Motor temperature rise evaluation method, device, equipment and medium

Abstract

The invention discloses a motor temperature rise evaluation method, device and equipment and a medium. The invention relates to the technical field of motors, and the method comprises the steps: obtaining an electromagnetic parameter of a motor, and carrying out the preprocessing of the electromagnetic parameter, and obtaining an input electromagnetic parameter; the input electromagnetic parameters are input into a temperature rise evaluation model for temperature rise evaluation to obtain a temperature rise evaluation result, and the temperature rise evaluation model is obtained by training and testing a constructed multi-attention mechanism convolution model through a temperature rise data set. According to the method, the problem that the temperature rise evaluation process seriously depends on experience and knowledge of motor designers during existing motor design is effectively solved, and the accuracy of temperature rise evaluation is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of motor technology, and in particular to a method, device, equipment, and medium for evaluating motor temperature rise. Background Art

[0002] Permanent magnet synchronous motors (PMSMs) are widely used in various fields, such as industrial automation and electric vehicles. When designing the electromagnetic scheme for a PMSM, temperature rise is a key parameter for evaluating the rationality of the electromagnetic design. Proper temperature rise assessment ensures efficient, safe, and reliable operation of the motor, extending its service life.

[0003] Current research on motor temperature rise primarily focuses on predicting motor temperature rise during actual operation to identify motor status trends and develop predictive maintenance plans in advance. However, limited research exists on evaluating motor temperature rise during electromagnetic scheme design. This primarily relies on motor designers' experience to estimate the potential temperature rise under different electromagnetic schemes. This requires a high level of expertise and practical experience from motor designers, and cannot guarantee the accuracy of temperature rise assessment results. Inaccurate temperature rise assessments can lead to inappropriate motor designs, resulting in wasted labor and production costs. Summary of the Invention

[0004] Embodiments of the present invention provide a method, apparatus, device, and medium for evaluating motor temperature rise, aiming to solve the problem of low accuracy in existing motor temperature rise evaluation.

[0005] In a first aspect, an embodiment of the present invention provides a method for evaluating motor temperature rise, comprising:

[0006] Acquiring electromagnetic parameters of the motor and preprocessing the electromagnetic parameters to obtain input electromagnetic parameters;

[0007] The input electromagnetic parameters are input into a temperature rise assessment model to perform temperature rise assessment to obtain a temperature rise assessment result, wherein the temperature rise assessment model is obtained by training and testing a constructed multi-attention mechanism convolution model using a temperature rise dataset.

[0008] In a second aspect, an embodiment of the present invention further provides a motor temperature rise assessment device, comprising:

[0009] an acquisition processing unit, configured to acquire electromagnetic parameters of the motor and preprocess the electromagnetic parameters to obtain input electromagnetic parameters;

[0010] A temperature rise assessment unit is used to input the input electromagnetic parameters into a temperature rise assessment model to perform temperature rise assessment and obtain a temperature rise assessment result, wherein the temperature rise assessment model is obtained by training and testing a multi-attention mechanism convolution model constructed using a temperature rise dataset.

[0011] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0012] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0013] Embodiments of the present invention provide a method, apparatus, device, and medium for assessing motor temperature rise. The method includes: obtaining electromagnetic parameters of the motor and preprocessing the electromagnetic parameters to obtain input electromagnetic parameters; and inputting the input electromagnetic parameters into a temperature rise assessment model to perform temperature rise assessment and obtain a temperature rise assessment result. The temperature rise assessment model is obtained by training and testing a multi-attention mechanism convolutional model constructed using a temperature rise dataset. The technical solution of the embodiments of the present invention, which preprocesses the electromagnetic parameters of the motor to obtain input electromagnetic parameters and then inputs the electromagnetic parameters into the temperature rise assessment model to perform temperature rise assessment and obtain a temperature rise assessment result, effectively addresses the problem of the existing temperature rise assessment process in motor design being heavily dependent on the experience and knowledge of the motor designer, thereby improving the accuracy of the temperature rise assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A schematic flow chart of a method for evaluating motor temperature rise provided by one embodiment of the present invention;

[0016] Figure 2 A schematic diagram of a multi-attention mechanism convolutional model provided by an embodiment of the present invention;

[0017] Figure 3 A schematic diagram of a sub-process of a method for evaluating motor temperature rise provided by an embodiment of the present invention;

