, and the sample points are more uniformly and fully distributed in the sample space.

[0065] The specific sampling process of sample point collection is shown below, and the final samples are shown in Table 2 and Figure 8 .

[0066] Step 1: Determine the required sample number N = 100, sample size D = 7;

[0067] Step 2: Divide the [0, 1] interval into 100 segments, and randomly select a value in any segment of each dimension;

[0068] Step 3: Combine the 7-dimensional values into a vector, and map them to standard sample values through the inverse function of the standard normal distribution;

[0069] Step 4: Repeat steps 2-3, and in the repeating process, for a single dimension, the segment of the sampled value will not be sampled again. Sample all segments of all dimensions. At this time, the sampling is completed, and 100 sampling points are obtained.

[0070] Table 2 Partial sample point data and target value

[0071]

[0072] It should be noted that in the above Table 2, r is the oil inside diameter; c is the nozzle size; b is the waterway connection width; R is the oil inlet hole diameter; L is the oil inlet depth; is the cooling oil flow rate; is the cooling water flow rate; is the maximum temperature of the electric drive assembly; Cooling water pressure; Cooling oil pressure.

[0073] S2 According to the sample point distribution reasonable sample space, select the highest temperature of electric drive assembly, cooling water pressure and cooling oil pressure as the research object, build electric drive assembly proxy model;

[0074] Specifically, for the complex engineering problems such as heat dissipation, it is often difficult to directly obtain the function expression between input and output. In order to overcome this difficulty, data driven proxy model method has been widely used in many fields. On the basis of experimental design, the sample points obtained from experimental design are used to establish proxy model and fit the relationship between input and output. Common proxy model methods include response surface analysis RSM, radial basis function algorithm RBF, support vector regression algorithm SVR and Kriging interpolation.

[0075] RSM is a simple and effective proxy model, which fits the relationship between input and output through polynomial. The most suitable precision of the model can be adjusted according to the order of polynomial. The basic expression is as follows:

[0076] ,

[0077] Among them, represents the design variables involved in fitting; , , indicates the coefficient of regression equation; , , and correspond to the design variable response value of first order, second order, third order and fourth order response surface method.

[0078] RBF is a single layer neural network, which has strong generalization ability and superior convergence speed. Its basic function expression is as follows:

[0079] ,

[0080] Among them, is the model adaptability weight coefficient, is a nonlinear basis function, which represents the Euclidean distance between two sample points, and y is the output value.

[0081] SVR realizes data regression prediction through hyperplane and support vector. Its core is to transform the problem into quadratic programming problem, and its equation is as follows:

[0082] ,

[0083] Among them, is the Lagrange multiplier, is a nonlinear transformation function that can map the training samples to a high-dimensional space.

[0084] S3 optimizes the electric drive assembly proxy model through an incremental learning strategy to obtain a high-precision proxy model.

[0085] Incremental learning, also known as continuous learning or lifelong learning, is a machine learning method that allows models to continuously learn from new data rather than retraining the entire model from scratch. This approach allows models to continuously learn new knowledge and adapt to changing environments.

[0086] First, the accuracy of the electric drive assembly proxy model is evaluated using evaluation indicators. Second, the incremental Kriging method is used to optimize the design variables in the evaluated electric drive assembly proxy model with insufficient precision. Through continuous optimization and updating of the initial training set using the expected improvement method, a high-precision proxy model is obtained.

[0087] Specifically, to verify the accuracy of the proxy model, evaluation indicators are introduced. Median absolute deviation (MAD), maximum absolute error (MAE), root mean square error (RMSE), and R2 are four typical evaluation indicators that can fully reflect the accuracy of the electric drive assembly proxy model fitting. Among them, the closer R-square is to 1, or the closer MAD, MAE, and RMSE are to 0, the higher the prediction accuracy of the electric drive assembly proxy model.

[0088] ,

[0089] ,

[0090] ,

[0091] ,

[0092] wherein, is the predicted value, is the true value, indicates the median, is the number of test set samples, and mean refers to the average value.

