Method, device and electronic equipment for predicting motor temperature

Abstract

The application discloses a motor temperature determination method and device and electronic equipment. The method comprises the following steps: obtaining test data of a motor, wherein the test data is obtained by testing the motor under multiple working conditions; converting the test data into multiple thermal resistance values of the motor under the multiple working conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; fitting the multiple thermal resistance values to obtain fitting parameters inside the motor; and determining a target working temperature of the motor based on the fitting parameters and the thermal resistance values. The application solves the technical problem of low prediction accuracy of the motor temperature.

Description

Technical Field

[0001] This invention relates to the field of motor temperature prediction technology, and more specifically, to a method, apparatus, and electronic device for determining motor temperature. Background Technology

[0002] Currently, the main methods for predicting motor temperature include the flux linkage method, data analysis method, and thermal network model method. However, these three methods cannot achieve dynamic adjustment of model parameters, resulting in low accuracy in motor temperature prediction.

[0003] There is currently no effective solution to the technical problem of low accuracy in predicting motor temperature. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for determining motor temperature, thereby at least solving the technical problem of low prediction accuracy of motor temperature.

[0005] According to one aspect of the invention, a method for determining motor temperature is provided. The method may include: acquiring test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions; converting the test data into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; fitting the multiple thermal resistance values ​​to obtain fitting parameters inside the motor; and determining the target operating temperature of the motor based on the fitting parameters and the thermal resistance values.

[0006] Optionally, converting test data into multiple thermal resistance values ​​of the motor under various operating conditions based on the target thermal network model may include: encoding the test data to obtain target test data; iterating the target test data multiple times through the target thermal network model to obtain target objects, wherein the target objects are used to represent individuals obtained after selection, mutation, and crossover operations; and decoding the target objects to obtain thermal resistance values.

[0007] Optionally, encoding the test data to obtain target test data may include: initializing the initial operating parameters to obtain target operating parameters, wherein the target operating parameters include at least selection operating parameters, mutation operating parameters, and / or crossover operating parameters; and inputting the target operating parameters and test data into the target thermal network model to obtain the target test data.

[0008] Optionally, the method may further include: building a target thermal network model based on the initial parameters of the motor, wherein the target thermal network model contains at least multiple object nodes.

[0009] Optionally, fitting multiple thermal resistance values ​​to obtain fitting parameters inside the motor may include: determining a target fitting function based on a nonlinear function; and fitting multiple thermal resistance values ​​based on the target fitting function to obtain fitting parameters.

[0010] Optionally, based on the target fitting function, multiple thermal resistance values ​​are fitted to obtain fitting parameters, including: based on evaluation coefficients, multiple thermal resistance values ​​are fitted using the target fitting function to obtain fitting parameters, wherein the evaluation coefficients are used to represent the evaluation index of fitting multiple thermal resistance values.

[0011] According to one aspect of the present invention, a device for determining motor temperature is provided. The device may include: a first acquisition unit for acquiring test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions; a conversion unit for converting the test data into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; a second acquisition unit for fitting the multiple thermal resistance values ​​to obtain fitting parameters inside the motor; and a determination unit for determining the target operating temperature of the motor based on the fitting parameters and the thermal resistance values.

[0012] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the motor temperature prediction method of the present invention.

[0013] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the motor temperature prediction method of the present invention during runtime.

[0014] According to another aspect of the present invention, an electronic device is also provided. The electronic device includes one or more processors and a memory, the memory storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the motor temperature prediction method of the present invention.

[0015] In this embodiment of the invention, test data of the motor is acquired, wherein the test data is obtained by testing the motor under various operating conditions; the test data is converted into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; the multiple thermal resistance values ​​are fitted to obtain fitting parameters inside the motor; and the target operating temperature of the motor is determined based on the fitting parameters and the thermal resistance values. In other words, this embodiment of the invention, based on the obtained test data of the motor and the mapping relationship between the test data and the thermal resistance values, can convert the motor test data into multiple thermal resistance values ​​of the motor under various operating conditions, then fit these multiple thermal resistance values ​​to obtain fitting parameters inside the motor, and finally determine the target operating temperature of the motor based on the obtained fitting parameters and the thermal resistance values. This solves the technical problem of low prediction accuracy of motor temperature and achieves the technical effect of improving the prediction accuracy of motor temperature. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0017] Figure 1 This is a flowchart of a method for determining motor temperature according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart illustrating temperature prediction for an oil-cooled motor according to an embodiment of the present invention.

