Motor stator hottest spot temperature determination method, device and equipment, medium and vehicle

Abstract

The invention discloses a motor stator hottest point temperature determination method and device, equipment, a medium and a vehicle, and the method comprises the steps: obtaining a first parameter set and stator temperature of a motor at an nth moment, and a first parameter set and stator hottest point temperature of the motor at an (n-1) th moment, on the basis of the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the (n-1) th moment, feature data corresponding to the nth moment are determined, the feature data represent temperature change features at adjacent moments, the feature data and the first parameter sets of the motor at the nth moment and the (n-1) th moment are spliced, a target feature vector is obtained, and the target feature vector is used as a target feature vector; and inputting the target feature vector into the hottest point temperature prediction model to obtain the stator hottest point temperature at the nth moment. According to the embodiment, the obtained target feature vector can represent multiple features of the motor stator temperature, so that the accuracy of the predicted hottest point temperature of the stator can be effectively improved by predicting the hottest point temperature of the stator at the nth moment based on the target feature vector.

Description

Technical Field

[0001] The present application belongs to the field of motor technology, and in particular, relates to a method, device, equipment, medium and vehicle for determining the hottest point temperature of a motor stator. Background Art

[0002] In new energy vehicles, the temperature of the hottest point of the motor stator winding needs to be paid special attention to. When the temperature is too high, the stator winding will experience insulation failure and thermal risks.

[0003] In the current related technologies, the most commonly used method for monitoring the hottest point temperature of the motor stator is to place a temperature sensor at a certain point of the stator winding, determine the hottest point temperature of the stator based on the temperature data measured in real time by the temperature sensor, and upload the temperature data to protect the motor. The hottest point temperature of the stator refers to the temperature of the hottest place of the stator winding. From the installation perspective, it is difficult to place temperature sensors such as NTC or thermocouples at the position corresponding to the hottest point of the stator. The temperature sensor can usually only be placed at the end of the winding, which means that the temperature sensor does not collect the hottest point of the stator winding.

[0004] At present, the collected temperature data is usually corrected by adding a certain compensation value to the temperature data collected by the temperature sensor, so that the corrected temperature data is used as the hottest point temperature. However, this method is very dependent on the accuracy of the temperature sensor measurement value and the compensation value. Traditional temperature sensors usually cannot guarantee stable and accurate temperature measurement. For example, due to the complex oil circuit of the oil-water mixed cooling motor, the temperature sensor is arranged at the end of the winding and is easily sprayed with oil, resulting in too low temperature sensor readings, or the temperature sensor is prone to failure, resulting in inaccurate readings, and the compensation value setting usually cannot be guaranteed to be accurate, which makes the final hottest point temperature inaccurate. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment, medium and vehicle for determining the hottest point temperature of a motor stator, which can improve the problem of inaccurate hottest point temperature of a motor stator.

[0006] In a first aspect, an embodiment of the present application provides a method for determining the hottest point temperature of a motor stator, comprising:

[0007] Obtaining a first parameter set of the motor at time n, a first parameter set at time n-1, a stator temperature at time n, and a stator hottest point temperature at time n-1, wherein the first parameter set includes physical parameters associated with the stator temperature of the motor, and n≥2;

[0008] Based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, determining the characteristic data corresponding to the nth moment, wherein the characteristic data corresponding to the nth moment represents the stator temperature change characteristics at the nth moment relative to the n-1th moment;

[0009] The first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment are concatenated to obtain the target feature vector corresponding to the nth moment;

[0010] The target feature vector corresponding to the nth moment is input into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

[0011] In a second aspect, an embodiment of the present application provides a device for determining the hottest point temperature of a motor stator, comprising:

[0012] An acquisition module, used to acquire a first parameter set of the motor at the nth moment, a first parameter set at the n-1th moment, a first stator temperature at the nth moment, and a first stator hottest point temperature at the n-1th moment, wherein the first parameter set includes physical parameters associated with the stator temperature of the motor, and n≥2;

[0013] A feature extraction module, for determining feature data corresponding to the nth moment based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, wherein the feature data corresponding to the nth moment represents a stator temperature change feature at the nth moment relative to the n-1th moment;

[0014] A splicing module, used for splicing the first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment to obtain a target feature vector corresponding to the nth moment;

[0015] The prediction module is used to input the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0017] When the processor executes the computer program instructions, the method for determining the hottest point temperature of the motor stator according to the first aspect is implemented.

[0018] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method for determining the hottest point temperature of a motor stator as in the first aspect is implemented.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device can execute the method for determining the hottest point temperature of a motor stator as described in the first aspect.