[0093] The first 80 samples are used as the training set, and the last 20 samples are used as the test set. The prediction accuracy of different modeling methods is shown in Table 1. Figures 9-11

[0094] ​From the comparison results among RSM, RBF, SVR and Kriging, it can be found that Kriging model has the highest accuracy for the three parameters (the maximum temperature of the electric drive assembly, the cooling oil pressure and the cooling water pressure). Although Kriging model has the best modeling accuracy among the existing methods, its accuracy is still low for the research target of the cooling water pressure. Therefore, a corresponding method is needed to improve the accuracy of the corresponding Kriging model.

[0095] In the high-dimensional data fitting problem, the traditional surrogate model method often cannot find the optimal fitting space due to the limitation of the initial experimental design, which leads to low accuracy of the surrogate model. In order to improve this phenomenon, a method called adaptive sequential sampling has been widely used, which is a kind of incremental learning strategy. By continuously optimizing and updating the initial training set, the purpose of improving the model accuracy is achieved. In order to better improve the modeling accuracy of the research target of the cooling water pressure, a Kriging surrogate model method based on sequential sampling is used here, also known as the incremental Kriging method (IK). The core of this method is to continuously update the corresponding process variables during the modeling process.

[0096] Assuming that the number of new sample points added is s, the incremental Kriging expression is as follows:

[0097] ,

[0098] Among them, the relevant update process variables are as follows:

[0099] ,

[0100] ,

[0101] In the formula, is the matrix composed of the values of the original sample points and the incremental sample points, which is used for the solution of the incremental Kriging method above; is the original sample point matrix, is n+1 to n+s, representing the newly added s sample points.

[0102] ,

[0103] ,

[0104] In the formula, is the matrix composed of the input covariance, which is used for the solution of the Kriging method, and R is the covariance between the input design variables.

[0105] The expected improvement method is used to increase the number of sample points in the incremental Kriging method. It is assumed that for any design variable x, the response value y is a random variable following a normal distribution with a mean of [value missing]. Its probability density function is:

[0106] ,

[0107] Assume the optimal response value for the current sample is Then the expected value of the objective function at this design point is:

[0108] ,

[0109] The desired improved function is as follows:

[0110] ,

[0111] in, It is the cumulative distribution function of the standard normal distribution; Standard deviation, For design variables The response value.

[0112] By analyzing and deriving the expected improvement function, it can be found that the expected improvement function is about... A monotonically decreasing function, that is, when When the value decreases, The value of will increase accordingly, therefore it is recommended to perform additional sampling in the region of minimum response value. At the same time, the expected improvement function is also... A monotonically increasing function, when When increasing, This will have a larger expected value, meaning that sample points are relatively scarce in larger regions, resulting in less sample information and model uncertainty. Additional sampling is needed here to improve the model.

[0113] In summary, referring to Figure 12 As shown, the basic process of the IK model includes: first, determining the design variables and design objectives. The design variables include the oil inner diameter r, nozzle size c, water channel connection width b, oil inlet diameter R, oil inlet depth L, and cooling oil flow rate. and cooling water flow rate Design objectives include the highest temperature (Tmax) of the electric drive assembly and the cooling water pressure. and cooling oil pressure ;

[0114] Then, based on the experimental design method, the design variables are sampled. In this embodiment, the LHS experimental design sampling method is more adaptable and the sample distribution is more uniform, so the sampling results of this method are applicable.

[0115] Secondly, a series of sample point data are obtained after sampling, and a surrogate model method is used to fit the relationship between the sample point input design variables and the output design targets. In this embodiment, an initial Kriging model can be used as a surrogate model;

[0116] The median absolute deviation (MAD), maximum absolute error (MAE), root mean square error (RMSE) and R2 are selected as evaluation indexes to reflect the accuracy of the model fitting. For the Kriging model with insufficient accuracy (this embodiment takes water pressure as an example), the IK method (incremental Kriging method) is used for improvement modeling, and the EI method (expected improvement method) is used to add new training samples. The JK model precision finally trained is as shown in Figure 13 It can be found that with the increase of sample points, the accuracy of the Kriging model is obviously improved, and the final R-square value can reach 0.983, which can truly reflect the actual physical situation.

[0117] It should be noted that the R-square value in the evaluation index will vary depending on the project, which is not limited in this embodiment.

