Subway traction motor bearing fault identification method, device and product

Abstract

The invention discloses a subway traction motor bearing fault identification method, device and product, and relates to the technical field of fault identification. Acquiring a vibration acceleration signal of the subway traction motor; dividing the vibration acceleration signal into a plurality of sections to obtain a plurality of sub-signal sections; performing time-frequency transformation on the plurality of sub-signal segments to obtain a plurality of time-frequency distribution matrixes; calculating an energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density value of the matrix element corresponding to each frequency; based on the energy amplitude spectrum entropies corresponding to all frequencies in each time frequency distribution matrix, determining an energy amplitude spectrum entropy sequence corresponding to the plurality of time frequency distribution matrixes; and performing fault detection by taking the energy amplitude spectrum entropy sequence as input of a pre-trained fault recognition model to obtain a fault recognition result of the subway traction motor. The subway traction motor bearing fault identification method, device and product disclosed by the invention can improve the accuracy of subway traction motor bearing fault detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault identification, and particularly relates to a method, device and product for identifying faults of subway traction motor bearings. Background Art

[0002] As a core component of the train power system, the operation state of the subway traction motor bearing directly affects the train safety and operation efficiency. Since the subway traction motor bearing is one of the most easily damaged core components in the train power system, a large part of train faults are caused by the faults of the traction motor bearing. Therefore, the fault diagnosis of the subway traction motor bearing is a key task in train operation and maintenance.

[0003] In traditional fault diagnosis methods, signal kurtosis analysis is widely used because of its simple calculation and no need for complex modeling. It realizes anomaly detection by quantifying the sharpness of impact components in vibration signals. However, this method is very sensitive to abnormal data caused by accidental factors and is also prone to cause the kurtosis value to exceed the threshold due to noise disturbance in the healthy state of the traction motor bearing, thus easily causing misjudgment.

[0004] Therefore, how to provide an effective solution to improve the accuracy of subway traction motor bearing fault detection has become an urgent problem to be solved in the prior art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device and product for identifying faults of subway traction motor bearings to solve the above problems existing in the prior art.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides a method for identifying faults of subway traction motor bearings, including:

[0008] Obtaining the vibration acceleration signal of the subway traction motor;

[0009] Dividing the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub-signal segments;

[0010] Performing time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding to the multiple sub-signal segments one by one;

[0011] Based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix is calculated. The energy amplitude spectrum entropy is used to represent the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency;

[0012] Based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix, an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices is determined;

[0013] The energy amplitude spectrum entropy sequence is used as the input of a pre-trained fault identification model for fault detection to obtain the fault identification result of the subway traction motor;

[0014] Among them, the fault identification model is trained with the energy amplitude spectrum entropy sequence of multiple sample time-frequency distribution matrices corresponding to multiple sample sub-signal segments divided from the historical sample vibration acceleration signals of the sample subway traction motor as the sample input, and the fault classification result of the sample subway traction motor when the historical sample vibration acceleration signal is detected as the output.

[0015] Based on the above - disclosed content, the present invention provides a new solution for accurately detecting faults in the bearings of subway traction motors, that is, acquiring the vibration acceleration signal of the subway traction motor; dividing the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub - signal segments; performing time - frequency transformation on the multiple sub - signal segments to obtain multiple time - frequency distribution matrices corresponding one - to - one to the multiple sub - signal segments; calculating the energy amplitude spectrum entropy corresponding to each frequency in each time - frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time - frequency distribution matrix, where the energy amplitude spectrum entropy is used to represent the complexity of the energy distribution frequency domain of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the complexity of the energy distribution frequency domain of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the complexity of the energy distribution frequency domain of the matrix elements corresponding to the same frequency; determining an energy amplitude spectrum entropy sequence corresponding to the multiple time - frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time - frequency distribution matrix; using the energy amplitude spectrum entropy sequence as the input of a pre - trained fault recognition model for fault detection to obtain the fault recognition result of the subway traction motor. Thus, through time - frequency transformation and calculation of the energy amplitude spectrum entropy, since the complexity of the change in the signal frequency components of the bearings in the normal and faulty states is different, their energy amplitude spectrum entropies are also different, which can be used for fault recognition of the bearings of subway traction motors. At the same time, the abnormal data caused by accidental factors has less influence on the complexity of the change in the signal frequency components, which can reduce the influence of the abnormal data caused by accidental factors, thereby reducing the misjudgment of the bearing state and improving the accuracy of fault detection of the bearings of subway traction motors.