[0020] In a sixth aspect, an embodiment of the present application provides a vehicle, comprising a device for determining the hottest point temperature of a motor stator as shown in the second aspect.

[0021] The method, device, equipment, medium and vehicle for determining the hottest spot temperature of the motor stator of the embodiments of the present application obtain the first parameter set and stator temperature of the motor at the nth moment, and the first parameter set and = stator hottest spot temperature at the n-1th moment, determine the characteristic data corresponding to the nth moment based on the first parameter set and stator temperature at the nth moment and the stator hottest spot temperature at the n-1th moment, the characteristic data corresponding to the nth moment characterizes the stator temperature change characteristics at the nth moment relative to the n-1th moment; concatenate the first parameter set at the nth moment, the first parameter set at the n-1th moment and the characteristic data corresponding to the nth moment to obtain a target characteristic vector corresponding to the nth moment; input the target characteristic vector corresponding to the nth moment into a pre-trained hottest spot temperature prediction model to obtain the stator hottest spot temperature at the nth moment. According to this embodiment, the obtained target characteristic vector can not only characterize the physical parameter change characteristics of the motor between the nth moment and the n-1th moment, but also characterize the stator temperature change characteristics of the motor between the nth moment and the n-1th moment. In this way, the stator hottest point temperature at the nth moment is predicted based on the target characteristic vector, which can effectively improve the accuracy of the stator hottest point temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 It is a flow chart of a method for determining the hottest point temperature of a motor stator provided in an embodiment of the present application;

[0024] Figure 2 It is a flow chart of the hottest point temperature prediction model training method provided in the embodiment of the present application;

[0025] Figure 3It is a flow chart of the method for determining the experimental working condition provided in the embodiment of the present application;

[0026] Figure 4 It is a schematic diagram of the processing flow of the hottest point temperature prediction model for the target feature vector provided in the embodiment of the present application;

[0027] Figure 5 It is a structural schematic diagram of a device for determining the hottest point temperature of a motor stator provided in an embodiment of the present application;

[0028] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0030] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0031] See also Figure 1 , is a flow chart of a method for determining the hottest point temperature of a motor stator provided in an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps: S11-S14.

[0032] S11. Obtain the first parameter set of the motor at the nth moment, the first parameter set at the n-1th moment, the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, the first parameter set including physical parameters associated with the stator temperature of the motor, n≥2.

[0033] In some embodiments of the present application, multiple sampling moments can be set for the motor, and the time corresponding to each sampling moment and the interval between adjacent sampling moments can be set according to actual conditions. Here, the nth moment and the n-1th moment refer to the nth sampling moment and the n-1th sampling moment, respectively, and the n-1th moment is the sampling moment before the nth moment. Wherein, n is a value greater than or equal to 2, that is, the nth moment can be any sampling moment after the first sampling moment.

[0034] The first parameter set of the motor at the nth moment can be obtained from the operating data of the motor at the nth moment. Similarly, the first parameter set of the motor at the n-1th moment can be obtained from the operating data of the motor at the n-1th moment.

[0035] In practical applications, the first parameter set may include physical parameters related to the stator temperature of the motor, which are selected from the physical parameters of the motor by manually analyzing the historical operation data of the motor or based on expert experience. Different types of motors may have different corresponding first parameter sets.

[0036] As an example, in the case where the motor is an oil-water mixed cooling motor, the first parameter set may include but is not limited to: current, water temperature, oil temperature, water flow, oil flow and other physical parameters.

[0037] In this embodiment, the stator temperature at the nth moment is the stator temperature of the motor collected at the nth moment. The stator temperature at the nth moment can be measured by a temperature sensor arranged near the stator of the motor. Because the temperature sensor cannot usually be installed at the hottest point of the stator of the motor, the stator temperature at the nth moment usually has a certain deviation from the stator hottest point temperature of the motor at the nth moment, and is not the accurate stator hottest point temperature.

[0038] In this embodiment, the stator hottest point temperature at the n-1th moment is the determined stator hottest point temperature of the motor at the n-1th moment. Because the motor stator hottest point temperature determination method provided in this embodiment needs to determine the stator hottest point temperature at the current moment based on the relevant data of the current moment and the previous moment, in practical applications, starting from the second moment, the motor stator hottest point temperature determination method provided in this embodiment can be used to determine the stator hottest point temperature of the motor at each moment, and at the first moment, the stator temperature collected by the temperature sensor can be directly used as the stator hottest point temperature, that is, when the n-1th moment is the first moment, the stator temperature collected by the temperature sensor at the first moment is used as the stator hottest point temperature at the n-1th moment, and when the n-1th moment is not the first moment, the stator hottest point temperature at the n-1th moment determined by the motor stator hottest point temperature determination method provided in this embodiment is used as the stator hottest point temperature at the n-1th moment.