[0118] (1) Drive electric drive assembly heat dissipation optimization model

[0119] ① Design variables

[0120] The design variables mainly include the structure parameters of the heat dissipation system and the cooling medium parameters. The structure parameters mainly include five types of parameters: oil inlet depth L, oil inlet diameter R, oil inlet inner diameter r, nozzle size c, and water channel connection width b. The cooling medium parameters include cooling water flow rate and cooling oil flow rate These are related variable parameters designed based on the comparison of heat dissipation schemes.

[0121] ② Research objectives

[0122] Because the purpose of this study is to achieve efficient heat dissipation of the electric drive assembly, the maximum temperature of the electric drive assembly , cooling water pressure and cooling oil pressure are selected as the corresponding research objectives. The research objective of the maximum temperature of the electric drive assembly directly reflects the heat dissipation effect of the electric drive assembly. The research objectives of cooling water pressure and cooling oil pressure are associated with the corresponding heat dissipation cost, and can comprehensively reflect the optimal heat dissipation of the electric drive assembly.

[0123] ③ Electric drive assembly surrogate model

[0124] After analyzing the corresponding design variables and research objectives, the electric drive assembly proxy model is shown as follows:

[0125] .

[0126] S4 takes the oil circuit structure of the motor as the design variable, takes the maximum temperature of the electric drive assembly and the cooling liquid pressure as the optimization target, and solves the high-precision proxy model by using a multi-objective optimization algorithm to obtain the optimal solution of different optimization algorithms.

[0127] In order to ensure the reliability of the optimization results, the multi-objective optimization algorithm is used to optimize the electric drive assembly proxy model. The multi-objective optimization algorithm includes multi-objective genetic algorithm NSGA-II, sparse large-scale multi-objective evolutionary algorithm SparseEA, TOP (used to solve complex problems and optimization algorithm), and multi-objective particle swarm optimization algorithm MOPSO. NSGA-II is a classic multi-objective genetic algorithm that quickly and accurately finds the optimal region through non-dominated sorting and elite strategy. SparseEA is an evolutionary algorithm for sparse data, which has been widely used in large-scale sparse matrix optimization. TOP is a two-stage optimization method that converts multi-objective problems into single-objective problems. MOPSO is a particle swarm optimization algorithm in the multi-objective field, which achieves optimization effect by marking and updating particles.

[0128] The optimization results of the above four multi-objective optimization algorithms are shown in Figure 14 The results show that the solution set of MOPSO is too dense to well display the optimal space. Except for the MOPSO method, the other three methods can obtain good Pareto solutions.

[0129] Since there is a Pareto relationship between the three research objectives (the maximum temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure ), it is impossible to obtain three optimal solutions at the same time. Since the Pareto solution set generated by the multi-objective genetic algorithm has a non-dominated relationship, it is impossible to compare the advantages and disadvantages between different solutions, therefore, the utopia point method is introduced to obtain the actual scheme required by the electric drive assembly.

[0130] After taking the oil circuit structure of the motor as the design variable, taking the maximum temperature of the electric drive assembly and the cooling liquid pressure as the optimization target, and solving the high-precision proxy model by using a multi-objective optimization algorithm to obtain the optimal solution of different optimization algorithms, the following includes:

[0131] Firstly, the utopia point method is used to compare the advantages and disadvantages of different solutions (Pareto solutions obtained by different multi-objective optimization algorithms) to obtain the optimal solution; then, the design variables corresponding to the optimal solution are introduced into the thermal simulation analysis model to obtain the maximum temperature of the electric drive assembly, the cooling water pressure and cooling oil pressure ; according to the deviation between the optimized value and the simulation value of the maximum temperature of the electric drive assembly , cooling water pressure and cooling oil pressure , the minimum deviation between the optimized value and the simulation value of the maximum temperature of the electric drive assembly , cooling water pressure and cooling oil pressure is selected, and the final optimization scheme is obtained.