[0019] Figure 3 This is a flowchart illustrating the prediction of oil-cooled motor temperature according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of a motor temperature determination device according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1

[0024] According to an embodiment of the present invention, a method for determining motor temperature is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] The method for predicting motor temperature according to an embodiment of the present invention will be described below.

[0026] Figure 1 This is a flowchart of a method for determining motor temperature according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method may include the following steps:

[0027] Step S101: Obtain test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions.

[0028] In the technical solution provided by step S101 of the present invention, test data of the motor under various operating conditions can be obtained. The test data can be the motor's operating temperature data or temperature rise test data. For example, when developing a motor temperature rise test, the motor temperature rise test is first designed, and the temperature rise test data is obtained.

[0029] It should be noted that this is only a preferred embodiment for obtaining test data of the motor, and does not limit the process and method of obtaining test data of the motor. All processes and methods for obtaining test data of the motor are within the protection scope of this invention, and will not be listed here.

[0030] Step S102: Based on the target thermal network model, the test data is converted into multiple thermal resistance values ​​of the motor under various operating conditions. The target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values.

[0031] In the technical solution provided by step S102 of the present invention, based on the test data of the motor obtained in step S101, the test data can be converted into multiple thermal resistance values ​​of the motor under various operating conditions according to the target thermal network model. Wherein, the thermal resistance value is the optimal thermal resistance value of the motor under a specific operating condition; more specifically, each thermal resistance value is the optimal thermal resistance value of the motor under various operating conditions.

[0032] Optionally, based on the target thermal network model, after encoding the test data, the target test data is iterated multiple times to obtain the target object. After decoding the target object, the thermal resistance value can be obtained.

[0033] For example, based on a target thermal network model, optimization algorithms can be used to convert test data into multiple thermal resistance values ​​for the motor under various operating conditions, thereby achieving the goal of obtaining the optimal thermal resistance value of the motor under each condition. These optimization algorithms can include genetic algorithms, particle swarm optimization, ant colony optimization, and artificial bee colony optimization, among others. This section only provides examples of optimization algorithms and does not impose specific limitations on them.

[0034] It should be noted that this is only a preferred embodiment for obtaining the optimal thermal resistance value of the motor under different operating conditions. The process and method for obtaining the optimal thermal resistance value of the motor under different operating conditions are not specifically limited. All processes and methods for obtaining the optimal thermal resistance value of the motor under different operating conditions are within the protection scope of this invention, and will not be listed here.

[0035] Step S103: Fit multiple thermal resistance values ​​to obtain the fitting parameters inside the motor.

[0036] In the technical solution provided in step S103 of the present invention, based on the multiple thermal resistance values ​​obtained in step S102, fitting parameters inside the motor are obtained by fitting the multiple thermal resistance values. These fitting parameters may include motor speed parameters, torque parameters, ambient temperature parameters, etc.

[0037] Optionally, a target fitting function can be determined using a nonlinear function, thereby further fitting multiple thermal resistance values ​​to obtain the fitting function inside the motor.

[0038] It should be noted that this is only a preferred embodiment for obtaining the fitting parameters inside the motor, and the process and method for obtaining the fitting parameters inside the motor are not specifically limited. All processes and methods for obtaining the fitting parameters inside the motor are within the protection scope of this invention, and will not be listed here.

[0039] For example, by analyzing the internal thermal resistance parameters of an oil-cooled motor, the optimal thermal resistance values ​​obtained under various operating conditions can be fitted to determine the fitted parameters such as motor speed, torque, and ambient temperature parameters inside the motor.

[0040] Step S104: Determine the target operating temperature of the motor based on the fitted parameters and thermal resistance value.

[0041] In the technical solution provided in step S104 of the present invention, based on the target thermal network model, the obtained test data of the motor is converted into multiple thermal resistance values ​​of the motor under various operating conditions, so that multiple thermal resistance values ​​can be fitted to obtain the fitting parameters inside the motor. Based on the obtained fitting parameters and thermal resistance values, the target operating temperature of the motor can be determined.