[0039] By adopting the above method, the accuracy of the determined stator hottest point temperature can be improved while ensuring that the stator hottest point temperature at each moment can be determined.

[0040] S12. Based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, determine the characteristic data corresponding to the nth moment, the characteristic data corresponding to the nth moment representing the stator temperature change characteristics at the nth moment relative to the n-1th moment.

[0041] Here, the characteristic data corresponding to the nth moment is data that can characterize the characteristic of the stator temperature change at the nth moment relative to the n-1th moment. A characteristic refers to an obvious or unique feature or attribute of an object or individual.

[0042] In some embodiments of the present application, feature extraction can be performed on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment according to preset feature extraction rules, so as to obtain feature data that can characterize the stator temperature change characteristics at the nth moment relative to the n-1th moment, and the feature data is used as the feature data corresponding to the nth moment.

[0043] In some embodiments of the present application, the feature extraction rules can be pre-set according to the characteristics of the motor. Since the first parameter sets of different types of motors are different, the feature extraction rules of different types of motors can also be different. It is sufficient to ensure that feature data that can characterize the stator temperature change characteristics at the nth moment relative to the n-1th moment can be extracted.

[0044] Exemplarily, when the motor is an oil-water mixed cooling motor and the first parameter set includes at least one of phase current, water temperature and oil temperature, the characteristic data at the nth moment can be determined in the following manner:

[0045] Calculate the first difference between the oil temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0046] Calculate the second difference between the water temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0047] Calculating a third difference between the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0048] Calculate the square of the phase current at the nth moment;

[0049] The first difference, the second difference, the third difference and the square of the phase current obtained by the above calculation are determined as the characteristic data corresponding to the nth moment.

[0050] Because the stator temperature is not abrupt, the stator temperature at each moment is usually associated with the stator temperature at the previous moment. Based on this association, the stator hottest point temperature at the current moment can be accurately predicted when the stator hottest point temperature at the previous moment is known. Feature data that can reflect this association can be obtained through feature extraction. In this way, the stator hottest point temperature is calculated based on the feature data, which can improve the accuracy of the stator hottest point temperature finally determined.

[0051] S13. Concatenate the first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment to obtain a target feature vector corresponding to the nth moment.

[0052] In some embodiments of the present application, concatenating the first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment may include:

[0053] The first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data are concatenated according to a preset feature vector structure, so as to obtain a target feature vector corresponding to the nth moment.

[0054] Among them, the feature vector structure can include the position corresponding to the first parameter set at the nth moment, the position corresponding to the first parameter set at the n-1th moment, and the position corresponding to the feature data corresponding to the nth moment. In this way, when data splicing is performed based on the feature vector structure, the corresponding data can be directly added to the corresponding position.

[0055] Exemplarily, the feature vector structure is an array including three sub-arrays, the three sub-arrays are respectively the first sub-array, the second sub-array and the third sub-array, wherein the first sub-array is used to place the first parameter set at the nth moment, the second sub-array is used to place the first parameter set at the n-1th moment, and the third sub-array is used to place the feature data corresponding to the nth moment. Based on this, after obtaining the feature data corresponding to the nth moment, the first parameter set at the nth moment can be placed in the first sub-array, the first parameter set at the n-1th moment can be placed in the second sub-array, and the feature data corresponding to the nth moment can be placed in the third sub-array. In this way, an array including the first parameter set at the nth moment, the first parameter set at the n-1th moment and the feature data corresponding to the nth moment can be obtained, and the array is used as the target feature vector corresponding to the nth moment.

[0056] In an embodiment of the present application, the first parameter set at the nth moment can reflect the stator temperature characteristics of the motor at the nth moment, and the first parameter set and the first stator hottest point temperature at the n-1th moment can reflect the stator temperature characteristics of the motor at the n-1th moment. The feature data extracted based on the above data can characterize the changing characteristics of the stator temperature between the nth moment and the n-1th moment. Based on this, the target feature vector finally spliced ​​together can reflect the multiple characteristics of the motor stator temperature. In this way, the prediction of the stator hottest point temperature of the motor at the nth moment based on multiple characteristics can improve the accuracy of the prediction results.

[0057] S14. Input the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

[0058] Here, the hottest point temperature prediction model is obtained by pre-training the initial model based on multiple groups of sample data. The initial model can be a machine learning model, and the initial model can include but is not limited to a neural network model, a linear regression model, a polynomial regression model, a random forest model, a support vector machine model, etc. Each group of sample data includes a feature vector corresponding to a sample time and the hottest point temperature of the stator. The sample time is the time when the sample is collected.

