Motor fault detection method, system and device and storage medium

Abstract

The embodiment of the invention provides a motor fault detection method, system and device and a storage medium, and belongs to the technical field of motor detection. The motor fault detection method comprises the steps of obtaining a motor vibration signal; calculating a kurtosis value of the motor vibration signal according to the motor vibration signal; based on the kurtosis value of the motor vibration signal, performing variational mode decomposition on the motor vibration signal to obtain a plurality of target vibration signal components; and performing signal processing on the target vibration signal component according to a preset signal processing strategy to obtain a fault characteristic frequency. According to the embodiment of the invention, the variational mode decomposition and the signal processing are carried out on the obtained motor vibration signal, so that the noise of the motor vibration signal is eliminated, the fault frequency characteristics are extracted, and the efficiency and the accuracy of motor fault detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor detection, and in particular to a motor fault detection method, a motor fault detection system, an electronic device and a readable storage medium. Background Art

[0002] As the power source of various mechanical systems and equipment, motors are naturally widely used in various fields such as rail transportation, automobile manufacturing, and industrial production. Three-phase asynchronous has become an indispensable part of the industrial field due to its simple structure, excellent operating performance, and economy. When the motor is in continuous operation, especially when the motor is running at high load, the motor bearings will be subjected to extremely large alternating loads, and the bearings are prone to surface wear and fatigue.

[0003] Existing motor fault detection detects the bearing status and identifies bearing faults by acquiring the surface vibration of the motor body. However, during the actual operation of the unit, the collected vibration signal is affected by the internal structure of the motor and the external environment. Therefore, it contains not only the fault vibration signal but also a lot of noise, which affects the accuracy of motor fault diagnosis. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a motor fault detection method, system, device and storage medium to solve the above technical problems.

[0005] In order to achieve the above object, an embodiment of the present invention provides a motor fault detection method, the method comprising: Get the motor vibration signal; Calculating a kurtosis value of the motor vibration signal according to the motor vibration signal; Based on the kurtosis value of the motor vibration signal, performing variational modal decomposition on the motor vibration signal to obtain a plurality of target vibration signal components; The target vibration signal component is processed according to a preset signal processing strategy to obtain the fault characteristic frequency.

[0006] Optionally, calculating the kurtosis value of the motor vibration signal according to the motor vibration signal includes: According to the motor vibration signal, the kurtosis value of the motor vibration signal is calculated using formula (1): (1); In formula (1), is the kurtosis value of the motor vibration signal, is the motor vibration signal, is the length of the motor vibration signal, is the mean value of the motor vibration signal, is the standard deviation of the motor vibration signal, i are discrete time points of a time domain waveform.

[0007] Optionally, based on the kurtosis value of the motor vibration signal, performing variational modal decomposition on the motor vibration signal to obtain multiple target vibration signal components includes: Based on the kurtosis value of the motor vibration signal, determining whether it is necessary to perform fault detection on the motor vibration signal; If it is necessary to perform fault detection on the motor vibration signal, then perform variational modal pre-decomposition on the motor vibration signal to determine the number of decomposition layers; Based on the number of decomposition levels, variational modal decomposition is performed on the motor vibration signal to obtain multiple target vibration signal components.

[0008] Optionally, performing variational modal pre-decomposition on the motor vibration signal to determine the number of decomposition layers includes: Performing variational modal pre-decomposition on the motor vibration signal to obtain a plurality of pre-decomposed signal components; Determining a maximum pre-decomposition signal component from the plurality of pre-decomposition signal components; wherein the maximum pre-decomposition signal component is a pre-decomposition signal component having a maximum correlation coefficient; Calculate the kurtosis value of the maximum pre-decomposed signal component; The number of decomposition levels is determined based on the kurtosis value of the maximum pre-decomposed signal component.