[0042] Optionally, the target operating temperature of the motor can be determined online based on the obtained fitting parameters such as motor speed parameters, torque parameters, and ambient temperature parameters, as well as the optimal thermal resistance value under various operating conditions. For example, 30 degrees Celsius (°C), 40 degrees Celsius, 50 degrees Celsius, etc. This is only an example of the target operating temperature of the motor online prediction, and no specific limit is made to the target operating temperature of the motor online prediction.

[0043] Optionally, the target thermal network model is loaded into the motor controller, and parameters such as motor voltage, current, speed, torque, and ambient temperature are collected in real time. The heat generation of each component of the motor and the thermal resistance of each node are calculated to obtain the online predicted temperature of the motor, thereby improving the accuracy of motor temperature prediction.

[0044] In steps S101 to S104 of this invention, test data of the motor is obtained, wherein the test data is obtained by testing the motor under various operating conditions; the test data is converted into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; the multiple thermal resistance values ​​are fitted to obtain fitting parameters inside the motor; and the target operating temperature of the motor is determined based on the fitting parameters and the thermal resistance values. In other words, this embodiment of the invention, based on a target thermal network model, converts the test data of the motor into multiple thermal resistance values ​​of the motor under various operating conditions, then fits these multiple thermal resistance values ​​to obtain fitting parameters inside the motor, and determines the target operating temperature of the motor based on the obtained fitting parameters and thermal resistance values, thereby solving the technical problem of low prediction accuracy of motor temperature and achieving the technical effect of improving the prediction accuracy of motor temperature.

[0045] The method described in this embodiment will be further described below.

[0046] As an optional embodiment, step S102, based on the target thermal network model, converts the test data into multiple thermal resistance values ​​of the motor under various operating conditions, including: encoding the test data to obtain target test data; iterating the target test data multiple times through the target thermal network model to obtain a target object, wherein the target object is used to represent the individual obtained after selection, mutation and crossover operations; and decoding the target object to obtain the thermal resistance value.

[0047] In this embodiment, the test data can be the original population data, for example, the original population data can be randomly generated according to the target hot network model. The target test data can be the initial population data. The target object can be the optimal individual, for example, the optimal individual can be obtained through an optimization algorithm, where the optimization algorithm can include genetic algorithms, particle swarm optimization algorithms, ant colony optimization algorithms, artificial bee colony optimization algorithms, etc. The selection operation can be to select some excellent individuals from the previous generation population and pass them on to the next generation population according to certain rules or methods based on the fitness value of each individual. The crossover operation can be used to generate new individuals by changing the gene combination of individuals. The mutation operation can be used to change the gene value of one or more loci to other alleles for each individual in the population with a mutation probability.

[0048] In this embodiment, the obtained test data can be encoded to obtain target test data. The target test data can be iterated multiple times using the target thermal network model to obtain the target object. After decoding the target object, the thermal resistance value can be obtained.

[0049] Optionally, after encoding the test data, target test data is obtained. This target test data is then iterated multiple times using a target thermal network model. The target object is calculated using the root mean square error (RMSE), and the optimal thermal resistance value can be obtained after decoding the target object. For example, the target object obtained through RMSE evaluation can be iterated multiple times using the target thermal network model to output the optimal individual. By decoding the optimal individual, the optimal thermal resistance value of the motor under various operating conditions can be obtained. The RMSE is expressed by the following formula:

[0050]

[0051] Where N can be used to represent the sum of the data, and T i This is the test temperature data, T' i This is the temperature prediction result.

[0052] As an optional embodiment, encoding the test data to obtain target test data includes: initializing the initial operating parameters to obtain target operating parameters, wherein the target operating parameters include at least selection operating parameters, mutation operating parameters, and / or crossover operating parameters; and inputting the target operating parameters and test data into the target thermal network model to obtain the target test data.

[0053] In this embodiment, initial operating parameters can be initialized to obtain target operating parameters. These target operating parameters and test data are then input into the target hot network model to further obtain target test data. Specifically, the selection operating parameters, mutation operating parameters, and crossover operating parameters in the target operating parameters are those used in the selection operation, mutation operation parameters, and crossover operation parameters, respectively. For example, target operating parameters may include chromosome coding parameters, fitness function selection operating parameters, crossover operation, or mutation operation probability parameters and other operating parameters. This is merely an illustrative example of target operating parameters and does not impose specific limitations on them.