[0018] Figure 4 A schematic diagram of another sub-process of a method for evaluating motor temperature rise provided by an embodiment of the present invention;

[0019] Figure 5 A schematic diagram of another sub-process of a method for evaluating motor temperature rise provided by an embodiment of the present invention;

[0020] Figure 6 A simplified flow chart of a method for evaluating motor temperature rise provided by an embodiment of the present invention;

[0021] Figure 7 A schematic block diagram of a motor temperature rise assessment device provided by an embodiment of the present invention;

[0022] Figure 8 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0025] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0026] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0027] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0028] See also Figure 1 , Figure 1FIG. 1 is a flow chart of a method for evaluating motor temperature rise according to an embodiment of the present invention. The method for evaluating motor temperature rise is described in detail below. Figure 1 As shown, the method includes the following steps S110-S120.

[0029] S110 , acquiring electromagnetic parameters of the motor, and preprocessing the electromagnetic parameters to obtain input electromagnetic parameters.

[0030] In an embodiment of the present invention, the electromagnetic parameters include basic information of the stator and the motor itself, such as stack height, wire diameter, number of turns and other parameters, and each parameter represents a channel. The electromagnetic parameters of the motor are obtained, and the electromagnetic parameters are preprocessed to obtain input electromagnetic parameters. Specifically, the electromagnetic parameters are encoded to obtain encoded electromagnetic parameters; the encoded electromagnetic parameters are normalized to obtain the input electromagnetic parameters. It should be noted that, in this embodiment, the input electromagnetic parameters are multi-channel data, for example Understandably, each parameter x i , i = 1, ..., n corresponds to an independent channel, where n represents the number of electromagnetic parameters. Encoding the electromagnetic parameters is intended to make the network more efficient when performing matrix operations. The essence of encoding is binary encoding of the parameters. It should also be noted that in this embodiment, to eliminate the impact of dimensional differences in parameters on the model's temperature rise assessment, the input electromagnetic parameters were normalized using the Min-Max normalization method to limit the data range to [0, 1].

[0031] S120. Input the input electromagnetic parameters into a temperature rise assessment model to perform temperature rise assessment to obtain a temperature rise assessment result, wherein the temperature rise assessment model is obtained by training and testing a constructed multi-attention mechanism convolution model using a temperature rise dataset.

[0032] In the embodiment of the present invention, Figure 2 As shown in , the multi-attention mechanism convolution model includes a feature extraction module, an attention module and an output module, as shown in Figure 3As shown, step S120 may specifically include steps S121-S122: S121, processing the input electromagnetic parameters through the feature extraction module and the attention module to obtain temperature rise assessment features; S122, inputting the temperature rise assessment features into the output module for flattening to obtain flattened temperature rise features, and outputting the flattened temperature rise features to the fully connected layer in the output module to obtain the temperature rise assessment results. It should be noted that, in this embodiment, the flattening process refers to converting the three-dimensional temperature rise assessment features into two-dimensional flattened temperature rise features in sequence. It should also be noted that, in this embodiment, the motor temperature rise is the comprehensive result of motor loss and heat dissipation, and there is a clear nonlinear mapping relationship between the electromagnetic parameters and the motor temperature rise. By extracting features from the input electromagnetic parameters through the temperature rise assessment model and mapping them to a high-dimensional nonlinear space, this nonlinear mapping relationship can be captured, thereby obtaining a temperature rise assessment result.

[0033] Furthermore, in this embodiment, Figure 4 As shown, step S121 may specifically include steps S1211-S1216:

[0034] S1211, inputting the input electromagnetic parameters into the first convolutional layer, the second convolutional layer, and the pooling layer to obtain a high-dimensional abstract feature, and applying the channel attention module to each channel feature of the high-dimensional abstract feature;

[0035] S1212, performing average pooling compression on the high-dimensional abstract features to obtain global compressed features of each channel;

[0036] S1213. Calculate a query vector and a key vector for each channel according to the global compression feature, and calculate a channel attention coefficient according to the query vector and the key vector;

[0037] S1214. Calculate an initial temperature rise feature based on the channel attention coefficient and the high-dimensional abstract feature;

[0038] S1215. Perform a convolution operation on the initial temperature rise feature through the third convolution layer to obtain a target temperature rise feature;

[0039] S1216. Calculate the temperature rise assessment feature based on the spatial attention module and the target temperature rise feature.