[0009] Optionally, the determining a maximum pre-decomposition signal component from the plurality of pre-decomposition signal components comprises: Based on the pre-decomposed signal components, the correlation function of each pre-decomposed signal component is calculated using formula (2): (2); In formula (2), For the Pre-resolved signal components The related function of is the number of points of the pre-decomposed signal components, is the vibration amplitude corresponding to the discrete time point; According to the correlation function of the pre-decomposed signal component, the correlation coefficient of each pre-decomposed signal component is calculated using formula (3): (3); In formula (3), is the correlation coefficient of the pre-decomposed signal components, No. Pre-resolved signal components The related function of is the number of points of the pre-decomposed signal components, is the autocorrelation function of the original vibration signal of the motor; Based on the correlation coefficients of the pre-resolved signal components, a maximum pre-resolved signal component is determined from a plurality of the pre-resolved signal components.

[0010] Optionally, based on the number of decomposition levels, performing variational modal decomposition on the motor vibration signal to obtain multiple target vibration signal components includes: Based on the number of decomposition levels, performing variational modal decomposition on the motor vibration signal to obtain a plurality of initial vibration signal components; Calculating and obtaining the kurtosis value and correlation coefficient of the initial vibration signal component; The initial vibration signal components whose kurtosis values ​​and correlation coefficients meet the preset effective component conditions are screened out from the multiple initial vibration signal components, and the initial vibration signal components that meet the preset signal component conditions are used as target vibration signal components.

[0011] Optionally, the signal processing of the target vibration signal component according to a preset signal processing strategy to obtain a fault characteristic frequency also includes: Performing Hilbert transform on the plurality of target vibration signal components to obtain a plurality of envelope signals corresponding to each target vibration signal component; Performing Fourier transform on the envelope signal to obtain an envelope spectrum; Based on the envelope spectrum, envelope frequency entropy is calculated; Selecting the minimum envelope frequency entropy from the multiple envelope frequency entropies; wherein the minimum envelope frequency entropy is the envelope frequency entropy with the smallest entropy value; Perform spectrum analysis on the envelope spectrum corresponding to the minimum envelope frequency entropy to determine the fault characteristic frequency.

[0012] Optionally, the calculating envelope frequency entropy based on the envelope spectrum includes: Based on the envelope spectrum, the envelope frequency entropy is calculated using formula (4): (4); In formula (4), is the envelope frequency entropy, is the number of envelope signals, is the probability of occurrence of frequency, .

[0013] In a second aspect of an embodiment of the present invention, a motor fault detection system is provided, the system comprising: A signal acquisition module, used to acquire a motor vibration signal; A kurtosis calculation module, used for calculating the kurtosis value of the motor vibration signal according to the motor vibration signal; A signal decomposition module, used for performing variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal to obtain multiple target vibration signal components; The signal processing module is used to perform signal processing on the target vibration signal component according to a preset signal processing strategy to obtain the fault characteristic frequency.

[0014] A third aspect of the present application provides an electronic device configured to execute the above-mentioned motor fault detection method.

[0015] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the above-mentioned motor fault detection method.

[0016] The embodiment of the present invention obtains the motor vibration signal, calculates the kurtosis value of the motor vibration signal according to the motor vibration signal, performs variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal, obtains multiple target vibration signal components, performs signal processing on the target vibration signal components according to a preset signal processing strategy, and obtains the fault characteristic frequency. That is, the embodiment of the present invention removes the noise of the motor vibration signal by performing variational modal decomposition and signal processing on the acquired motor vibration signal to extract the fault frequency characteristics, thereby improving the efficiency and accuracy of motor fault detection.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a motor fault detection method provided in an embodiment of the present application; Figure 2 It is a flowchart of solving the number of decomposition layers of variational mode decomposition; Figure 3 It is a schematic diagram of the overall process of a motor fault detection method provided by an embodiment of the present application; Figure 4 It is the variational mode decomposition diagram of the bearing in normal state; Figure 5 This is the global diagram of the envelope spectrum of the bearing in normal condition; Figure 6 This is the envelope spectrum diagram of the bearing in normal state; Figure 7 It is the variational modal decomposition diagram of the bearing raceway fault state; Figure 8 It is the global diagram of the envelope spectrum under the condition of bearing raceway fault; Fig. 9 It is the envelope spectrum diagram of the raceway fault state in the bearing; Fig.10 It is the variational modal decomposition diagram of the bearing outer raceway under fault condition; Fig.11 It is the global diagram of the envelope spectrum under the fault state of the outer raceway of the bearing; Fig.12 It is the envelope spectrum diagram of the bearing outer raceway under fault condition; Fig.13 A schematic diagram of the functional modules of a motor fault detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0021] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0022] Embodiment 1 Please refer to Figure 1 , Figure 1 It is a flow chart of a motor fault detection method provided in this embodiment.