[0054] It should be noted that this is only a preferred embodiment for obtaining target test data, and does not limit the method and process of obtaining target test data. All methods and processes for obtaining target test data are within the protection scope of this invention, and are not listed here.

[0055] As an optional embodiment, the method further includes: building a target thermal network model based on the initial parameters of the motor, wherein the target thermal network model contains at least multiple object nodes.

[0056] In this embodiment, the initial parameters of the motor can be motor geometric parameters, cooling method parameters, material property parameters, etc. Multiple object nodes can include at least four nodes, such as motor windings, stator cores, rotor cores, magnets, etc. This is merely an example to illustrate the initial parameters and object nodes of the motor, and no specific limitations are imposed on them.

[0057] In this embodiment, an initial thermal network model can be built based on the initial parameters of the motor to obtain the target thermal network model. For example, the motor thermal network model can be built based on parameters such as motor geometry parameters, cooling method parameters, and material property parameters. The thermal network model includes four nodes: motor windings, stator core, rotor core, and magnets, thereby reducing the complexity of the model, reducing the workload of experimental calibration, and shortening the development cycle.

[0058] As an optional embodiment, multiple thermal resistance values ​​are fitted to obtain fitting parameters inside the motor, including: determining a target fitting function based on a nonlinear function; and fitting multiple thermal resistance values ​​based on the target fitting function to obtain fitting parameters.

[0059] In this embodiment, a target fitting function can be determined based on a nonlinear function. Based on the obtained target fitting function, multiple thermal resistance values ​​can be fitted to obtain fitting parameters. For example, fitting parameters can be obtained by analyzing the relevant parameters of the internal thermal resistance of an oil-cooled motor and fitting the optimal thermal resistance value obtained under various operating conditions using the fitting function. The fitting function can be as follows:

[0060] r = Av 2 +Bv+CN 2 +DN+ET

[0061] Where r is the internal node thermal resistance of the motor, v is the motor speed, N is the motor output torque, T is the ambient temperature, and A, B, C, D, and E are constants.

[0062] Optionally, the fitting effect of the target fitting function on multiple thermal resistance values ​​can be evaluated using evaluation coefficients. This enables adaptive adjustment of the thermal network model parameters, solving the problem of large variations in internal thermal resistance of oil-cooled motors under operating conditions and improving the accuracy of motor temperature prediction. It should be noted that this is merely a preferred implementation of the evaluation index for evaluating the target fitting function, and no specific limitation is made to the evaluation index for evaluating the target fitting function.

[0063] As an optional embodiment, multiple thermal resistance values ​​are fitted based on a target fitting function to obtain fitting parameters, including: fitting multiple thermal resistance values ​​based on an evaluation coefficient using a target fitting function to obtain fitting parameters, wherein the evaluation coefficient is an evaluation index for fitting multiple thermal resistance values.

[0064] In this embodiment, multiple thermal resistance values ​​can be fitted using a target fitting function based on evaluation coefficients to obtain fitting parameters. The evaluation coefficients can be the coefficients of determination, and these coefficients can be expressed by R0. 2 To express.

[0065] Optionally, the target fitting function can be evaluated using the coefficient of determination. A coefficient closer to 1 indicates a better fit. The coefficient of determination can be expressed by the following formula:

[0066]

[0067] In the above formula, r i′ is the fitting function for the thermal resistance value, r i This is the thermal resistance value. denoted as the mean thermal resistance, and n as the number of samples.

[0068] In this embodiment, based on the target thermal network model, the test data of the motor can be converted into multiple thermal resistance values ​​of the motor under various operating conditions. Then, the multiple thermal resistance values ​​are fitted to obtain the fitting parameters inside the motor. Based on the obtained fitting parameters and thermal resistance values, the target operating temperature of the motor is determined, which solves the technical problem of low prediction accuracy of motor temperature and achieves the technical effect of improving the prediction accuracy of motor temperature.

[0069] Example 2

[0070] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0071] With the development of new energy vehicles, the power density of motors is increasing, and the heat generation is becoming more severe. When the temperature reaches a certain value, not only is there a risk of demagnetization of the rotor magnets, but the motor windings may also burn out, leading to motor damage. To address these issues, online temperature sensors can be used to measure the motor temperature. However, this method suffers from slow response times, and as a high-speed rotating component, directly measuring the rotor temperature using online temperature sensors is very difficult.