[0059] In some embodiments of the present application, when training the hottest spot temperature prediction model, the characteristic vector in the sample data can be used as the input value, and the stator hottest spot temperature can be used as the label value of the input value to construct the training data. When the initial model is trained using the training data, a hottest spot temperature prediction model is obtained that takes the characteristic vector of the motor as the input and the stator hottest spot temperature of the motor as the output. Among them, when the initial model is trained using the sample data, the characteristic vector in the sample data is input into the initial model to obtain the stator hottest spot temperature prediction value corresponding to the input characteristic vector output by the initial model. The stator hottest spot temperature in the sample data, i.e., the label value of the input value, is used to determine whether the stator hottest spot temperature prediction value output by the initial model is accurate. The accuracy of the initial model is determined based on the judgment result. When the accuracy of the initial model reaches the preset accuracy requirement, the training can be stopped to obtain the hottest spot temperature prediction model.

[0060] It can be understood that in order to ensure that the stator hottest point temperature of the motor at the nth moment can be predicted based on the target feature vector, the generation method of the feature vector in the sample data is consistent with the generation method of the target feature vector at the nth moment.

[0061] The present embodiment provides a method for determining the hottest-spot temperature of a motor stator, which obtains the first parameter set and stator temperature of the motor at the nth moment, as well as the first parameter set and the hottest-spot temperature of the stator at the n-1th moment, and determines the characteristic data corresponding to the nth moment based on the first parameter set and the stator temperature at the nth moment and the hottest-spot temperature of the stator at the n-1th moment, wherein the characteristic data characterizes the characteristics of the stator temperature change at the nth moment relative to the n-1th moment; concatenates the operating data and the characteristic data at the nth moment and the n-1th moment to obtain a target characteristic vector corresponding to the nth moment; and inputs the target characteristic vector into a pre-trained hottest-spot temperature prediction model to obtain the hottest-spot temperature of the stator at the nth moment. According to the embodiment of the present application, the obtained target characteristic vector can characterize multiple characteristics of the motor stator temperature, so that the prediction of the hottest-spot temperature of the stator at the nth moment based on the target characteristic vector can effectively improve the accuracy of the predicted hottest-spot temperature of the stator.

[0062] In some embodiments, see Figure 2 The training process of the hotspot temperature prediction model may include the following steps S21-S24.

[0063] S21. Determine multiple experimental conditions.

[0064] In some embodiments of the present application, multiple operating conditions can be selected from multiple operating conditions of the motor as experimental conditions according to actual needs. For example, various operating conditions that may occur when the motor is running can be selected as experimental conditions to ensure that the sample data finally obtained can cover various operating conditions when the motor is running.

[0065] S22. Control the sample motor to run for a preset time under each experimental condition, and obtain multiple groups of sample operation data corresponding to multiple experimental conditions. The sample operation data include a first parameter set and a stator hotspot temperature corresponding to each sampling moment within the preset time. The stator hotspot temperature corresponding to each sampling moment is measured by a temperature sensor installed at the hottest position in the sample motor.

[0066] In some embodiments of the present application, in order to ensure that the hottest point temperature prediction model finally trained can predict the hottest point temperature of the stator of the motor in S11, the sample motor used in the experiment is of the same type as the motor in S11. For example, if the motor in S11 is an oil-water mixed cooling motor, the sample motor also uses an oil-water mixed cooling motor.

[0067] In order to obtain the accurate stator hottest point temperature under experimental conditions, the temperature sensor in the sample motor can be set at the hottest point of the stator, so that the accurate stator hottest point temperature can be directly measured by the temperature sensor. The hottest point of the stator is the hottest place in the stator winding, which can be determined according to the motor type and model corresponding to the sample motor.

[0068] The motor model is controlled to run for a preset time under each experimental condition, so that multiple groups of sample operation data of the sample motor under multiple experimental conditions can be obtained. Among them, the length of the preset time can be set according to the actual situation, for example, it can be N minutes. Multiple sampling moments can be set within the preset time. When the sample motor runs under the experimental condition, the operation data of the motor model can be obtained at each sampling moment, and then the first parameter set corresponding to each sampling moment can be obtained from the operation data.

[0069] For example, taking the preset duration as N minutes and each second as a sampling moment as an example, for each experimental condition, N*60 sets of first parameter sets can be obtained, and if there are M experimental conditions, M*N*60 sets of first parameter sets can be obtained in the end. It can be seen that in this way, a large amount of data required for training the model can be quickly obtained.