[0023] Step S100: Acquire the motor vibration signal.

[0024] In this embodiment, an acceleration sensor is added beside the motor, the acceleration sensor is connected to a current data acquisition control device, and the current data acquisition control device is further connected to a computer to achieve real-time monitoring of the motor vibration signal.

[0025] Step S200: Calculate the kurtosis value of the motor vibration signal according to the motor vibration signal.

[0026] Specifically, the collected motor vibration signal is subjected to Fourier transform to obtain the spectrum of the motor signal, and the kurtosis of the motor vibration signal at different bandpass frequencies at equal time intervals is further calculated using formula (1) to obtain the kurtosis diagram. Formula (1) includes: (1); In formula (1), is the kurtosis value of the motor vibration signal, is the motor vibration signal, is the length of the motor vibration signal, is the mean value of the motor vibration signal, is the standard deviation of the motor vibration signal, i are discrete time points of a time domain waveform.

[0027] Step S300: Based on the kurtosis value of the motor vibration signal, performing variational modal decomposition on the motor vibration signal to obtain multiple target vibration signal components.

[0028] It can be understood that before performing variational mode, in order to improve detection efficiency, this embodiment proposes to judge whether it is necessary to perform fault detection on the motor vibration signal based on the kurtosis value of the motor vibration signal, that is, if the kurtosis exceeds the kurtosis range of the normal motor vibration signal, it indicates that further fault detection is needed for the motor vibration signal. If it does not exceed the kurtosis range of the normal motor vibration signal, there is no need to perform fault detection on the motor vibration signal.

[0029] It should be understood that before formally performing variational mode decomposition, the number of decomposition levels of variational mode decomposition needs to be determined first, so the solution for the number of decomposition levels in this implementation is as follows: Depend on Figure 2 As shown, the initial decomposition layer number is recorded as , and initialize , the kurtosis value of the initial pre-decomposed signal component is recorded as , and initialize , current decomposition times , the motor vibration signal is pre-decomposed by variational mode to obtain multiple pre-decomposed signal components, and the correlation function of each pre-decomposed signal component is calculated using formula (2). Then, the correlation coefficient of each pre-decomposed signal component is calculated based on the correlation function of the pre-decomposed signal component using formula (3). Based on the correlation coefficient, the maximum pre-decomposed signal component with the maximum correlation coefficient is determined from multiple pre-decomposed signal components, and the kurtosis value of the maximum pre-decomposed signal component is calculated. Based on the kurtosis value of the maximum pre-decomposed signal component, the number of decomposition layers is determined. Wherein, formula (2) and formula (3) are as follows: (2); In formula (2), For the signal components The related function of is the number of signal components, is the vibration amplitude corresponding to the discrete time point; (3); In formula (3), is the correlation coefficient of the pre-decomposed signal components, No. Pre-resolved signal components The related function of is the number of points of the pre-decomposed signal components, is the autocorrelation function of the original vibration signal of the motor; The motor vibration signal is subjected to variational mode pre-decomposition to obtain a plurality of pre-decomposed signal components. Specifically, the mode function sequence of the variational mode pre-decomposition is recorded as , the center frequency of the mode function is recorded as , and denote the quadratic penalty factor as , the current number of iterations is recorded as , and respectively , , as well as Initialize, set the loop iteration, and when the modal function center frequency is greater than or equal to 0, use equations (5), (6) and (7) to calculate , and Perform iterative update and use formula (8) to set the iteration termination condition. When the mode function sequence satisfies formula (8), the iteration is stopped to obtain the decomposed pre-decomposed signal components. Formula (5), formula (6), formula (7) and formula (8) are as follows: (5); In formula (5), is the updated modal function sequence, is the Fourier transform of the motor vibration signal, is the quadratic penalty factor, is the center frequency of the mode function, is the number of penalty factors for signal decomposition; (6); In formula (6), is the updated modal function center frequency, is the modal function sequence; (7); In formula (7), is the updated quadratic penalty factor, is the quadratic penalty factor before updating, is the Fourier transform of the motor vibration signal, is the updated modal function sequence; (8); In formula (8), is the updated modal function sequence, The modal function sequence before updating, It is a preset iteration accuracy, which can be set according to actual needs and is not limited in this embodiment.