[0072] Current research on online motor temperature prediction methods mainly includes: flux linkage method, data analysis method, and thermal network model method. Among these, the flux linkage method calculates the rotor flux linkage using a simple voltage equation, resulting in a large error in the calculated rotor temperature. This method is also unsuitable for stationary and low-speed motor conditions and suffers from poor reliability. The data analysis method utilizes machine learning to collect motor operating parameters and temperature data, forming a dataset, and then training a model to predict motor temperature. However, the data analysis method requires high-quality experimental data and a large sample size for establishing temperature prediction models, and it also faces challenges such as difficulty in data acquisition, long development cycles, and high development costs. The thermal network model method treats points with similar temperatures in the motor as equivalent nodes, connected by thermal resistance. The heat storage of different parts of the material can be represented by heat capacity, resulting in a thermal network model. However, because oil-cooled motors employ winding oil spraying and rotor oil slinging cooling methods, their internal thermal resistance and other parameters fluctuate significantly with motor speed. Therefore, the thermal network model method cannot dynamically adjust the model parameters, leading to inaccurate prediction accuracy.

[0073] In one possible implementation, a method and system for predicting motor rotor temperature for control is proposed. This method includes: conducting rotor temperature measurement tests on the motor under different operating conditions; synchronously collecting electrical, mechanical, and temperature time-series data of the tested motor during the tests to establish a sample dataset; training a pre-established deep learning model based on the sample dataset to obtain a trained motor rotor temperature prediction model; acquiring motor parameters in real time and loading them into the motor rotor temperature prediction model to obtain the electronic rotor temperature prediction result; and performing motor control based on this electronic rotor temperature prediction result, thereby improving motor control performance. However, the above method suffers from the technical problems of requiring a large amount of experimental data and having a long development cycle.

[0074] In another possible implementation, a real-time rotor temperature prediction method for permanent magnet synchronous motors is proposed. This method includes: collecting rotor-related physical parameters to construct a sample dataset; selecting first relevant data from the sample dataset as input; selecting first temperature data corresponding to the first relevant data from the sample dataset as output; normalizing the input and output; constructing a Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN) prediction model using the normalized input and output; during permanent magnet synchronous motor operation, collecting second relevant data and corresponding second temperature data to construct a training dataset; normalizing the data in the training dataset and using it as training data to train the LSTM-CNN prediction model; and predicting the real-time rotor temperature using third relevant data monitored online and the trained LSTM-CNN prediction model. However, the above method suffers from the technical problems of requiring a large amount of experimental data and having a long development cycle.

[0075] In another possible implementation, a real-time rotor temperature estimation method for motors is proposed. This method includes constructing a motor temperature estimation model based on a motor loss model and a thermal circuit model. The model is expressed in state-space form. The model inputs are the motor's operating current, speed, ambient temperature, and other hot spot temperatures that can be measured using reliable and low-cost sensors. The model outputs key hot spot temperatures such as the motor winding temperature, stator core temperature, and rotor magnet temperature, thus solving the technical problem of the difficulty in real-time measurement of motor rotor temperature. However, the above method still suffers from the technical problem of low prediction accuracy of motor temperature.

[0076] However, to address the problem of low prediction accuracy of motor temperature, this invention provides a method for determining motor temperature. This method uses a target thermal network model to convert the obtained test data of the motor into multiple thermal resistance values ​​of the motor under various operating conditions. Then, the multiple thermal resistance values ​​are fitted to obtain the fitting parameters inside the motor, and finally the target operating temperature of the motor is determined. This solves the technical problem of low prediction accuracy of motor temperature and achieves the technical effect of improving the prediction accuracy of motor temperature.

[0077] Figure 2 This is a flowchart of a controlled oil-cooled motor temperature prediction according to an embodiment of the present invention, such as... Figure 2 As shown, the method may include the following steps:

[0078] Step S201: Build a thermal network model.

[0079] In this embodiment, a motor thermal network model can be built based on the motor geometric model, cooling method, and motor material properties, and the thermal network model can be initialized to simplify the setting of initial values ​​for the motor thermal network model parameters.

[0080] Step S202: Conduct a temperature rise test on the motor based on the established thermal network model.

[0081] In this embodiment, a motor temperature rise test is designed to obtain temperature rise test data.

[0082] Step S203: Optimize the parameters of the thermal network model to obtain the optimal thermal resistance value of the motor under different operating conditions.

