Bearing fault detection model training method and bearing fault detection method

Abstract

The invention provides a training method of a bearing fault detection model and a bearing fault detection method, and the training method of the bearing fault detection model comprises the steps: obtaining corresponding sample data of a rolling bearing under different actual working conditions; obtaining a one-dimensional sample data vector based on the sample data; inputting the one-dimensional sample data vector into a bearing fault detection model; processing the one-dimensional sample data vector based on a convolution unit and a pooling unit to obtain a multi-dimensional sample data vector; performing feature extraction on the multi-dimensional sample data vector based on a one-dimensional multi-scale convolution unit to obtain sample data features; and according to the sample data features, a classification prediction unit is adopted to predict a prediction working condition corresponding to the vibration sample data, and a bearing fault detection model is trained based on the prediction working condition and an actual working condition. According to the scheme, the trained bearing fault detection model can be combined with the monitoring data to detect different fault working conditions of the rolling bearing.

Description

Technical Field

[0001] The present application relates to the technical field of shield machine bearings, and in particular to a training method for a bearing fault detection model, a bearing fault detection method, a device, equipment and a storage medium. Background Art

[0002] In the related art, the bearing fault detection method using deep learning usually uses various signal analysis methods to extract the features of the bearing detection signal. This method requires pre-extraction of features as input, and usually uses a convolutional neural network with a single convolution kernel. As a result, the neural network model loses some information in the pooling layer when processing feature information, resulting in possible deviations in the final results. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] In the first aspect, the present application proposes a training method for a bearing fault detection model, the method comprising: obtaining sample data corresponding to a rolling bearing under different actual working conditions; obtaining a one-dimensional sample data vector based on the sample data; inputting the one-dimensional sample data vector into a bearing fault detection model; wherein the bearing fault detection model comprises a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit; processing the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector; performing feature extraction on the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features; according to the sample data features, using the classification prediction unit to predict a predicted working condition corresponding to the vibration sample data, and training the bearing fault detection model based on the predicted working condition and the actual working condition.

[0005] In one implementation, the one-dimensional multi-scale convolution unit includes at least one convolution kernel of a different size and / or a different number, each of the convolution kernels of a different size and / or a different number includes at least one convolution branch, and different convolution branches corresponding to each of the convolution kernels of a different size and / or a different number contain convolution kernels of different sizes and / or numbers.

[0006] In one implementation, the classification prediction unit is used to predict the predicted working condition corresponding to the vibration sample data based on the sample data characteristics, and the bearing fault detection model is trained based on the predicted working condition and the actual working condition, including: calculating the model loss based on the predicted working condition and the actual working condition; performing gradient calculation and back propagation based on the model loss to update the model parameters of the bearing fault detection model using the gradient descent method.

[0007] In the second aspect, the present application proposes a bearing fault detection method, comprising: obtaining monitoring data of a rolling bearing; inputting the monitoring data into a bearing fault detection model to obtain output data of the bearing fault detection model; wherein the bearing fault detection model is trained using the method described in the first aspect; and determining whether there is an abnormality in the rolling bearing based on the output data.

[0008] In a third aspect, the present application proposes a training device for a bearing fault detection model, comprising: an acquisition module for acquiring sample data corresponding to a rolling bearing under different actual working conditions; a data processing module for acquiring a one-dimensional sample data vector based on the sample data; a first processing module for inputting the one-dimensional sample data vector into a bearing fault detection model; wherein the bearing fault detection model comprises a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit; a second processing module for processing the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector; a third processing module for performing feature extraction on the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features; a model training module for predicting a predicted working condition corresponding to the vibration sample data using the classification prediction unit according to the sample data features, and training the bearing fault detection model based on the predicted working condition and the actual working condition.

[0009] In one implementation, the one-dimensional multi-scale convolution unit includes at least one convolution kernel of a different size and / or a different number, each of the convolution kernels of a different size and / or a different number includes at least one convolution branch, and different convolution branches corresponding to each of the convolution kernels of a different size and / or a different number contain convolution kernels of different sizes and / or numbers.

[0010] In one implementation, the model training module can be used to: calculate the model loss based on the predicted operating condition and the actual operating condition; perform gradient calculation and back propagation based on the model loss to update the model parameters of the bearing fault detection model using the gradient descent method.