[0132] Referring to Table 3, the optimal solutions of the three multi-objective optimization algorithms (NSGA-II, TOP and SparseEA) are calculated by the utopia point method. In order to verify the feasibility of the optimization results, the design variables (such as the oil inner diameter r, the nozzle size c, the water channel connection width b, the oil inlet diameter R, the oil inlet depth L, the cooling oil flow rate and the cooling water flow rate ) corresponding to the optimal solutions are substituted into the electric drive assembly thermal simulation analysis model to obtain the simulation electric drive assembly maximum temperature , cooling water pressure and cooling oil pressure and other research targets, the deviation between the optimized value and the simulation value of the maximum temperature of the electric drive assembly , cooling water pressure and cooling oil pressure is calculated, and the NSGA-II optimization scheme with the minimum deviation is selected as the final optimization scheme, as shown in Table 4 and Figures 15-19 .

[0133] Table 3 Optimal solution set of different optimization algorithms

[0134]

[0135] Table 4 Comparison of schemes before and after optimization

[0136]

[0137] Referring to Table 4 and Figures 15-19 , it can be found that by changing the electric drive assembly structure parameters and the cooling process variables, the maximum temperature can be reduced by about 5K, and the temperature of the winding and stator region is obviously improved. Although the optimized scheme sacrifices a certain coolant pressure, it is within the allowable range of design. The final result shows that the optimization design of the electric drive assembly heat dissipation combined with the electric drive assembly proxy model can significantly improve the heat dissipation effect of the electric drive assembly, and provide theoretical support for the production and processing of the actual electric drive assembly heat dissipation system. In addition, since the service life of the induction motor is greatly affected by the maximum working temperature, improving the internal heat dissipation of the motor can improve the service life of the motor.

[0138] ③ Experimental verification of the optimized scheme

[0139] Finally, based on the modeling and optimization results, experimental verification was conducted. Considering the manufacturing conditions, some parameters were regularized. Furthermore, since the winding temperature is generally the highest temperature of the electric drive assembly, this temperature was used as the verification object. The experimental procedure is as follows, and the final verification results are as follows. Figure 20 As shown.

[0140] a) Before the experiment, the temperature of the electric drive assembly windings was recorded by the host computer;

[0141] b) During the experiment, the electric drive assembly was operated under rated conditions of 400V, 6500rpm, 125N·m, and 25℃ coolant temperature. The host computer recorded the winding temperature, continuous torque, and rated speed of the electric drive assembly.

[0142] c) Starting when the electric drive assembly outputs a stable rated power of 85 kW, record the temperature every 30 seconds and observe the temperature change of the electric drive assembly windings on the host computer until the maximum and minimum values ​​of ten consecutive values ​​are less than 1K.

[0143] d) Plot the temperature rise curve under rated operating conditions, such as Figure 21 As shown.

[0144] Figure 21 To test the actual temperature change curve of the electric drive assembly, the graph shows that the temperature of the electric drive assembly basically reaches a stable state after about 1000s, indicating that the heat generation and dissipation of the electric drive assembly are in balance at this time. Since the highest temperature of this electric drive assembly is at the winding end, a corresponding temperature sensor is designed at the winding end for data acquisition. The experimentally measured maximum steady-state heat dissipation temperature of the electric drive assembly is 393 K, which can well meet the heat dissipation requirements of the electric drive assembly. At the same time, the experimental value differs from the 391.831 K obtained through design simulation by only 1.169 K, which shows that the established electric drive assembly thermal analysis model and heat dissipation optimization framework have high reliability.

[0145] In summary, referring to Figure 22 As shown, Figure 22 This is a schematic diagram of the structure of an electric drive assembly heat dissipation optimization framework provided by the present invention. Before optimizing and analyzing the heat dissipation method of the electric drive assembly, a corresponding electric drive assembly heat dissipation optimization framework is first constructed. Through the electric drive assembly heat dissipation optimization framework, the parametric modeling and optimization of the electric drive assembly heat dissipation system can be effectively realized. The electric drive assembly heat dissipation optimization framework includes: scheme design and parameter selection, construction of surrogate model, evaluation and improvement of surrogate model, and optimization model and algorithm solution.

[0146] Specifically, the electric drive assembly heat dissipation method is optimized and designed to find the optimal electric drive assembly heat dissipation parameters and obtain the best heat dissipation effect. First, an electric drive assembly heat dissipation optimization framework is constructed, then the design parameters are selected according to the electric drive assembly heat dissipation optimization framework, the proxy model is constructed and improved, and the best proxy model method is verified and selected. For the constructed proxy model, a multi-objective optimization algorithm is selected for optimization and solution. Finally, the optimization results are analyzed and described to obtain the optimal design scheme.