[0016] In a possible design, the performing time - frequency transformation on the multiple sub - signal segments to obtain multiple time - frequency distribution matrices corresponding one - to - one to the multiple sub - signal segments includes:

[0017] Performing time - frequency transformation on the multiple sub - signal segments through short - time Fourier transform to obtain multiple time - frequency distribution matrices corresponding one - to - one to the multiple sub - signal segments.

[0018] In a possible design, the calculating the energy amplitude spectrum entropy corresponding to each frequency in each time - frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time - frequency distribution matrix includes:

[0019] Calculating the energy amplitude spectrum entropy corresponding to each frequency in each time - frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time - frequency distribution matrix according to the following formula (1);

[0020]

[0021] Wherein, H represents the energy amplitude spectrum entropy corresponding to a certain frequency in the time-frequency distribution matrix, N represents the total number of matrix elements corresponding to a certain frequency, X(i) represents the normalized value of the energy density value corresponding to the i-th matrix element corresponding to a certain frequency, and i is a positive integer less than or equal to N.

[0022] In a possible design, determining the energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix includes:

[0023] Selecting the minimum value of the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix to obtain the energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices.

[0024] In a possible design, using the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model for fault detection includes:

[0025] Normalizing the energy amplitude spectrum entropy sequence and using it as the input of a pre-trained fault identification model for fault detection.

[0026] In a possible design, after acquiring the vibration acceleration signal of the subway traction motor, the method further includes:

[0027] Filtering the vibration acceleration signal.

[0028] In a possible design, the fault identification model is a convolutional neural network model or a recurrent neural network model.

[0029] In a second aspect, the present invention provides a subway traction motor bearing fault identification device, including:

[0030] An acquisition unit for acquiring the vibration acceleration signal of the subway traction motor;

[0031] A partitioning unit for partitioning the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub-signal segments;

[0032] A time-frequency transformation unit for performing time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments;

[0033] An entropy calculation unit, configured to calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, where the energy amplitude spectrum entropy is used to represent the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency;

[0034] A determination unit, configured to determine an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix;

[0035] A fault detection unit, configured to use the energy amplitude spectrum entropy sequence as the input of a pre-trained fault recognition model for fault detection to obtain a fault recognition result of the subway traction motor;

[0036] Wherein, the fault recognition model is trained with the energy amplitude spectrum entropy sequence of multiple sample time-frequency distribution matrices corresponding to multiple sample sub-signal segments divided from the historical sample vibration acceleration signals of the sample subway traction motor as the sample input, and the fault classification result of the sample subway traction motor when the historical sample vibration acceleration signal is detected as the output.

[0037] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Wherein, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the subway traction motor bearing fault recognition method according to the first aspect or any possible design of the first aspect.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, the subway traction motor bearing fault recognition method according to the first aspect or any possible design of the first aspect is executed.

[0039] In a fifth aspect, the present invention provides a computer program product containing instructions. When the instructions are run on a computer, the computer is made to execute the subway traction motor bearing fault recognition method according to the first aspect or any possible design of the first aspect.

[0040] Beneficial effects:

[0041] The method, device and product for identifying faults of subway traction motor bearings provided by the present invention, through time-frequency transformation and calculation of energy amplitude spectrum entropy, since the complexity of the change in signal frequency components of bearings in normal and faulty states is different, their energy amplitude spectrum entropy is also different, and thus can be used for fault identification of subway traction motor bearings. At the same time, abnormal data caused by accidental factors has little influence on the complexity of the change in signal frequency components, which can reduce the influence of abnormal data caused by accidental factors, thereby reducing the misjudgment of the bearing state, improving the accuracy of fault detection of subway traction motor bearings, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of the method for identifying faults of subway traction motor bearings provided by an embodiment of the present application;

[0043] Figure 2 It is a block diagram schematic of the device for identifying faults of subway traction motor bearings provided by an embodiment of the present application;

[0044] Figure 3 It is a block diagram schematic of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the present invention in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structures of the drawings is only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0046] It should be understood that although terms such as first and second may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, the first unit can be called the second unit, and similarly, the second unit can be called the first unit, without departing from the scope of the exemplary embodiments of the present invention.