[0070] In this embodiment, the temperature sensor in the sample motor is set at the hottest position, which ensures that the hottest temperature of the stator obtained based on the experiment is the temperature of the theoretical hottest point, without intermediate errors, and more accurate. In addition, compared with obtaining sample data from the operating data of the actual motor, this method avoids the problem of inaccurate readings due to the physical sensor in the motor being sprayed with oil or failing, further ensuring the accuracy of the data and effectively improving the quality of the sample data.

[0071] S23. Construct multiple sample data based on multiple groups of sample operation data.

[0072] Similar to the method of generating the target feature vector, for each sampling moment under each experimental condition, the feature data corresponding to each sampling moment can be extracted in the same way as the feature data of the nth moment, and then the first parameter set of the sampling moment, the first parameter set of the previous sampling moment, the stator hottest point temperature of the previous sampling moment, and the feature data corresponding to the sampling moment are concatenated together to form the feature vector corresponding to the sampling moment. Then, the feature vector corresponding to the sampling moment is used as the input value, and the stator hottest point temperature collected at the sampling moment is used as the label value of the input value to construct the sample data corresponding to the sampling moment.

[0073] The above process is performed for each sampling moment under each experimental condition to obtain multiple sample data.

[0074] S24. Use multiple sample data to train the preset initial model until the training end condition is met to obtain the hotspot temperature prediction model.

[0075] After obtaining multiple sample data, the initial model can be trained using the multiple sample data.

[0076] When training the initial model, multiple sample data can be divided into a training set and a test set according to a preset division ratio, wherein the sample data in the training set is used to iteratively train the initial model, and the sample data in the test set is used to test the trained initial model.

[0077] After obtaining the training set and the test set, the initial model is trained using the training set and the test set using a conventional supervised training method until the training end condition is met.

[0078] Among them, the training end conditions can be set according to actual conditions, and may include but are not limited to: the accuracy of the model is higher than the set accuracy threshold, the number of iterations of the model training is greater than the set number threshold, etc.

[0079] When the training end condition is met, the training is ended, and the model obtained by the last training is used as the hotspot temperature prediction model.

[0080] Through the above method, a large amount of sample data can be obtained by using the experimental method, which is simple and easy to implement, and the sample data obtained based on the experiment is more accurate.

[0081] In some embodiments, see Figure 3 , determining multiple experimental conditions may include the following steps S31-S34.

[0082] S31. Determine a second parameter set and a value range of each physical parameter in the second parameter set, wherein the second parameter set includes physical parameters related to the operating conditions of the sample motor.

[0083] Here, the physical parameters in the second parameter set can be manually selected from the physical parameters related to the operating conditions of the sample motor according to actual conditions. For example, the second parameter set can include but is not limited to: voltage, power, speed, frequency, etc. The value range of each physical parameter in the second parameter set can be set based on prior knowledge or historical data.

[0084] S32. Generate a multi-dimensional value space based on the value ranges of all physical parameters in the second parameter set.

[0085] In this embodiment, after obtaining the second parameter set and the value range of each physical parameter in the second parameter set, the value range of each physical parameter in the second parameter set can be used as one dimension to establish a multidimensional value space. Each point in the multidimensional value space corresponds to a parameter value group, which includes a parameter value of each physical parameter in the second parameter set, and the parameter value of each physical parameter is within its corresponding value range. One parameter group corresponds to one operating condition. The multidimensional value space contains all possible parameter value groups of the second parameter set within the set value range, that is, the operating conditions.

[0086] S33. Generate multiple operating points that are evenly distributed in the multi-dimensional value space.

[0087] In this embodiment, in the generated multidimensional value space, a fixed number of uniformly distributed operating points are randomly generated to fill the multidimensional value space, and the operating conditions corresponding to the generated operating points are used as experimental conditions, where the number of operating points can be set according to actual conditions.

[0088] The operating points can be generated by uniform distribution, Latin hypercube, Halton sequence and other methods.

[0089] S34. Determine the multiple operating conditions corresponding to the multiple operating points as multiple experimental conditions.

[0090] Through the above method, a plurality of different experimental working conditions can be obtained, and the obtained experimental working conditions can reflect various operating conditions of the motor to the greatest extent.

[0091] In some embodiments, before training the preset initial model using multiple sample data, the following steps may be performed:

[0092] Normalize the feature vectors in each sample data respectively;

[0093] In this way, when a preset initial model is trained using a plurality of sample data, the initial model is trained using the plurality of sample data after normalization.

[0094] When normalizing the feature vector of the sample data, the following steps are performed for each parameter in the feature vector:

[0095] The maximum value and the minimum value of the parameter are determined from multiple feature vectors of multiple sample data, and the two values ​​are saved as normalized parameters of the parameter. The parameter is normalized based on the normalized parameter and normalized formula corresponding to the parameter to obtain the normalized parameter.