[0147] In some optional embodiments, the pros and cons of different optimization algorithms are compared using the utopia point method to obtain the actual optimal scheme, which includes:

[0148] The data is normalized, and target repair weights are given according to the importance of the research targets (cooling water pressure, cooling oil pressure, and maximum temperature of the electric drive assembly). The Euclidean distance between the point represented by each optimal solution and the utopia point is calculated using the utopia point and the target repair weight. The Euclidean distance between the point represented by each optimal solution and the anti-utopia point is calculated using the anti-utopia point and the target repair weight. The fitness is obtained according to the Euclidean distance between the point represented by each optimal solution and the utopia point and the Euclidean distance between the point represented by each optimal solution and the anti-utopia point.

[0149] Specifically, the data (such as cooling water pressure, cooling oil pressure, and maximum temperature of the electric drive assembly) is normalized, and target repair weights are given according to the importance of the research targets (cooling water pressure, cooling oil pressure, and maximum temperature of the electric drive assembly).

[0150] Specifically, the calculation method of the normalized value is repair weight * (original value - worst value) / normalization range. The selection of the normalization range and the repair weight should be determined according to the specific numerical size, numerical range, and project requirements. In this design scheme, the normalization range is the difference between the maximum and minimum values in the Pareto frontier solution. As can be seen from the distribution range of the Pareto solution, the maximum temperature value is concentrated near 400K, which is relatively high under the rated operating condition, so the corresponding repair weight should be increased to obtain better optimization results for temperature. The numerical size of the cooling oil pressure and the cooling water pressure is close, and the load demand of the radiator and the pump body is also close, so the same repair weight can be selected. Based on the above, the repair weight values of the cooling water pressure, the cooling oil pressure, and the maximum temperature of the electric drive assembly are selected as 1, 1, and 3. The value of the utopia point is the best value of the research target Pareto solution, which is normalized; the value of the anti-utopia point is the water pressure difference calculated based on the rated power of the water pump and the calculated flow (the maximum water pressure allowed under the rated power); the oil pressure difference calculated based on the rated power of the oil pump and the calculated flow (the maximum oil pressure allowed under the rated power); and the maximum operating temperature of the motor, which is normalized.

[0151] The target repair weight is calculated by using the utopia point P+, and the Euclidean distance S+ between the point Ti represented by each optimal solution and the utopia point is obtained, and the specific calculation formula is as follows:

[0152] Wherein, S represents the distance, i=1 represents that the distance starts from unit 1;

[0153] The target repair weight is calculated by using the anti-utopia point P-, and the Euclidean distance S- between the point Ti represented by each optimal solution and the anti-utopia point is obtained, and the specific calculation formula is as follows:

[0154]

[0155] Wherein, S represents the distance, i=1 represents that the distance starts from unit 1;

[0156] According to the Euclidean distance between the point represented by each optimal solution and the utopia point and the Euclidean distance between the point represented by each optimal solution and the anti-utopia point, the fitness C is obtained, and the fitness C represents the difference between the optimization point and the ideal optimal point, and the specific calculation formula is as follows:

[0157]

[0158] The above scheme can be understood as determining the fitness by the Euclidean distance between the point represented by each optimal solution and the utopia point and the Euclidean distance between the point represented by each optimal solution and the anti-utopia point, and selecting the point with the best fitness as the actual optimal scheme.