[0083] In this embodiment, optimizing the parameters of the thermal network model includes: determining the optimization algorithm: genetic algorithm, particle swarm optimization algorithm, ant colony optimization algorithm, artificial bee colony optimization algorithm, etc.; determining the optimization objective: in order to determine whether the model parameters meet the optimization objective, the root mean square error (RMSE) is introduced to evaluate the model; determining the thermal resistance: the thermal resistance value that minimizes the root mean square error of the thermal network model prediction is the optimal thermal resistance under this operating condition, so as to obtain the optimal thermal resistance value under different operating conditions.

[0084] Step S204: Determine the parameters based on the optimal thermal resistance value of the motor under different operating conditions.

[0085] In this embodiment, the thermal resistance is fitted to the operating conditions based on the thermal resistance optimization results, thereby determining relevant parameters, such as motor speed, torque, and ambient temperature.

[0086] Step S205: Based on the determined parameters, predict the motor temperature using a model.

[0087] In this embodiment, a thermal network model is embedded in the motor controller to collect parameters such as motor voltage, current, speed, torque, and ambient temperature in real time. The model calculates the current heat generation of each component of the motor and the current thermal resistance value of each node, inputs them into the prediction model, and obtains the online prediction results of the temperature of each node of the motor.

[0088] In steps S201 to S205, a thermal network model is first built. Based on the built thermal network model, a temperature rise test of the motor is conducted. Then, the parameters of the thermal network model are optimized to obtain the optimal thermal resistance value of the motor under different operating conditions. Based on the optimal thermal resistance value of the motor under different operating conditions, the parameters are determined. Based on the determined parameters, the motor temperature is predicted using the model, thereby solving the technical problem of low prediction accuracy of motor temperature and achieving the technical effect of improving the prediction accuracy of motor temperature.

[0089] Figure 3 This is a flowchart illustrating the prediction of oil-cooled motor temperature according to an embodiment of the present invention, such as... Figure 3 As shown, the method may include the following steps:

[0090] Step S301: Determine the structure of the thermal network model.

[0091] In this embodiment, a motor thermal network model is built based on parameters such as motor geometry, cooling method, and material properties. The thermal network model includes four nodes: motor windings, stator core, rotor core, and magnets. That is, the thermal network model contains 4 nodes, which can reduce the complexity of the model, reduce the workload of test calibration, and shorten the development cycle.

[0092] Step S302: After determining the thermal network model structure, design a motor temperature rise test and obtain temperature rise test data.

[0093] In this embodiment, when conducting a motor temperature rise test, a motor temperature rise test is designed to obtain temperature rise test data.

[0094] Step S303: Combine the thermal network model and the genetic algorithm to obtain the optimal thermal resistance value of the motor under different operating conditions.

[0095] In this embodiment, a thermal network model and a genetic algorithm can be combined to obtain the optimal thermal resistance value of the motor under different operating conditions.

[0096] Optionally, the parameters in the thermal network model are optimized based on the temperature rise test data. Parameter optimization methods mainly include genetic algorithms, particle swarm optimization, ant colony optimization, and artificial bee colony optimization. Here, we take the genetic algorithm as an example to introduce the parameter optimization process of the thermal network model. The above process may include the following steps:

[0097] Step S3031: Determine the relevant parameters of the genetic algorithm.

[0098] In this embodiment, the relevant parameters of the genetic algorithm (GA) can be determined. These parameters may include the determination of the chromosome encoding method, the selection of the fitness function, the determination of the selection operation implementation algorithm, the probability of crossover and mutation operations, and the setting of operation parameters.

[0099] Step S3032: Encode the initial data.

[0100] In this embodiment, the input data can be preprocessed to encode the initial data using a genetic algorithm.

[0101] Optionally, based on the structure of the thermal network, an original population is randomly generated, and individuals in the original population are encoded with real numbers, with each individual encoded as information related to the thermal resistance of the motor.

[0102] Step S3033: Perform the selection operation.

[0103] Step S3034: Perform the crossover operation.

[0104] Step S3035: Perform the mutation operation.

[0105] Step S3036: Calculate the individual fitness value using the mean square error to obtain the optimal individual.

[0106] In this embodiment, the individual fitness value is calculated using the root mean square error (RMSE). The RMSE is defined as follows:

[0107]

[0108] In the above formula, N is the total sum of the data, and T... i It is the test temperature data, T i This is the temperature prediction result.