[0011] In a fourth aspect, the present application proposes a bearing fault detection device, comprising: an acquisition module for acquiring monitoring data of a rolling bearing; a first processing module for inputting the monitoring data into a bearing fault detection model to obtain output data of the bearing fault detection model; wherein the bearing fault detection model is trained using the device described in the third aspect; and a second processing module for determining whether there is an abnormality in the rolling bearing based on the output data.

[0012] In a fifth aspect, the present application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the training method of the bearing fault detection model as described in the first aspect.

[0013] In a sixth aspect, the present application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the bearing fault detection method as described in the second aspect.

[0014] In a seventh aspect, the present application proposes a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the first aspect to be implemented.

[0015] In an eighth aspect, the present application proposes a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the second aspect to be implemented.

[0016] In a ninth aspect, the present application proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for training a bearing fault detection model as described in the first aspect.

[0017] In a tenth aspect, the present application proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the bearing fault detection method as described in the second aspect.

[0018] The training method, bearing fault detection method, device, equipment and storage medium of the bearing fault detection model provided in the present application can generate sample data vectors based on sample data of rolling bearings under different working conditions, and process the sample data vectors based on the bearing fault detection model to obtain predicted working conditions, thereby training the bearing fault detection model based on the predicted working conditions and actual working conditions. Thus, the trained bearing fault detection model can be used in combination with monitoring data to detect different fault working conditions of rolling bearings.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 It is a flowchart of a method for training a bearing fault detection model provided in an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of a convolution kernel structure of different sizes and / or different numbers provided in an embodiment of the present application;

[0023] Figure 3 It is a flowchart of another method for training a bearing fault detection model provided in an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of a bearing fault detection model provided in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of a training device for a bearing fault detection model provided in an embodiment of the present application;

[0026] Figure 6 It is a structural schematic diagram of a bearing fault detection device provided in an embodiment of the present application;

[0027] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] The following describes the training method and device of the bearing fault detection model of the embodiment of the present application with reference to the accompanying drawings.

[0030] Figure 1 is a flow chart of a method for training a bearing fault detection model provided in an embodiment of the present application. Figure 1 As shown, the method may include but is not limited to the following steps:

[0031] Step S101: Obtain sample data corresponding to the rolling bearing under different actual working conditions.

[0032] The actual operating condition includes at least one of the following: a normal operating condition, a roller failure operating condition, an inner ring failure operating condition, and an outer ring failure operating condition.

[0033] The sample data includes at least one of the following: vibration data, temperature data, sound data and rotation speed data.

[0034] Step S102: Obtain a one-dimensional sample data vector based on the sample data.

[0035] Exemplarily, data cleaning is performed on the sample data, and a one-dimensional sample data vector is generated based on the cleaned data.

[0036] Step S103: inputting the one-dimensional sample data vector into the bearing fault detection model.

[0037] Among them, the bearing fault detection model includes a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit.

[0038] Step S104: Process the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector.

[0039] Exemplarily, the vector strength of the one-dimensional sample data vector is shortened based on the convolution layer in the convolution unit, and the number of vector channels is increased based on the pooling layer in the pooling unit to obtain a multi-dimensional sample data vector.

[0040] In an embodiment of the present application, the convolution unit includes at least one convolution layer, and the pooling unit includes at least one pooling layer.

[0041] Step S105: extracting features from the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features.

[0042] In one implementation, the one-dimensional multi-scale convolution unit includes at least one convolution kernel of different size and / or different number, each convolution kernel of different size and / or different number includes at least one convolution branch, and different convolution branches corresponding to each convolution kernel of different size and / or different number contain convolution kernels of different size and / or number.

[0043] As an example, see Figure 2 , Figure 2 Schematic diagram of a convolution kernel structure of different sizes and / or different numbers provided in an embodiment of the present application. Figure 2 As shown in Figure 1, the module consists of four branches, and the convolution kernel scale used by each branch is different from that of other convolution kernels, so that multi-scale features can be extracted from the output of the previous layer, and then the feature vectors obtained by convolution of each branch are concatenated as the input of the next layer. As an example, the number of convolution kernels in each branch of convolution kernels of different sizes and / or different numbers is shown in Table 1.

[0044] Table 1: Example table of the number of convolution kernels in each branch

[0045]

[0046] Step S106: According to the sample data characteristics, a classification prediction unit is used to predict the predicted working condition corresponding to the vibration sample data, and a bearing fault detection model is trained based on the predicted working condition and the actual working condition.

[0047] In an embodiment of the present application, the classification prediction unit includes a dropout layer, a fully connected layer and a softmax classifier.