[0159] It can be known from the above embodiment that the heat dissipation method of the vehicle electric drive assembly provided by the application at least has the following beneficial effects:

[0160] ​​​The present invention provides a heat dissipation method for a vehicle electric drive assembly, comprising: acquiring a sample space with a reasonable distribution of sample points; selecting the highest temperature, cooling water pressure, and cooling oil pressure of the electric drive assembly as research objectives based on the sample space with a reasonable distribution of sample points, and constructing a surrogate model of the electric drive assembly; optimizing the surrogate model of the electric drive assembly through an incremental learning strategy to obtain a high-precision surrogate model; using the oil circuit structure of the motor as a design variable, and the highest temperature and coolant pressure of the electric drive assembly as optimization objectives, solving the high-precision surrogate model using a multi-objective optimization algorithm to obtain the optimal solution of different optimization algorithms; and using the above scheme, optimizing the surrogate model of the electric drive assembly through an incremental learning strategy to achieve a high-precision surrogate model. The model's accuracy was significantly improved, with the final R-squared value reaching 0.983, accurately reflecting the actual physical conditions. Subsequently, different multi-objective optimization algorithms were used to solve the high-precision surrogate model, yielding optimal solutions for each algorithm. These optimal solutions were then analyzed using the Utopian point method to obtain the final optimal solution, which was verified to have high reliability. This significantly improves the heat dissipation of the electric drive assembly, providing theoretical support for the production and processing of actual electric drive assembly heat dissipation systems. Furthermore, since the lifespan of the induction motor is greatly affected by the maximum operating temperature of the electric drive assembly, improving the internal heat dissipation of the motor can extend its lifespan.

[0161] Example 2

[0162] Reference Figure 23 As shown, Figure 23 This is a schematic diagram of a heat dissipation system for a vehicle electric drive assembly provided by the present invention. This embodiment provides a heat dissipation system for a vehicle electric drive assembly, applied to a heat dissipation method for the aforementioned vehicle electric drive assembly, including:

[0163] The acquisition module 100 is used to acquire a sample space with a reasonable distribution of sample points.

[0164] Module 200 is used to construct a proxy model of the electric drive assembly by selecting the highest temperature, cooling water pressure and cooling oil pressure of the electric drive assembly as research targets based on a reasonable sample space with sample point distribution;

[0165] The optimization module 300 is used to optimize the electric drive assembly proxy model through an incremental learning strategy to obtain a high-precision proxy model.

[0166] The calculation module 400 is used to solve the high-precision surrogate model using a multi-objective optimization algorithm, with the motor's oil circuit structure as the design variable and the electric drive assembly's maximum temperature and coolant pressure as the optimization objectives, to obtain the optimal solution for different optimization algorithms.

[0167] Example 3

[0168] This embodiment provides an electronic device, which includes:

[0169] a memory for storing a program; and

[0170] a processor for executing the heat dissipation method of the vehicle electric drive assembly by calling the program stored in the memory.

[0171] Embodiment Four

[0172] The embodiment provides a computer readable storage medium, and the computer readable storage medium stores computer instructions, and the computer instructions are used for causing a computer to execute the heat dissipation method of the vehicle electric drive assembly.

[0173] Although some specific embodiments of the present application have been described in detail by examples, those skilled in the art should understand that the above examples are only for illustration, and are not intended to limit the scope of the present application. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. A heat dissipation method of a vehicle electric drive assembly, characterized in that, The method comprises the following steps: obtaining a sample space with reasonable sample point distribution; selecting the maximum temperature of the electric drive assembly, the cooling water pressure and the cooling oil pressure as research targets according to the sample space with reasonable sample point distribution, and constructing an electric drive assembly surrogate model; optimizing the electric drive assembly surrogate model through an incremental learning strategy to obtain a high-precision surrogate model; taking the oil path structure of the motor as a design variable, taking the maximum temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, and solving the high-precision surrogate model by using a multi-objective optimization algorithm to obtain optimal solutions of different optimization algorithms; comparing the advantages and disadvantages of different optimization algorithms by using the utopia point method to obtain an actual optimal scheme; the method comprises the following steps: normalizing the data, and determining the target repair weight values of the cooling water pressure, the cooling oil pressure and the maximum temperature of the electric drive assembly as 1, 1 and 3 respectively according to the importance of the research targets; calculating the Euclidean distance between the point represented by each optimal solution and the utopia point by using the utopia point and the target repair weight; calculating the Euclidean distance between the point represented by each optimal solution and the anti-utopia point by using the anti-utopia point and the target repair weight; the value of the anti-utopia point is the water pressure difference calculated based on the rated power of the water pump and the calculated flow, the oil pressure difference calculated based on the rated power of the oil pump and the calculated flow, and the maximum working temperature of the motor; obtaining the fitness according to the Euclidean distance between the point represented by each optimal solution and the utopia point and the Euclidean distance between the point represented by each optimal solution and the anti-utopia point.