[0040] In an embodiment of the present invention, Figure 2 As shown, the feature extraction module includes a convolution layer and a pooling layer, and the convolution layer includes a first convolution layer Conv _ 1. The second convolutional layer Conv _ 2 and the third convolutional layer Conv _ 3. The pooling layer includes the first pooling layer Pool_ 1 and the second pooling layer Pool _ 2. The attention module includes a channel attention module and a spatial attention module. The input electromagnetic parameters are sequentially input into the first convolutional layer Conv _ 1. The first pooling layer Pool _ 1. The second convolutional layer Conv _ 2 and the second pooling layer Pool _ 2. After obtaining the high-dimensional abstract feature, the channel attention module is applied to each channel feature of the high-dimensional abstract feature to dynamically focus on each channel feature in the channel dimension. It should be noted that, in this embodiment, the step of calculating the temperature rise evaluation feature based on the spatial attention module and the target temperature rise feature includes: randomly generating the query matrix, key matrix and value matrix of the spatial attention module; calculating the temperature rise evaluation feature according to the query matrix, the key matrix, the value matrix, the dimension of the key matrix and the target temperature rise feature. It should also be noted that, in this embodiment, the convolution kernels of the first convolution layer, the second convolution layer and the third convolution layer are different, but they are all depth-separable convolutions to extract multi-scale feature information; and the first pooling layer and the second pooling layer use maximum pooling operations to effectively reduce computational complexity and extract key features.

[0041] For ease of understanding, the specific implementation process of steps S1211-S1216 is introduced as follows: The high-dimensional abstract feature is represented as F i , for F i The average pooling compression is performed on each channel to obtain the global compression feature f of each channel c , based on f c Calculate the query vector q = f for each channel c ×W q , key vector k = f c ×W k , where W q Represents the query vector weight parameter, W k Represents the key vector weight parameter, and the channel attention coefficient Attention(q,k) is calculated by formula (1):

[0042]

[0043] In formula (1), d k represents the dimension of the key vector, and F(·) represents the average pooling operation, which is performed only at the channel level.

[0044] According to Attention(q,k) i Each channel is dynamically weighted to calculate the weighted initial temperature rise characteristic FW , as shown in formula (2), in formula (2), Stands for element-wise dot product.

[0045]

[0046] like Figure 4 As shown, through the third convolutional layer Conv _ 3 pairs of F W Perform convolution operation to obtain the target temperature rise feature F C , according to the spatial attention module, F is calculated by formula (3) C Perform adaptive weighted calculation in spatial dimension to obtain temperature rise assessment feature F W ′:

[0047]

[0048] In formula (3), W Q represents the query matrix of the spatial attention module, W K represents the key matrix of the spatial attention module, W V Represents the value matrix of the spatial attention module, d K Indicates the dimensions of the bond matrix.

[0049] Through the output module F W ′ is flattened and the temperature rise evaluation result of the output motor is obtained through the fully connected layer.

[0050] Furthermore, in this embodiment, if Figure 5As shown, the steps of training and testing the constructed multi-attention mechanism convolution model using the temperature rise dataset to obtain the temperature rise evaluation model include steps S131-S135: S131, dividing the temperature rise dataset into a training dataset and a test dataset according to a preset ratio; S132, inputting the training dataset into the constructed multi-attention mechanism convolution model for training until the preset training end condition is met; S133, inputting the test dataset into the trained multi-attention mechanism convolution model to obtain a predicted temperature rise result; S134, calculating the mean absolute error and the mean square error based on the predicted temperature rise result and the actual temperature rise result in the test dataset; S135, if the mean absolute error is less than the preset mean absolute error and the mean square error is less than the preset mean square error, then the trained multi-attention mechanism convolution model is used as the temperature rise evaluation model. It should be noted that in this embodiment, the preset ratio is 4:1. In other embodiments, the preset ratio can also be divided according to actual needs, for example, 7:3. It should also be noted that, in this embodiment, in order to verify the prediction accuracy and generalization ability of the model, the performance of the model in the temperature rise prediction task is objectively evaluated by using the two indicators of mean absolute error and mean square error to verify its practical application value.