[0109] Optionally, the root mean square error can be used to evaluate the fitness of each individual in the population. Excellent individuals will be inherited into the next generation of the population, and crossover and mutation operations will be performed. After multiple iterations, the genetic algorithm can finally output the optimal individual.

[0110] Step S3037: Decode the optimal individual to obtain the optimal thermal resistance value, and then obtain the optimal thermal resistance value under different operating conditions.

[0111] Step S304: Based on the optimal thermal resistance value under different operating conditions, determine the fitting parameters through a fitting function.

[0112] In this embodiment, the internal thermal resistance parameters of the oil-cooled motor can be analyzed, and the optimal thermal resistance value obtained under various operating conditions can be fitted using a fitting function to determine the fitting parameters. These fitting parameters include motor speed, torque, and ambient temperature. This is merely an illustrative example and is not intended to be specific.

[0113] Alternatively, the above fitting function is shown below:

[0114] r = Av 2 +Bv+CN 2 +DN+ET

[0115] In the above formula, r is the internal node thermal resistance of the motor, v is the motor speed, N is the motor output torque, T is the ambient temperature, and A, B, C, D, and E are constants.

[0116] Optionally, by the coefficient of determination R 2 Evaluate the fitted function; if R... 2 A value closer to 1 indicates a better function fit. The coefficient of determination is shown in the following formula:

[0117]

[0118] In the formula r i ' is the function to fit the thermal resistance value, r i This is the thermal resistance value. denoted as the mean thermal resistance, and n as the number of samples.

[0119] Step S305: Model application to predict motor temperature.

[0120] In this embodiment, the thermal network model can be embedded into the motor controller to collect parameters such as motor voltage, current, speed, torque, and ambient temperature in real time. The heat generation of each component of the motor and the thermal resistance of each node are calculated and input into the prediction model to obtain the online prediction result of motor temperature. This enables adaptive adjustment of thermal network model parameters, solves the problem of large changes in internal thermal resistance of oil-cooled motors with operating conditions, and improves the accuracy of temperature prediction.

[0121] In steps S301 to S305, the thermal network model structure is first determined. After determining the thermal network model structure, a motor temperature rise test is designed, and temperature rise test data is obtained. Then, the thermal network model and the genetic algorithm are combined to obtain the optimal thermal resistance value of the motor under different operating conditions. Based on the optimal thermal resistance value under different operating conditions, the fitting parameters are determined through the fitting function. Finally, the model can be applied to predict the motor temperature, thereby solving the technical problem of low prediction accuracy of motor temperature and achieving the technical effect of improving the prediction accuracy of motor temperature.

[0122] Example 3

[0123] According to an embodiment of the present invention, a device for determining motor temperature is provided. It should be noted that this motor temperature prediction device can be used to execute a motor temperature determination method as described in Embodiment 1.

[0124] Figure 4 This is a schematic diagram of a motor temperature determination device according to an embodiment of the present invention. Figure 4 As shown, a motor temperature determination device 400 may include: a first acquisition unit 401, a conversion unit 402, a second acquisition unit 403, and a determination unit 404.

[0125] The first acquisition unit 401 is used to acquire test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions.

[0126] The conversion unit 402 is used to convert test data into multiple thermal resistance values ​​of the motor under various operating conditions based on the target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between test data and thermal resistance values.

[0127] The second acquisition unit 403 is used to fit multiple thermal resistance values ​​to obtain the fitting parameters inside the motor.

[0128] The determination unit 404 is used to determine the target operating temperature of the motor based on the fitted parameters and the thermal resistance value.

[0129] Optionally, the conversion unit 402 includes: a first acquisition module for encoding the test data to obtain target test data; a second acquisition module for iterating the target test data multiple times through a target thermal network model to obtain a target object, wherein the target object represents an individual obtained after selection, mutation and crossover operations; and a third acquisition module for decoding the target object to obtain a thermal resistance value.

[0130] Optionally, the first acquisition module may include: a first acquisition submodule, used to initialize the initial operation parameters to obtain the target operation parameters, wherein the target operation parameters include at least selection operation parameters, mutation operation parameters and / or crossover operation parameters; and a second acquisition submodule, used to input the target operation parameters and test data into the target thermal network model to obtain the target test data.