[0047] It should be understood that for the term "and / or" that may appear in this text, it is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and both A and B exist simultaneously. For the term " / and" that may appear in this text, it describes another association object relationship, indicating that two relationships can exist. For example, A / and B can represent two situations: A exists alone, and both A and B exist. Additionally, for the character " / " that may appear in this text, it generally indicates that the associated objects before and after are in an "or" relationship.

[0048] Embodiment

[0049] As Figure 1 shown, the subway traction motor bearing fault identification method provided in the first aspect of this embodiment can, but is not limited to, be executed by a computer device with certain computing resources, such as a cloud server, an edge computer configured with a GPU, a personal computer (Personal Computer, PC, referring to a multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptops, small laptops, tablets, and ultrabooks all belong to personal computers), a smartphone, a personal digital assistant (Personal Digital Assistant, PDA), or a wearable device, etc. As Figure 1 shown, the subway traction motor bearing fault identification method can, but is not limited to, include the following steps S101 to S106.

[0050] Step S101. Obtain the vibration acceleration signal of the subway traction motor.

[0051] In the embodiment of this application, an acceleration sensor can be set on or near the outer shell of the subway traction motor, and the vibration acceleration signal of the subway traction motor during operation can be detected through the acceleration sensor.

[0052] In one or more embodiments, after obtaining the vibration acceleration signal of the subway traction motor, the obtained vibration acceleration signal can be filtered.

[0053] Step S102. Divide the vibration acceleration signal into multiple segments with a specified duration to obtain multiple sub-signal segments.

[0054] Among them, the specified duration can be set according to the actual situation. For example, the specified duration can be 0.4s, 0.8s, or 1s, etc.

[0055] Step S103. Perform time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments.

[0056] In the embodiments of the present application, short-time Fourier transform (SIFT) can be used to perform time-frequency transformation on multiple sub-signal segments, and multiple time-frequency distribution matrices corresponding to the multiple sub-signal segments one by one can be obtained. It can be understood that in some other embodiments, other methods such as wavelet transform (WT) or Hilbert-Huang Transform can also be used to perform time-frequency transformation on multiple sub-signal segments.

[0057] Through time-frequency transformation, the sub-signal segment can be converted into a time-frequency distribution matrix of the signal, and the time-frequency distribution matrix can be expressed as where M represents the number of frequencies (number of frequency points), C represents the number of matrix elements corresponding to the same frequency, and r m,c represents the c-th matrix element in the m-th frequency. C = N / L, where N represents the number of signals in the sub-signal segment, and L represents the step size of the window function moving along the time axis.

[0058] Step S104. Based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix.

[0059] Among them, the energy amplitude spectrum entropy is used to represent the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency.

[0060] When the signal frequency components are more complex, that is, the signal energy is distributed under many frequencies, the value of the energy amplitude spectrum entropy is larger. Especially when the signal energy is evenly distributed within the entire frequency band, the energy amplitude spectrum entropy takes the maximum value of 1. When the signal frequency components are simpler, that is, the signal energy is concentrated in a few frequency components, the value of the energy amplitude spectrum entropy is small. Especially when the signal energy is concentrated at a certain frequency, the energy amplitude spectrum entropy takes the minimum value of 0.

[0061] In the embodiments of the present application, based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix can be calculated according to the following formula (1);

[0062]

[0063] Wherein, H represents the energy amplitude spectrum entropy corresponding to a certain frequency in the time-frequency distribution matrix, N represents the total number of matrix elements corresponding to a certain frequency, X(i) represents the normalized value of the energy density value corresponding to the i-th matrix element corresponding to a certain frequency, and i is a positive integer less than or equal to N.

[0064] Step S105. Based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix, determine an energy amplitude spectrum entropy sequence corresponding to multiple time-frequency distribution matrices.

[0065] In the embodiment of the present application, the minimum value of the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix can be selected, and the selected energy amplitude spectrum entropy is combined in the order corresponding to the time-frequency distribution matrix to obtain an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices.

[0066] It can be understood that in some other embodiments, the median or average value of the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix can also be selected and combined in time sequence to obtain an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices.

[0067] Step S106. Use the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model to perform fault detection, and obtain the fault identification result of the subway traction motor.

[0068] Specifically, the energy amplitude spectrum entropy sequence can be normalized and then used as the input of a pre-trained fault identification model to perform fault detection, and obtain the fault identification result of the subway traction motor.