[0051] Furthermore, in this embodiment, the step of inputting the training data set into the constructed multi-attention mechanism convolution model for training until the preset training end condition is met includes: inputting the training data set into the constructed multi-attention mechanism convolution model to output the training predicted temperature rise result; calculating the loss value through the cross-loss function based on the training predicted temperature rise result and the training actual temperature rise result in the training data set; iteratively training the multi-attention mechanism convolution model based on the loss value until the preset training end condition is met. It should be noted that, in this embodiment, the preset training end condition can be reaching the preset number of training times. The cross-loss function is shown in formula (4). In formula (4), y i,ass Indicates the training prediction temperature rise result, y i,tru Represents the actual temperature rise result of the training, i represents the sample number of the training set, and N represents the number of samples in the training set. It should also be noted that in this embodiment, the ReLU activation function is used in the model, and its nonlinear characteristics help to improve the expressive ability of the model. The optimizer selects the Momentum optimization algorithm, the momentum coefficient is set to 0.9, the initial value of the learning rate is set to 0.001, and the learning rate decay strategy is adopted to improve the convergence speed and optimization effect. During the entire training process of the model, a batch processing method is adopted, the batch size is set to 128, the number of training iterations is 1000 times, and the early stopping strategy is adopted to prevent overfitting.

[0052]

[0053] See also Figure 6 , Figure 6 A flow chart of a method for evaluating motor temperature rise provided by an embodiment of the present invention is shown in FIG. Figure 6 In the process, the electromagnetic parameters of the motor are obtained, and the electromagnetic parameters are feature encoded and normalized to obtain the input electromagnetic parameters. According to the collected temperature rise data set, the constructed multi-attention mechanism convolution model is iteratively optimized, trained and tested to obtain the temperature rise evaluation model. The input electromagnetic parameters are input into the temperature rise evaluation model to perform temperature rise evaluation and obtain the temperature rise evaluation results.

[0054] To sum up, in this embodiment, the electromagnetic parameters of the motor are preprocessed to obtain input electromagnetic parameters, and the electromagnetic parameters are input into the temperature rise assessment model to fully explore the features of the electromagnetic parameters related to the temperature rise of the motor, construct a feature space, introduce an attention mechanism in the feature space, and dynamically focus on key features to obtain temperature rise assessment results. This effectively solves the problem that the temperature rise assessment process in existing motor design is heavily dependent on the experience and knowledge of motor designers, improves the accuracy of temperature rise assessment, avoids unreasonable motor design caused by inaccurate temperature rise assessment, and saves labor and production costs to a certain extent.

[0055] Figure 7 FIG. 2 is a schematic block diagram of a motor temperature rise evaluation device 200 provided by an embodiment of the present invention. Figure 7 As shown, corresponding to the above motor temperature rise evaluation method, the present invention also provides a motor temperature rise evaluation device 200. The motor temperature rise evaluation device 200 includes a unit for executing the above motor temperature rise evaluation method, and the device can be configured in a computer device. Specifically, please refer to Figure 7 The motor temperature rise assessment device 200 includes an acquisition processing unit 201 and a temperature rise assessment unit 202 .

[0056] In which, the acquisition processing unit 201 is used to acquire the electromagnetic parameters of the motor and preprocess the electromagnetic parameters to obtain input electromagnetic parameters; the temperature rise evaluation unit 202 is used to input the input electromagnetic parameters into the temperature rise evaluation model to perform temperature rise evaluation to obtain a temperature rise evaluation result, wherein the temperature rise evaluation model is obtained by training and testing the constructed multi-attention mechanism convolution model using the temperature rise dataset. Specifically, the step of training and testing the constructed multi-attention mechanism convolution model using the temperature rise dataset to obtain the temperature rise evaluation model includes: dividing the temperature rise dataset into a training dataset and a test dataset according to a preset ratio; inputting the training dataset into the constructed multi-attention mechanism convolution model for training until a preset training end condition is met; inputting the test dataset into the trained multi-attention mechanism convolution model to obtain a predicted temperature rise result; calculating the mean absolute error and the mean square error based on the predicted temperature rise result and the actual temperature rise result in the test dataset; if the mean absolute error is less than the preset mean absolute error and the mean square error is less than the preset mean square error, the trained multi-attention mechanism convolution model is used as the temperature rise evaluation model. More specifically, the step of inputting the training data set into the constructed multi-attention mechanism convolution model for training until the preset training end condition is met includes: inputting the training data set into the constructed multi-attention mechanism convolution model to output the training predicted temperature rise result; calculating the loss value through the cross loss function based on the training predicted temperature rise result and the training actual temperature rise result in the training data set; iteratively training the multi-attention mechanism convolution model according to the loss value until the preset training end condition is met.