[0131] Optionally, the device may further include: a third acquisition unit for building a target thermal network model based on the initial parameters of the motor, wherein the target thermal network model contains at least multiple object nodes.

[0132] Optionally, the second acquisition unit 403 may include: a determination module for determining a target fitting function based on a nonlinear function; and a fourth acquisition module for fitting multiple thermal resistance values ​​based on the target fitting function to obtain fitting parameters.

[0133] Optionally, the fourth acquisition module may include: a third acquisition submodule, used to fit multiple thermal resistance values ​​based on evaluation coefficients and a target fitting function to obtain fitting parameters, wherein the evaluation coefficients are used to represent the evaluation index for fitting multiple thermal resistance values.

[0134] In this embodiment, a first acquisition unit acquires test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions; a conversion unit is used to convert the test data into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; a second acquisition unit is used to fit the multiple thermal resistance values ​​to obtain fitting parameters inside the motor; and a determination unit is used to determine the target operating temperature of the motor based on the fitting parameters and the thermal resistance values, thereby determining the target operating temperature of the motor, solving the technical problem of low prediction accuracy of motor temperature, and achieving the technical effect of improving the prediction accuracy of motor temperature.

[0135] Example 4

[0136] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the motor temperature prediction method of Embodiment 1.

[0137] Example 5

[0138] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the motor temperature prediction method in Embodiment 1 during runtime.

[0139] Example 6

[0140] According to an embodiment of the present invention, an electronic device is also provided, the electronic device including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the motor temperature prediction method of embodiment 1 is executed.

[0141] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0147] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining motor temperature, characterized in that, include: Acquire test data for the motor, wherein the test data is obtained by testing the motor under various operating conditions; The test data is converted into multiple thermal resistance values ​​of the motor under various operating conditions based on the target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; The multiple thermal resistance values ​​are fitted to obtain the fitting parameters inside the motor; Based on the fitting parameters and the thermal resistance value, the target operating temperature of the motor is determined.

2. The method according to claim 1, characterized in that, Based on the target thermal network model, the test data is converted into multiple thermal resistance values ​​of the motor under various operating conditions, including: The test data is encoded to obtain the target test data; The target test data is iterated multiple times through the target hot network model to obtain the target object, wherein the target object is used to represent the individual obtained after selection, mutation and crossover operations; The target object is decoded to obtain the thermal resistance value.

3. The method according to claim 2, characterized in that, The test data is encoded to obtain target test data, including: Initialize the initial operation parameters to obtain the target operation parameters, wherein the target operation parameters include at least selection operation parameters, mutation operation parameters and / or crossover operation parameters; The target operating parameters and the test data are input into the target thermal network model to obtain the target test data.

4. The method according to claim 1, characterized in that, The method further includes: Based on the initial parameters of the motor, the target thermal network model is constructed, wherein the target thermal network model contains at least multiple object nodes.

5. The method according to claim 1, characterized in that, By fitting the multiple thermal resistance values, fitting parameters for the internal components of the motor are obtained, including: Determining the target fitting function based on nonlinear functions; Based on the target fitting function, the plurality of thermal resistance values ​​are fitted to obtain the fitting parameters.

6. The method according to claim 5, characterized in that, Based on the target fitting function, the plurality of thermal resistance values ​​are fitted to obtain the fitting parameters, including: Based on the evaluation coefficients, the plurality of thermal resistance values ​​are fitted using the target fitting function to obtain the fitting parameters, wherein the evaluation coefficients are used to represent the evaluation index for fitting the plurality of thermal resistance values.

7. A device for determining motor temperature, characterized in that, include: The first acquisition unit is used to acquire test data of the motor, wherein the test data is obtained by testing the motor under various operating conditions; A conversion unit is used to convert the test data into multiple thermal resistance values ​​of the motor under various operating conditions based on a target thermal network model, wherein the target thermal network model is used to represent the mapping relationship between the test data and the thermal resistance values; The second acquisition unit is used to fit the plurality of thermal resistance values ​​to obtain the fitting parameters inside the motor; The determining unit is used to determine the target operating temperature of the motor based on the fitting parameters and the thermal resistance value.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the motor temperature prediction method according to any one of claims 1 to 6.

9. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method for predicting motor temperature according to any one of claims 1 to 6.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the motor temperature prediction method according to any one of claims 1 to 6.

Images