[0096] The normalization formula is as follows:

[0097]

[0098] Among them, X nor represents the parameters after normalization, X represents the parameters before normalization, and x min Indicates the minimum value of the parameter, x max Indicates the maximum value of the parameter.

[0099] Accordingly, before inputting the target feature vector into the pre-trained hotspot temperature prediction model, the following steps may also be performed:

[0100] The target feature vector is normalized, and the normalized target feature vector is input into a pre-trained hotspot temperature prediction model.

[0101] The method of normalizing the target feature vector is the same as the method of normalizing the feature vector in the sample data, that is, for each parameter in the target feature vector, the parameter is normalized based on the normalization parameter corresponding to the parameter and the normalization formula to obtain the normalized parameter. The normalization parameter corresponding to the parameter is the normalization parameter used when normalizing the feature vector in the sample data.

[0102] Through normalization, dimensional parameters can be converted into dimensionless scalars, which facilitates subsequent data processing and accelerates model convergence.

[0103] In some embodiments, the hotspot temperature prediction model can be obtained by training an initial model based on a neural network model, a linear regression model, a polynomial regression model, a random forest model, a support vector machine model, or the like.

[0104] As an example, when the hotspot temperature prediction model is based on a neural network model, the neural network model includes an input layer, an output layer, and multiple hidden layers, each layer containing one or more neurons. Usually, the number of neurons in the input layer is the same as the feature dimension of the feature vector input to the model, for example, Figure 4 As shown, the target feature vector input to the model is [x 1 , x 2 , …x n0 ], the target feature vector contains n0 features, that is, the feature dimension of the target feature vector is n0, then the number of neurons in the input layer can be n0. The number of neurons in the output layer is consistent with the dimension of the final output result. In the embodiment of the present application, the model finally only needs to output the value of the hottest temperature of the stator, so the number of neurons in the output layer is 1. The number of layers of the middle hidden layer and the number of neurons in each hidden layer can be set according to the actual situation. Figure 4In the example, only one hidden layer is taken, and the hidden layer contains n neurons.

[0105] The trained hotspot temperature prediction model includes the nonlinear function g(x), coefficient matrix W and bias value b corresponding to each layer of neurons. Among them, the nonlinear function g(x) is also the activation function, which is used to remove the linearization of each neuron output, making the entire neural network model nonlinear. The coefficient matrix W is also the weight matrix, which is used for linear change operations to multiply the input data with the connection weights of the neurons. The bias value b is used as the bias term in the linear change operation to translate the input data.

[0106] During model processing, the output calculation formula for each neuron is:

[0107] f(∑ i ω i x i +b)

[0108] Where f(·) represents the nonlinear function g(x), ω i Represents the feature x in the coefficient matrix W and the input to the neuron i The corresponding weight.

[0109] Based on this, after the target feature vector is input into the hotspot temperature prediction model, each layer except the input layer can be calculated according to the following formula:

[0110] z [L] =W [L] a [L-1] +b [L]

[0111] a [L] =g [L] (z [L] )

[0112] Among them, a [L] is the output of the previous nonlinear function g(x), where the first layer is the input layer, that is, the target feature vector [x 1 , x 2 , …, x n0 ], the last layer is the output layer, which outputs the predicted value of the stator hottest point temperature at the nth moment W [L] and b [L] is the parameter matrix and bias of each layer saved after training, g [L]is a nonlinear function of each layer. As another example, when the hotspot temperature prediction model is trained based on a linear regression model, the hotspot temperature prediction model includes the trained coefficient vector a and intercept b. Based on this, after the target feature vector is input into the hotspot temperature prediction model, the model can substitute the target feature vector into the following formula for calculation layer by layer, and finally output the predicted value of the stator hotspot temperature at the nth moment:

[0113]

[0114] In the formula, represents the predicted value of the stator hottest point temperature at the nth moment, X nor represents the target feature vector.

[0115] The processing process of the target feature vector for the hottest point temperature prediction model constructed with other models as initial models is the conventional processing flow corresponding to the initial model, which will not be listed here one by one.

[0116] Based on the method for determining the hottest point temperature of a motor stator provided in the above embodiment, the present application also provides a specific implementation of a device for determining the hottest point temperature of a motor stator. Please refer to the following embodiment.