[0030] Among them, based on the kurtosis value of the maximum pre-decomposed signal component, the number of decomposition layers is determined, specifically including: Figure 2 As shown, after this variational mode pre-decomposition, the kurtosis value of the pre-decomposed signal component calculated is recorded as ,judge Is it greater than ,like Greater than , then perform variational mode pre-decomposition again and judge again Is it greater than ,like Less than or equal to , then take , and get the number of decomposition levels.

[0031] Specifically, this step formally performs variational modal decomposition on the motor vibration signal based on the above-mentioned decomposition layers to obtain multiple initial vibration signal components. The kurtosis value and correlation coefficient of the initial vibration signal components are calculated using equations (1), (2) and (3). The initial vibration signal components whose kurtosis value and correlation coefficient meet the preset valid component conditions are screened out from the multiple initial vibration signal components, and the initial vibration signal components that meet the preset signal component conditions are used as target vibration signal components. Among them, the larger the absolute value of the correlation coefficient, the greater the degree of correlation, and vice versa. In this implementation, the initial vibration signal component with a correlation coefficient greater than 0.1 and a kurtosis greater than 3 can be selected as the target vibration signal component to eliminate invalid initial vibration signal components and retain valid target vibration signal components. Among them, the steps of formal variational modal decomposition are the same as the steps of variational modal pre-decomposition, and the above-mentioned decomposition steps can be used.

[0032] Step S400: performing signal processing on the target vibration signal component according to a preset signal processing strategy to obtain a fault characteristic frequency.

[0033] This step specifically includes the following: First, the present embodiment performs Fourier transform on the target vibration signal component to convert the target vibration signal component from the time domain to the frequency domain, and stores the result in a preset vector In the example above, we create a vector ,vector Elements within In satisfying or hour, , in satisfying hour, , h The rest of the values h ( i )=0, is the length of the input signal, and the vector With vector Perform element-wise multiplication to obtain the transformed , further use formula (10) to transform Perform inverse Fourier transform calculation to obtain the signal to be analyzed , and then use formula (11) to find The modulus value is used to calculate the envelope signal. Among them, equations (9), (10) and (11) are as follows: (9); In formula (9), The transformed target vibration signal component, is the signal period, is the integral time variable; (10); In formula (10), is the signal to be analyzed, The transformed target vibration signal component, is the target vibration signal component before transformation, For complex functions z ( t )'s imaginary unit: (11); In formula (11), is the envelope signal, is the signal to be analyzed, The transformed target vibration signal component, is the target vibration signal component before transformation.

[0034] Then perform Fourier transform on the envelope signal to obtain the envelope spectrum. Based on the envelope spectrum, divide the envelope spectrum into m layers in the vertical direction, use formula (12) to calculate the probability of each frequency component falling in each layer, and further use formula (4) to calculate the envelope frequency entropy. Among them, formula (12) and formula (4) are as follows: (12); In formula (12), is the probability of a frequency component falling into each layer, is the envelope signal; (4); In formula (4), is the envelope frequency entropy, is the number of envelope signals, is the probability of a frequency component falling into each layer, .