[0057] In some embodiments, such as this embodiment, the acquisition processing unit 201 includes a first processing unit and a second processing unit.

[0058] The first processing unit is used to encode the electromagnetic parameters to obtain encoded electromagnetic parameters; and the second processing unit is used to normalize the encoded electromagnetic parameters to obtain the input electromagnetic parameters.

[0059] In some embodiments, such as this embodiment, the temperature rise evaluation unit 202 includes a third processing unit and a flattening output unit.

[0060] Among them, the third processing unit is used to process the input electromagnetic parameters through the feature extraction module and the attention module to obtain the temperature rise assessment feature; the flattened output unit is used to input the temperature rise assessment feature into the output module for flattening to obtain the flattened temperature rise feature, and output the flattened temperature rise feature to the fully connected layer in the output module to obtain the temperature rise assessment result.

[0061] In some embodiments, such as this embodiment, the third processing unit includes an input unit, a pooling compression unit, a first computing unit, a second computing unit, a third computing unit, and a fourth computing unit.

[0062] Among them, the input unit is used to input the input electromagnetic parameters into the first convolution layer, the second convolution layer and the pooling layer to obtain high-dimensional abstract features, and apply the channel attention module to each channel feature of the high-dimensional abstract features; the pooling compression unit is used to perform average pooling compression on the high-dimensional abstract features to obtain global compression features of each channel; the first calculation unit is used to calculate the query vector and key vector of each channel based on the global compression features, and calculate the channel attention coefficient based on the query vector and the key vector; the second calculation unit is used to calculate the initial temperature rise feature based on the channel attention coefficient and the high-dimensional abstract feature; the third calculation unit is used to perform a convolution operation on the initial temperature rise feature through the third convolution layer to obtain a target temperature rise feature; the fourth calculation unit is used to calculate the temperature rise evaluation feature based on the spatial attention module and the target temperature rise feature.

[0063] In some embodiments, such as this embodiment, the fourth computing unit includes a generating unit and a fifth computing unit.

[0064] Among them, the generation unit is used to randomly generate the query matrix, key matrix and value matrix of the spatial attention module; the fifth calculation unit is used to calculate the temperature rise evaluation feature based on the query matrix, the key matrix, the value matrix, the dimension of the key matrix and the target temperature rise feature.

[0065] The above-mentioned motor temperature rise evaluation device can be implemented in the form of a computer program. The computer program can be used in Figure 8 Runs on the computer device shown.

[0066] See also Figure 8 , Figure 8 3 is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device 300 is a device with a motor temperature rise assessment function.

[0067] See Figure 8 The computer device 300 includes a processor 302 , a memory, and a network interface 305 connected via a system bus 301 , wherein the memory may include a non-volatile storage medium 303 and an internal memory 304 .

[0068] The non-volatile storage medium 303 may store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, the processor 302 may execute a method for evaluating motor temperature rise.

[0069] The processor 302 is used to provide computing and control capabilities to support the operation of the entire computer device 300.

[0070] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303 . When the computer program 3032 is executed by the processor 302 , the processor 302 can execute a motor temperature rise assessment method.

[0071] The network interface 305 is used to communicate with other devices through the network. Figure 8 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 300 to which the solution of the present invention is applied. The specific computer device 300 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0072] The processor 302 is configured to run a computer program 3032 stored in a memory to implement any embodiment of the motor temperature rise assessment method.

[0073] It should be understood that in the embodiment of the present invention, the processor 302 may be a central processing unit (CPU), and the processor 302 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0074] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0075] Therefore, the present invention further provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to execute any embodiment of the motor temperature rise assessment method described above.

[0076] The storage medium may be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0077] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0078] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0079] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0080] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the portion 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 a number of instructions for causing a computer device to execute all or part of the steps of the method described in various embodiments of the present invention.

[0081] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, to the extent such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to encompass such changes and modifications.