[0069] Among them, the fault identification model can be trained with the energy amplitude spectrum entropy sequence corresponding to multiple sample time-frequency distribution matrices of multiple sample sub-signal segments divided from the historical sample vibration acceleration signals of the sample subway traction motor as the sample input, and the fault classification result of the sample subway traction motor when the historical sample vibration acceleration signal is detected as the output.

[0070] The fault identification model can be, but is not limited to, a Convolutional Neural Networks (CNN) model or a Recurrent Neural Network (RNN) model, etc., and is not specifically limited in the embodiment of the present application.

[0071] In summary, the subway traction motor bearing fault identification method provided by the present invention includes obtaining the vibration acceleration signal of the subway traction motor; dividing the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub-signal segments; performing time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments; calculating the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density value of the matrix element corresponding to each frequency in each time-frequency distribution matrix. The energy amplitude spectrum entropy is used to represent the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency; determining an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix; using the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model for fault detection to obtain the fault identification result of the subway traction motor bearing. In this way, through time-frequency transformation and calculation of the energy amplitude spectrum entropy, since the complexity of the signal frequency component changes of the bearings in the normal and faulty states is different, their energy amplitude spectrum entropies are also different. Therefore, it can be used for the fault identification of subway traction motor bearings. At the same time, the abnormal data caused by accidental factors has little impact on the complexity of the signal frequency component changes, which can reduce the impact of the abnormal data caused by accidental factors, thereby reducing the misjudgment of the bearing state, improving the accuracy of the subway traction motor bearing fault detection, and facilitating practical application and promotion.

[0072] Please refer to Figure 2 , the second aspect of the embodiments of the present application provides a subway traction motor bearing fault identification device. The subway traction motor bearing fault identification device includes:

[0073] An acquisition unit for acquiring the vibration acceleration signal of the subway traction motor;

[0074] A division unit for dividing the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub-signal segments;

[0075] A time-frequency transformation unit for performing time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments;

[0076] An entropy calculation unit, configured to calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density value of the matrix element corresponding to each frequency in each time-frequency distribution matrix. The energy amplitude spectrum entropy is used to represent the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency;

[0077] A determination unit, configured to determine an energy amplitude spectrum entropy sequence corresponding to the plurality of time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix;

[0078] A fault detection unit, configured to use the energy amplitude spectrum entropy sequence as the input of a pre-trained fault recognition model to perform fault detection, and obtain a fault recognition result of the subway traction motor;

[0079] Wherein, the fault recognition model is trained by using the energy amplitude spectrum entropy sequence of a plurality of sample time-frequency distribution matrices corresponding to multiple sample sub-signal segments divided from the historical sample vibration acceleration signal of the sample subway traction motor as the sample input, and the fault classification result of the sample subway traction motor when the historical sample vibration acceleration signal is detected as the output.

[0080] For the working process, working details and technical effects of the subway traction motor bearing fault recognition device provided in the second aspect of this embodiment, reference may be made to the first aspect of the embodiment, which will not be elaborated herein.

[0081] As Figure 3 shown, a third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Wherein, the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the subway traction motor bearing fault recognition method as described in the first aspect of the embodiment.

[0082] Specifically, for example, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in first-out memory (FIFO), and / or first-in last-out memory (FILO), etc.; the processor may not be limited to using a microprocessor of the STM32F105 series, a processor of architectures such as ARM (Advanced RISC Machines), X86, or a processor integrated with NPU (neural-network processing units); the transceiver may include, but is not limited to, a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee (a low-power local area network protocol based on the IEEE 802.15.4 standard) wireless transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver, etc.

[0083] In the fourth aspect of this embodiment, there is provided a computer-readable storage medium storing instructions for implementing the subway traction motor bearing fault identification method described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions that, when run on a computer, execute the subway traction motor bearing fault identification method as described in the first aspect. Among them, the computer-readable storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or memory sticks, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0084] In the fifth aspect of this embodiment, there is provided a computer program product containing instructions that, when run on a computer, cause the computer to execute the subway traction motor bearing fault identification method as described in the first aspect of the embodiment. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0085] It should be understood that specific details are provided in the following description to facilitate a complete understanding of the example embodiments. However, those of ordinary skill in the art should understand that the example embodiments can be implemented without these specific details. For example, a system may be shown in a block diagram to avoid obscuring the example with unnecessary details. In other instances, well-known processes, structures, and technologies may not be shown with unnecessary details to avoid obscuring the example embodiments.