[0035] Finally, the minimum envelope frequency entropy with the smallest entropy value is selected from the multiple envelope frequency entropies, and the envelope frequency spectrum corresponding to the minimum envelope frequency entropy is analyzed to determine the fault characteristic frequency.

[0036] Figure 3 : is a schematic diagram of the overall process of this embodiment. This embodiment obtains the motor vibration signal, and then calculates the kurtosis value of the motor vibration signal according to the motor vibration signal. Further based on the kurtosis value of the motor vibration signal, it is determined whether it is necessary to perform fault detection on the motor vibration signal. If it is not necessary to perform fault detection on the motor vibration signal, the next step is stopped. If it is necessary to perform fault detection on the motor vibration signal, the motor vibration signal is pre-decomposed by variational mode to determine the number of decomposition layers, and then based on the number of decomposition layers, the motor vibration signal is pre-decomposed by variational mode to obtain multiple initial vibration signal components. The kurtosis value and correlation coefficient of the initial vibration signal component are calculated, and the initial vibration signal component whose kurtosis value and correlation coefficient meet the preset effective component conditions is screened out from multiple initial vibration signal components. The multiple target vibration signal components are Hilbert transformed to obtain multiple envelope signals corresponding to each target vibration signal component. The envelope signal is then Fourier transformed to obtain an envelope spectrum. Based on the envelope spectrum, the envelope frequency entropy is calculated, and the minimum envelope frequency entropy is further selected from the multiple envelope frequency entropies. Finally, the envelope spectrum corresponding to the minimum envelope frequency entropy is subjected to spectrum analysis to determine the fault characteristic frequency.

[0037] Based on the above motor fault detection method, this embodiment provides two motor fault detection examples, which are as follows: Example 1: The bearing used on the driving side of the induction motor is a deep groove ball bearing. The parameters of the bearing are shown in Table 1: Table 1 6205-2RS JEM SKF deep groove ball bearing parameter table Figure 4 and Figure 5 They are respectively the variational mode decomposition diagram and the envelope spectrum global diagram under the normal state of the bearing. Figure 6 is the envelope spectrum diagram of the bearing in normal state. Table 2 shows the kurtosis value, correlation coefficient value and envelope frequency entropy of the vibration signal component of the bearing in normal state. The vibration signal component IMF4 is taken for analysis. Figure 6 As shown in Table 2, the maximum spectrum peak of the bearing in normal state is 0.005572, and the corresponding vibration frequency is 11Hz, which means that the frequency corresponding to the calculated envelope frequency entropy is the normal motor frequency. Table 2 Kurtosis and correlation coefficient values ​​of each IMF when the bearing is normal Use electric spark to process single point faults (rolling element fault, inner raceway fault, outer raceway fault) of certain defect sizes (0.1778mm, 0.3556mm, 0.5334mm, 0.7112mm) on normal bearings, and then use acceleration sensors to collect motor vibration signals. Figure 7 is the variational modal decomposition diagram of the bearing raceway fault state. Figure 8 is the global diagram of the envelope spectrum under the condition of bearing raceway fault, Fig. 9 is the envelope spectrum of the bearing inner raceway fault state. Table 3 shows the kurtosis value, correlation coefficient value and envelope frequency entropy of the vibration signal component under the bearing inner raceway fault state. The envelope spectrum of the vibration signal component IMF3 is analyzed. Fig. 9 As shown, the maximum spectrum peak reaches 0.1095, and the corresponding vibration frequency at the maximum spectrum peak is 164.1Hz, which is consistent with the theoretical value of 163.18Hz calculated at the corresponding speed. Compared with the envelope spectrum of the normal bearing, the bearing fault obviously has a larger frequency vibration at 164.1Hz. The signal frequency at this time is the fault characteristic frequency that characterizes the bearing raceway fault. Among them, Table 3 is as follows: Table 3 Kurtosis, correlation coefficient and envelope entropy of each IMF when the inner raceway fails Example 2: The motor and bearings used are the same as those used in Example 1, and the initial parameters are the same. Fig.10 is the variational modal decomposition diagram of the bearing outer raceway fault state, Fig.11 is the global diagram of the envelope spectrum under the bearing outer raceway fault state, Fig.12is the envelope spectrum diagram of the bearing outer raceway fault state, and Table 4 is the kurtosis value, correlation coefficient value and envelope frequency entropy of the vibration signal component under the bearing outer raceway fault state. Take the vibration signal component IMF4 for spectrum analysis, and Fig.12 It can be seen that the maximum spectrum peak reaches 0.3229, and the corresponding vibration frequency at the maximum spectrum peak is 105.5Hz, which is consistent with the theoretical value of 106.13Hz calculated at the corresponding speed. Compared with the envelope spectrum of the normal bearing, the outer raceway fault of the bearing obviously has a larger frequency vibration at the position of 105.5Hz, that is, the signal frequency at this time is the fault characteristic frequency that characterizes the outer raceway fault of the bearing. Among them, Table 4 is as follows: Table 4 Kurtosis, correlation coefficient and envelope entropy of each IMF when the outer raceway of the bearing is normal This embodiment obtains the motor vibration signal, calculates the kurtosis value of the motor vibration signal according to the motor vibration signal, performs variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal, obtains multiple target vibration signal components, performs signal processing on the target vibration signal components according to a preset signal processing strategy, and obtains the fault characteristic frequency. That is, the embodiment of the present invention removes the noise of the motor vibration signal by performing variational modal decomposition and signal processing on the obtained motor vibration signal, so as to extract the fault frequency characteristics, thereby improving the efficiency and accuracy of motor fault detection.