[0048] For example, the global average pooling layer changes the number of channels of the sample data features to 1, and then passes through the dropout layer to prevent the overfitting of the model. Finally, the softmax classifier after the fully connected layer classifies the input into classified prediction conditions, and trains the bearing fault detection model based on the classified prediction conditions and actual conditions.

[0049] By implementing the embodiments of the present application, sample data vectors can be generated based on sample data of rolling bearings under different working conditions, and the sample data vectors can be processed based on the bearing fault detection model to obtain predicted working conditions, thereby training the bearing fault detection model based on the predicted working conditions and the actual working conditions. Thus, the trained bearing fault detection model can be used to detect different fault working conditions of rolling bearings.

[0050] In some embodiments, the above-mentioned training of the bearing fault detection model based on the predicted working conditions and the actual working conditions may include: calculating the model loss according to the predicted working conditions and the actual working conditions; performing gradient calculation and back propagation according to the model loss to update the model parameters of the bearing fault detection model using the gradient descent method.

[0051] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of another bearing fault detection method provided in an embodiment of the present application. Figure 3 As shown, the method may include but is not limited to the following steps:

[0052] Step S301: Acquire monitoring data of rolling bearings.

[0053] Step S302: input the monitoring data into the bearing fault detection model to obtain output data of the bearing fault detection model.

[0054] Among them, the bearing fault detection model is trained using the training method of the bearing fault detection model provided in any embodiment of the present application.

[0055] Step S303: Determine whether there is an abnormality in the rolling bearing based on the output data.

[0056] By implementing the embodiments of the present application, the detection data of the rolling bearing can be input into the pre-trained bearing fault detection model to determine whether the rolling bearing has a fault based on the output data of the bearing fault detection model, thereby providing convenience and accuracy in detecting different rolling bearing faults.

[0057] See also Figure 4 , Figure 4 Schematic diagram of a bearing fault detection model provided in an embodiment of the present application. Figure 4 As shown in the figure, the model consists of 1 input layer, 2 convolutional layers, 2 pooling layers, 3 multi-scale convolutional layers, 1 dropout layer and output layer. In the process of training the model, an end-to-end method can be used. The input layer is a one-dimensional vector of 6000x 1. After two convolutional pooling layers, the vector strength is continuously shortened and the number of channels is increased. Then, the core 3 multi-scale convolutional pooling layers are continuously used to extract features. After the global average pooling layer, the input feature changes the number of channels to 1. Then, the dropout layer is used to prevent the overfitting of the model. Finally, the softma classifier after the fully connected layer divides the output into 10 categories. Therefore, the predicted working condition predicted by the bearing fault detection model can be determined according to the probability of each category.

[0058] See also Figure 5 , Figure 5 Schematic diagram of a structure of a training device for a bearing fault detection model provided in an embodiment of the present application. Figure 5 As shown, the device 500 includes: an acquisition module 501, which is used to acquire sample data corresponding to the rolling bearing under different actual working conditions; a data processing module 502, which is used to acquire a one-dimensional sample data vector based on the sample data; a first processing module 503, which is used to input the one-dimensional sample data vector into a bearing fault detection model; wherein the bearing fault detection model includes a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit; a second processing module 504, which is used to process the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector; a third processing module 505, which is used to extract features from the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features; a model training module 506, which is used to predict the predicted working condition corresponding to the vibration sample data using the classification prediction unit according to the sample data features, and train the bearing fault detection model based on the predicted working condition and the actual working condition.

[0059] In one implementation, the one-dimensional multi-scale convolution unit includes at least one convolution kernel of a different size and / or a different number, each of the convolution kernels of a different size and / or a different number includes at least one convolution branch, and different convolution branches corresponding to each of the convolution kernels of a different size and / or a different number contain convolution kernels of different sizes and / or numbers.

[0060] In one implementation, the model training module 506 can be used to: calculate the model loss based on the predicted operating condition and the actual operating condition; perform gradient calculation and back propagation based on the model loss to update the model parameters of the bearing fault detection model using the gradient descent method.

[0061] Through the device of the embodiment of the present application, a sample data vector can be generated based on sample data of a rolling bearing under different working conditions, and the sample data vector can be processed based on a bearing fault detection model to obtain a predicted working condition, thereby training the bearing fault detection model based on the predicted working condition and the actual working condition. Thus, the trained bearing fault detection model can be used to detect different fault working conditions of the rolling bearing.