[0117] See also Figure 5 The device for determining the hottest point temperature of a motor stator provided in the embodiment of the present application includes the following modules:

[0118] An acquisition module 501 is used to acquire a first parameter set of the motor at the nth moment, a first parameter set at the n-1th moment, a stator temperature at the nth moment, and a stator hottest point temperature at the n-1th moment, wherein the first parameter set includes physical parameters associated with the stator temperature of the motor, and n≥2;

[0119] A feature extraction module 502 is used to determine feature data corresponding to the nth moment based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, wherein the feature data corresponding to the nth moment represents a stator temperature change feature at the nth moment relative to the n-1th moment;

[0120] A concatenation module 503 is used to concatenate the first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment to obtain a target feature vector corresponding to the nth moment;

[0121] The prediction module 504 is used to input the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

[0122] The present embodiment provides a device for determining the hottest spot temperature of a motor stator, which obtains the first parameter set and stator temperature of the motor at the nth moment, the first parameter set and the hottest spot temperature of the stator at the n-1th moment, and determines the characteristic data corresponding to the nth moment based on the first parameter set and the stator temperature at the nth moment and the hottest spot temperature of the stator at the n-1th moment, wherein the characteristic data corresponding to the nth moment represents the stator temperature change characteristics at the nth moment relative to the n-1th moment; the first parameter set at the nth moment, the first parameter set at the n-1th moment and the characteristic data corresponding to the nth moment are spliced ​​to obtain the target characteristic vector corresponding to the nth moment; the target characteristic vector is input into a pre-trained hottest spot temperature prediction model to obtain the stator hottest spot temperature at the nth moment. According to the present embodiment, the obtained target characteristic vector can represent both the physical parameter change characteristics of the motor between the nth moment and the n-1th moment, and the stator temperature change characteristics of the motor between the nth moment and the n-1th moment, so that the stator hottest spot temperature at the nth moment is predicted based on the target characteristic vector, which can effectively improve the accuracy of the stator hottest spot temperature.

[0123] In some embodiments, the apparatus may further include: a model training module, including:

[0124] A working condition determination submodule is used to determine multiple experimental working conditions;

[0125] The experimental submodule is used to control the sample motor to run for a preset time under each experimental condition, and obtain multiple groups of sample operation data corresponding to multiple experimental conditions, wherein the sample operation data includes a first parameter set and a stator hottest point temperature corresponding to each sampling moment within the preset time, and the stator hottest point temperature corresponding to each sampling moment is measured by a temperature sensor installed at the hottest point position in the sample motor;

[0126] A data construction submodule, used for constructing multiple sample data based on multiple groups of sample running data;

[0127] The training submodule is used to train the preset initial model using multiple sample data until the training end conditions are met to obtain the hottest point temperature prediction model.

[0128] In some embodiments, the operating condition determination submodule is used to:

[0129] Determining a plurality of second parameter sets and a value range of each physical parameter in the second parameter set, wherein the second parameter set includes physical parameters related to the operating condition of the sample motor;

[0130] Generate a multidimensional value space based on the value ranges of all physical parameters in the second parameter set;

[0131] Generate multiple operating points evenly distributed in a multi-dimensional value space;

[0132] The multiple operating conditions corresponding to the multiple operating points are determined as multiple experimental conditions.

[0133] In some embodiments, the model training module may further include:

[0134] A normalization submodule, used for normalizing the feature vectors in each sample data before training the preset initial model with multiple sample data;

[0135] Accordingly, the training submodule is used to:

[0136] The preset initial model is trained using multiple sample data after normalization.

[0137] In some embodiments, the apparatus may further include:

[0138] A normalization module, used for normalizing the target feature vector before inputting the target feature vector into the pre-trained hotspot temperature prediction model;

[0139] Accordingly, the prediction module 504 is used to:

[0140] The normalized target feature vector is input into the pre-trained hotspot temperature prediction model.

[0141] In some embodiments, the motor is an oil-water mixed cooling motor, and the first parameter set includes at least one of the following physical parameters: phase current, water temperature, and oil temperature. The characteristic data corresponding to the nth moment includes at least one of the following:

[0142] The first difference between the oil temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0143] The second difference between the water temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0144] A third difference between the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment;

[0145] The square of the phase current at the nth moment.

[0146] The device for determining the hottest point temperature of a motor stator provided in the embodiment of the present application can achieve Figures 1 to 4 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0147] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0148] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0149] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0150] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 602 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory. The memory 602 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Therefore, generally, the memory 602 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it may perform the operations described in any one of the above-mentioned embodiments of the method for determining the hottest temperature of the motor stator.

[0151] The processor 601 reads and executes the computer program instructions stored in the memory 602 to implement any one of the methods for determining the hottest point temperature of the motor stator in the above embodiments.

[0152] In one example, the electronic device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0153] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0154] The bus 610 includes hardware, software, or both, and couples the components of the online data flow metering device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 610 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0155] In addition, in combination with the method for determining the hottest spot temperature of the motor stator in the above embodiments, an embodiment of the present application can provide a computer storage medium to implement. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the methods for determining the hottest spot temperature of the motor stator in the above embodiments is implemented.