[0038] Embodiment 2 Please refer to Fig.13 , Fig.13 It is a functional module diagram of a motor fault detection system 200 provided in an embodiment of the present application.

[0039] A signal acquisition module 210 is used to acquire a motor vibration signal; A kurtosis calculation module 220, used for calculating the kurtosis value of the motor vibration signal according to the motor vibration signal; A signal decomposition module 230 is used to perform variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal to obtain multiple target vibration signal components; The signal processing module 240 is used to perform signal processing on the target vibration signal component according to a preset signal processing strategy to obtain a fault characteristic frequency.

[0040] It should be understood that the device corresponds to the above-mentioned motor fault detection method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the above description. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0041] Embodiment 3 In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0042] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0043] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0044] Embodiment 4 An embodiment of the present invention further provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the program having the steps of the motor fault detection method is executed.

[0045] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0050] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0051] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0052] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A motor fault detection method, characterized in that: The method comprises: Get the motor vibration signal; Calculating a kurtosis value of the motor vibration signal according to the motor vibration signal; Based on the kurtosis value of the motor vibration signal, performing variational modal decomposition on the motor vibration signal to obtain a plurality of target vibration signal components; The target vibration signal component is processed according to a preset signal processing strategy to obtain the fault characteristic frequency.

2. The motor fault detection method according to claim 1, characterized in that: The step of calculating the kurtosis value of the motor vibration signal comprises: According to the motor vibration signal, the kurtosis value of the motor vibration signal is calculated using formula (1): （1）； In formula (1), is the kurtosis value of the motor vibration signal, is the motor vibration signal, is the length of the motor vibration signal, is the mean value of the motor vibration signal, is the standard deviation of the motor vibration signal, i are discrete time points of the time domain waveform.

3. The motor fault detection method according to claim 1, characterized in that: The step of performing variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal to obtain a plurality of target vibration signal components includes: Based on the kurtosis value of the motor vibration signal, determining whether it is necessary to perform fault detection on the motor vibration signal; If it is necessary to perform fault detection on the motor vibration signal, then perform variational modal pre-decomposition on the motor vibration signal to determine the number of decomposition layers; Based on the number of decomposition levels, variational modal decomposition is performed on the motor vibration signal to obtain multiple target vibration signal components.