[0083] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for evaluating motor temperature rise, characterized in that: include: Acquiring electromagnetic parameters of the motor and preprocessing the electromagnetic parameters to obtain input electromagnetic parameters; The input electromagnetic parameters are input into a temperature rise assessment model to perform temperature rise assessment to obtain a temperature rise assessment result, wherein the temperature rise assessment model is obtained by training and testing a constructed multi-attention mechanism convolution model using a temperature rise dataset.

2. The method according to claim 1, characterized in that The step of preprocessing the electromagnetic parameters to obtain input electromagnetic parameters includes: encoding the electromagnetic parameters to obtain encoded electromagnetic parameters; The encoded electromagnetic parameters are normalized to obtain the input electromagnetic parameters.

3. The method according to claim 2, characterized in that The multi-attention mechanism convolution model includes a feature extraction module, an attention module, and an output module. The step of inputting the input electromagnetic parameters into the temperature rise assessment model to perform temperature rise assessment to obtain a temperature rise assessment result includes: Processing the input electromagnetic parameters by the feature extraction module and the attention module to obtain temperature rise assessment features; The temperature rise assessment feature is input into the output module for flattening to obtain a flattened temperature rise feature, and the flattened temperature rise feature is output to a fully connected layer in the output module to obtain the temperature rise assessment result.

4. The method according to claim 3, characterized in that The feature extraction module includes a convolution layer and a pooling layer, the convolution layer includes a first convolution layer, a second convolution layer, and a third convolution layer, the attention module includes a channel attention module and a spatial attention module, and the step of processing the input electromagnetic parameters by the feature extraction module and the attention module to obtain the temperature rise assessment feature includes: Inputting the input electromagnetic parameters into the first convolution layer, the second convolution layer, and the pooling layer to obtain a high-dimensional abstract feature, and applying the channel attention module to each channel feature of the high-dimensional abstract feature; Performing average pooling compression on the high-dimensional abstract features to obtain global compressed features of each channel; Calculating a query vector and a key vector for each channel according to the global compression feature, and calculating a channel attention coefficient according to the query vector and the key vector; Calculating an initial temperature rise feature according to the channel attention coefficient and the high-dimensional abstract feature; Performing a convolution operation on the initial temperature rise feature through the third convolution layer to obtain a target temperature rise feature; The temperature rise assessment feature is calculated based on the spatial attention module and the target temperature rise feature.

5. The method according to claim 4, characterized in that The step of calculating the temperature rise assessment feature according to the spatial attention module and the target temperature rise feature comprises: Randomly generate a query matrix, a key matrix, and a value matrix for the spatial attention module; The temperature rise assessment feature is calculated according to the query matrix, the key matrix, the value matrix, the dimension of the key matrix, and the target temperature rise feature.

6. The method according to any one of claims 1 to 5, characterized in that The steps of training and testing the constructed multi-attention mechanism convolutional model using the temperature rise dataset to obtain the temperature rise evaluation model include: Dividing the temperature rise data set into a training data set and a test data set according to a preset ratio; Inputting the training data set into the constructed multi-attention mechanism convolutional model for training until a preset training end condition is met; Inputting the test data set into the trained multi-attention mechanism convolutional model to obtain a predicted temperature rise result; Calculate the mean absolute error and the mean square error based on the predicted temperature rise result and the actual temperature rise result in the test data set; If the mean absolute error is less than the preset mean absolute error and the mean square error is less than the preset mean square error, the trained multi-attention mechanism convolution model is used as the temperature rise evaluation model.

7. The method according to claim 6, characterized in that The step of inputting the training data set into the constructed multi-attention mechanism convolutional model for training until a preset training end condition is met includes: Inputting the training data set into the constructed multi-attention mechanism convolutional model to output the training predicted temperature rise result; Calculating a loss value using a cross-loss function based on the training predicted temperature rise result and the training actual temperature rise result in the training data set; The multi-attention mechanism convolution model is iteratively trained according to the loss value until the preset training end condition is met.

8. A motor temperature rise assessment device, characterized in that: include: an acquisition processing unit, configured to acquire electromagnetic parameters of the motor and preprocess the electromagnetic parameters to obtain input electromagnetic parameters; A temperature rise assessment unit is used to input the input electromagnetic parameters into a temperature rise assessment model to perform temperature rise assessment and obtain a temperature rise assessment result, wherein the temperature rise assessment model is obtained by training and testing a multi-attention mechanism convolution model constructed using a temperature rise dataset.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the computer program can implement the method according to any one of claims 1 to 7.

Images