[0086] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying faults in bearings of subway traction motors, characterized in that, Including: Obtain the vibration acceleration signal of the subway traction motor; Divide the vibration acceleration signal into multiple segments with a specified duration to obtain multiple sub-signal segments; Perform time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments; Based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix. The energy amplitude spectrum entropy is used to represent the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency. The larger the energy amplitude spectrum entropy, the greater the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency-domain complexity of the energy distribution of the matrix elements corresponding to the same frequency; Based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix, determine an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices; Use the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model for fault detection to obtain the fault identification result of the subway traction motor; Wherein, the fault identification model is trained with the energy amplitude spectrum entropy sequence of multiple sample time-frequency distribution matrices corresponding to multiple sample sub-signal segments divided from the historical sample vibration acceleration signals of the sample subway traction motors as the sample input, and the fault classification results of the sample subway traction motors when the historical sample vibration acceleration signals are detected as the output.

2. The method for identifying the bearing fault of the subway traction motor according to claim 1, wherein The performing time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments includes: Perform time-frequency transformation on the multiple sub-signal segments through short-time Fourier transform to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments.

3. The method for identifying the bearing fault of the subway traction motor according to claim 1, wherein The calculating the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix includes: Based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix according to the following formula (1); Wherein, H represents the energy amplitude spectrum entropy corresponding to a certain frequency in the time-frequency distribution matrix, N represents the total number of matrix elements corresponding to a certain frequency, X(i) represents the normalized value of the energy density value corresponding to the i-th matrix element corresponding to a certain frequency, and i is a positive integer less than or equal to N.

4. The method for identifying the bearing fault of a subway traction motor according to claim 1, wherein, The determining an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix includes: Select the minimum value of the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix to obtain an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices.

5. The subway traction motor bearing fault identification method according to claim 1, characterized in that The using the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model for fault detection includes: Normalize the energy amplitude spectrum entropy sequence and use it as the input of a pre-trained fault identification model for fault detection.

6. The method for identifying the bearing fault of the subway traction motor according to claim 1, wherein After obtaining the vibration acceleration signal of the subway traction motor, the method further includes: Performing filtering processing on the vibration acceleration signal.

7. The method for identifying the bearing fault of the subway traction motor according to claim 1, characterized in that The fault identification model is a convolutional neural network model or a recurrent neural network model.

8. A subway traction motor bearing fault identification device, characterized in that, Including: An acquisition unit, configured to acquire the vibration acceleration signal of the subway traction motor; A division unit, configured to divide the vibration acceleration signal into multiple segments of a specified duration to obtain multiple sub-signal segments; A time-frequency transformation unit, configured to perform time-frequency transformation on the multiple sub-signal segments to obtain multiple time-frequency distribution matrices corresponding one-to-one to the multiple sub-signal segments; An entropy calculation unit, configured to calculate the energy amplitude spectrum entropy corresponding to each frequency in each time-frequency distribution matrix based on the energy density values of the matrix elements corresponding to each frequency in each time-frequency distribution matrix, where the energy amplitude spectrum entropy is used to represent the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, the larger the energy amplitude spectrum entropy, the greater the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency, and the smaller the energy amplitude spectrum entropy, the smaller the frequency domain complexity of the energy distribution of the matrix elements corresponding to the same frequency; A determination unit, configured to determine an energy amplitude spectrum entropy sequence corresponding to the multiple time-frequency distribution matrices based on the energy amplitude spectrum entropy corresponding to all frequencies in each time-frequency distribution matrix; A fault detection unit, configured to use the energy amplitude spectrum entropy sequence as the input of a pre-trained fault identification model to perform fault detection to obtain the fault identification result of the subway traction motor; Wherein, the fault identification model is trained with the energy amplitude spectrum entropy sequence of the multiple sample time-frequency distribution matrices corresponding to the multiple sample sub-signal segments divided from the historical sample vibration acceleration signal of the sample subway traction motor as the sample input and the fault classification result of the sample subway traction motor when the historical sample vibration acceleration signal is detected as the output.

9. An electronic device, characterized in that, Including a memory, a processor, and a transceiver that are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the subway traction motor bearing fault identification method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or the instruction, when executed by a computer, implements the subway traction motor bearing fault identification method according to any one of claims 1 to 7.

Images