4. The motor fault detection method according to claim 3, characterized in that: The step of performing variational modal pre-decomposition on the motor vibration signal to determine the number of decomposition layers includes: Performing variational modal pre-decomposition on the motor vibration signal to obtain a plurality of pre-decomposed signal components; Determining a maximum pre-decomposition signal component from the plurality of pre-decomposition signal components; wherein the maximum pre-decomposition signal component is a pre-decomposition signal component having a maximum correlation coefficient; Calculate the kurtosis value of the maximum pre-decomposed signal component; The number of decomposition levels is determined based on the kurtosis value of the maximum pre-decomposed signal component.

5. The motor fault detection method according to claim 4, characterized in that: The step of determining the maximum pre-decomposed signal component from the plurality of pre-decomposed signal components comprises: Based on the pre-decomposed signal components, the correlation function of each pre-decomposed signal component is calculated using formula (2): （2）； In formula (2), For the Pre-resolved signal components The related function of is the number of points of the pre-decomposed signal components, is the vibration amplitude corresponding to the discrete time point; According to the correlation function of the pre-decomposed signal component, the correlation coefficient of each pre-decomposed signal component is calculated using formula (3): （3）； In formula (3), is the correlation coefficient of the pre-decomposed signal components, No. Pre-resolved signal components The related function of is the number of points of the pre-decomposed signal components, is the autocorrelation function of the original vibration signal of the motor; Based on the correlation coefficients of the pre-resolved signal components, a maximum pre-resolved signal component is determined from a plurality of the pre-resolved signal components.

6. The motor fault detection method according to claim 3, characterized in that: The step of performing variational modal decomposition on the motor vibration signal based on the number of decomposition layers to obtain a plurality of target vibration signal components includes: Based on the number of decomposition levels, performing variational modal decomposition on the motor vibration signal to obtain a plurality of initial vibration signal components; Calculating and obtaining the kurtosis value and correlation coefficient of the initial vibration signal component; The initial vibration signal components whose kurtosis values ​​and correlation coefficients meet the preset effective component conditions are screened out from the multiple initial vibration signal components, and the initial vibration signal components that meet the preset signal component conditions are used as target vibration signal components.

7. The motor fault detection method according to claim 6, characterized in that: The signal processing of the target vibration signal component according to the preset signal processing strategy to obtain the fault characteristic frequency includes: Performing Hilbert transform on the plurality of target vibration signal components to obtain an envelope signal corresponding to each target vibration signal component; Performing Fourier transform on the envelope signal to obtain an envelope spectrum; Based on the envelope spectrum, envelope frequency entropy is calculated; Selecting the minimum envelope frequency entropy from the multiple envelope frequency entropies; wherein the minimum envelope frequency entropy is the envelope frequency entropy with the smallest entropy value; Perform spectrum analysis on the envelope spectrum corresponding to the minimum envelope frequency entropy to determine the fault characteristic frequency.

8. The motor fault detection method according to claim 7, characterized in that: The step of calculating envelope frequency entropy based on the envelope spectrum includes: Based on the envelope spectrum, the envelope frequency entropy is calculated using formula (4): （4）； In formula (4), is the envelope frequency entropy, is the number of envelope signals, is the probability of occurrence of frequency, .

9. A motor fault detection system, characterized in that: The system comprises: A signal acquisition module, used to acquire a motor vibration signal; A kurtosis calculation module, used for calculating the kurtosis value of the motor vibration signal according to the motor vibration signal; A signal decomposition module, used for performing variational modal decomposition on the motor vibration signal based on the kurtosis value of the motor vibration signal to obtain multiple target vibration signal components; The signal processing module is used to perform signal processing on the target vibration signal component according to a preset signal processing strategy to obtain the fault characteristic frequency.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the motor fault detection method according to any one of claims 1 to 8 is executed.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions for causing a machine to execute the motor fault detection method according to any one of claims 1 to 8.

Images