[0062] It should be noted that the above explanation of the embodiment of the training method for the bearing fault detection model is also applicable to the training device for the bearing fault detection model of this embodiment, and will not be repeated here.

[0063] See also Figure 6 , Figure 6 Schematic diagram of the structure of a bearing fault detection device provided in an embodiment of the present application. Figure 6 As shown, the device 600 includes: an acquisition module 601, used to acquire monitoring data of a rolling bearing; a first processing module 602, used to input the monitoring data into a bearing fault detection model to obtain output data of the bearing fault detection model; wherein the bearing fault detection model adopts Figure 5 The device shown is trained; the second processing module 603 is used to determine whether there is an abnormality in the rolling bearing based on the output data.

[0064] Through the device of the embodiment of the present application, the detection data of the rolling bearing can be input into the pre-trained bearing fault detection model to determine whether the rolling bearing has a fault based on the output data of the bearing fault detection model, thereby providing convenience and accuracy in detecting different rolling bearing faults.

[0065] It should be noted that the above explanation of the embodiment of the bearing fault detection method is also applicable to the training device of the bearing fault detection model of this embodiment, which will not be repeated here.

[0066] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 7 , Figure 7 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 7 As shown, the electronic device 700 includes: a processor 701, and a memory 702 communicatively connected to the processor 701; the memory 702 stores computer-executable instructions; the processor 701 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0067] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0068] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0069] In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0070] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0071] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0072] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0074] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0075] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0076] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0077] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A training method for a bearing fault detection model, characterized in that: include: Obtain sample data corresponding to rolling bearings under different actual working conditions; Acquire a one-dimensional sample data vector based on the sample data; Inputting the one-dimensional sample data vector into a bearing fault detection model; wherein the bearing fault detection model includes a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit; Processing the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector; Performing feature extraction on the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features; According to the sample data features, the classification prediction unit is used to predict the predicted working condition corresponding to the vibration sample data, and the bearing fault detection model is trained based on the predicted working condition and the actual working condition.

2. The method according to claim 1, characterized in that The one-dimensional multi-scale convolution unit includes at least one convolution kernel of different size and / or different number, each of the convolution kernels of different size and / or different number includes at least one convolution branch, and different convolution branches corresponding to each of the convolution kernels of different size and / or different number contain convolution kernels of different size and / or number.

3. The method according to claim 1, characterized in that The method of using the classification prediction unit to predict a predicted working condition corresponding to the vibration sample data according to the sample data characteristics, and training the bearing fault detection model based on the predicted working condition and the actual working condition, includes: Calculating model losses according to the predicted operating conditions and the actual operating conditions; Gradient calculation is performed based on the model loss and back propagation is performed to update the model parameters of the bearing fault detection model using a gradient descent method.

4. A bearing fault detection method, characterized in that: include: Obtain monitoring data of rolling bearings; Inputting the monitoring data into a bearing fault detection model to obtain output data of the bearing fault detection model; wherein the bearing fault detection model is trained by the method according to any one of claims 1 to 3; It is determined whether the rolling bearing has an abnormality based on the output data.

5. A training device for a bearing fault detection model, characterized in that: include: An acquisition module is used to acquire sample data corresponding to the rolling bearing under different actual working conditions; A data processing module, used for obtaining a one-dimensional sample data vector based on the sample data; A first processing module, used for inputting the one-dimensional sample data vector into a bearing fault detection model; wherein the bearing fault detection model comprises a convolution unit, a pooling unit, a one-dimensional multi-scale convolution unit and a classification prediction unit; A second processing module, used for processing the one-dimensional sample data vector based on the convolution unit and the pooling unit to obtain a multi-dimensional sample data vector; A third processing module, configured to extract features from the multi-dimensional sample data vector based on the one-dimensional multi-scale convolution unit to obtain sample data features; A model training module is used to predict the predicted working condition corresponding to the vibration sample data using the classification prediction unit according to the sample data characteristics, and train the bearing fault detection model based on the predicted working condition and the actual working condition.

6. A bearing fault detection device, characterized in that: include: An acquisition module, used for acquiring monitoring data of rolling bearings; A first processing module, configured to input the monitoring data into a bearing fault detection model to obtain output data of the bearing fault detection model; wherein the bearing fault detection model is trained using the device according to claim 5; The second processing module is used to determine whether the rolling bearing has an abnormality based on the output data.

7. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 3 and 4.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the method according to any one of claims 1 to 3 and 4 when executed by a processor.

9. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 3 and 4 when being executed by a processor.

Images