[0156] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0157] The functional blocks shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. A "machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0158] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0159] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0160] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining the hottest point temperature of a motor stator, It is characterized in that include: Acquire a first parameter set of the motor at the nth moment, a first parameter set at the n-1th moment, a stator temperature at the nth moment, and a stator hottest point temperature at the n-1th moment, wherein the first parameter set includes physical parameters associated with the stator temperature of the motor, and n≥2; Determine, based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, characteristic data corresponding to the nth moment, wherein the characteristic data corresponding to the nth moment represents a stator temperature change characteristic at the nth moment relative to the n-1th moment; The first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment are concatenated to obtain a target feature vector corresponding to the nth moment; The target feature vector corresponding to the nth moment is input into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each of the sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

2. The method according to claim 1, It is characterized in that The training of the hottest point temperature prediction model includes: Determine multiple experimental conditions; Controlling the sample motor to run for a preset time under each experimental condition, respectively, to obtain multiple groups of sample operation data corresponding to the multiple experimental conditions, wherein the sample operation data includes a first parameter set and a stator hottest point temperature corresponding to each sampling moment within the preset time, wherein the stator hottest point temperature corresponding to each sampling moment is measured by a temperature sensor installed at the hottest point position in the sample motor; constructing a plurality of sample data based on the plurality of sets of sample operation data; The preset initial model is trained using the multiple sample data until the training end condition is met to obtain the hottest point temperature prediction model.

3. The method according to claim 2, It is characterized in that Determining multiple experimental conditions includes: Determining a second parameter set and a value range of each physical parameter in the second parameter set, wherein the second parameter set includes physical parameters related to the operating condition of the sample motor; Generate a multidimensional value space based on the value ranges of all physical parameters in the second parameter set; Generating a plurality of operating points evenly distributed in the multidimensional value space; The multiple operating conditions corresponding to the multiple operating points are determined as multiple experimental conditions.

4. The method according to claim 2, It is characterized in that Before using the plurality of sample data to train the preset initial model, the method further includes: Normalize the feature vectors in each sample data respectively; The using the plurality of sample data to train a preset initial model comprises: The preset initial model is trained using the normalized multiple sample data.

5. The method according to claim 2, It is characterized in that Before inputting the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model, the method further includes: Normalizing the target feature vector corresponding to the n-th moment; The step of inputting the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model comprises: The normalized target feature vector corresponding to the nth moment is input into a pre-trained hotspot temperature prediction model.

6. The method according to any one of claims 1 to 5, It is characterized in that The motor is an oil-water mixed cooling motor, and the first parameter set includes at least one of the following physical parameters: phase current, water temperature, and oil temperature; the characteristic data corresponding to the nth moment includes at least one of the following: A first difference between the oil temperature at the nth moment and the stator hottest point temperature at the n-1th moment; a second difference between the water temperature at the nth moment and the stator hottest point temperature at the n-1th moment; a third difference between the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment; The square of the phase current at the nth moment.

7. A device for determining the hottest point temperature of a motor stator, It is characterized in that include: An acquisition module, used to acquire a first parameter set of the motor at the nth moment, a first parameter set at the n-1th moment, a stator temperature at the nth moment, and a stator hottest point temperature at the n-1th moment, wherein the first parameter set includes physical parameters associated with the stator temperature of the motor, and n≥2; A feature extraction module, for determining feature data corresponding to the nth moment based on the first parameter set and the stator temperature at the nth moment and the stator hottest point temperature at the n-1th moment, wherein the feature data corresponding to the nth moment represents a stator temperature change feature at the nth moment relative to the n-1th moment; A splicing module, used for splicing the first parameter set at the nth moment, the first parameter set at the n-1th moment, and the feature data corresponding to the nth moment to obtain a target feature vector corresponding to the nth moment; A prediction module is used to input the target feature vector corresponding to the nth moment into a pre-trained hotspot temperature prediction model to obtain the stator hotspot temperature at the nth moment. The hotspot temperature prediction model is trained based on multiple sample data, and each of the sample data includes a feature vector corresponding to a sample moment and the stator hotspot temperature.

8. An electronic device, It is characterized in that The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the hottest point temperature of the motor stator according to any one of claims 1 to 6 is implemented.

9. A computer storage medium, It is characterized in that The computer storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the method for determining the hottest point temperature of the motor stator according to any one of claims 1 to 6 is implemented.

10. A vehicle, It is characterized in that The invention comprises the device for determining the hottest point temperature of the motor stator as shown in claim 7.

Images