2. The heat dissipation method of the vehicle electric drive assembly according to claim 1, characterized in that, After the step of taking the oil path structure of the motor as a design variable, taking the maximum temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, and solving the high-precision surrogate model by using a multi-objective optimization algorithm to obtain optimal solutions of different optimization algorithms, the method further comprises the following steps: comparing the advantages and disadvantages of different optimization algorithms by using the utopia point method to obtain an actual optimal scheme; importing the design variable corresponding to the optimal solution into a thermal simulation analysis model to obtain simulation values of the maximum temperature, the cooling water pressure and the cooling oil pressure; selecting the minimum deviation between the optimization values and the simulation values of the maximum temperature, the cooling water pressure and the cooling oil pressure according to the deviation between the optimization values and the simulation values of the maximum temperature, the cooling water pressure and the cooling oil pressure to obtain a final optimization scheme.

3. The heat dissipation method of the vehicle electric drive assembly according to claim 1, characterized in that, The step of optimizing the electric drive assembly surrogate model through an incremental learning strategy to obtain a high-precision surrogate model comprises the following steps: evaluating the accuracy of the electric drive assembly surrogate model by using an evaluation index; optimizing the design variables with insufficient precision in the evaluated electric drive assembly surrogate model by using an incremental Kriging method, and continuously optimizing and updating the initial training set by using an expectation improvement method to obtain the high-precision surrogate model.

4. The heat dissipation method of the vehicle electric drive assembly according to claim 3, characterized in that, The step of optimizing the design variables with insufficient precision in the evaluated electric drive assembly surrogate model by using an incremental Kriging method, and continuously optimizing and updating the initial training set by using an expectation improvement method to obtain the high-precision surrogate model comprises the following steps: assuming that the number of new sample points added is s, and the incremental Kriging expression is as follows: ， wherein the related update process variables are as follows: ， ， ， ， The expected improvement method is used to add sample points in the incremental kriging method. It is assumed that for any design variable x, the response value y is a random variable obeying normal distribution, and its mean value is and its probability density function is ， Assume the optimal response value of the current sample is The expected value of the objective function of this design point is: ， the expectation improvement function is as follows: ， wherein is the cumulative distribution function of the standard normal distribution.

5. The heat dissipation method of the vehicle electric drive assembly according to claim 1, characterized in that, The step of obtaining the sample space with reasonable sample point distribution comprises the following steps: Obtaining a heat dissipation design variable corresponding to the electric drive assembly, the heat dissipation design variable including an oil inner diameter, a nozzle size, a water channel connection width, an oil inlet diameter, an oil inlet depth, a cooling oil flow rate, and a cooling water flow rate; Sampling the heat dissipation design variable by using an experimental design method, and selecting a sample space with reasonable sample point distribution.

6. A heat dissipation system of a vehicle electric drive assembly, characterized in that, The heat dissipation method applied to the electric drive assembly of any one of claims 1-5, comprising: An obtaining module configured to obtain a sample space with reasonable sample point distribution; A constructing module configured to select the highest temperature of the electric drive assembly, the cooling water pressure, and the cooling oil pressure as research targets according to the sample space with reasonable sample point distribution, and construct an electric drive assembly proxy model; An optimizing module configured to optimize the electric drive assembly proxy model by using an incremental learning strategy to obtain a high-precision proxy model; A calculating module configured to take the oil path structure of the motor as a design variable, take the highest temperature of the electric drive assembly and the cooling liquid pressure as optimization targets, use a multi-objective optimization algorithm to solve the high-precision proxy model, and obtain optimal solutions of different optimization algorithms.

7. An electronic device, comprising: The electronic device comprises: a memory for storing a program; and a processor for executing the heat dissipation method of the electric drive assembly of any one of claims 1-5 by calling the program stored in the memory.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the computer to execute the heat dissipation method of the electric drive assembly of any one of claims 1-5. The computer readable storage medium stores computer instructions for causing the computer to execute the heat dissipation method of the electric drive assembly of any one of claims 1-5.

Images