Empirical wavelet transform based planetary gearbox fault diagnosis method and related device
By using an empirical wavelet transform-based fault diagnosis method for planetary gearboxes, the fault characteristic frequency and meshing frequency are calculated using structural parameters. The frequency band is reconstructed by combining indicators such as cross-correlation coefficient and kurtosis value. This solves the problem of insufficient adaptability in traditional wavelet transform methods and enables accurate identification of early and weak faults in planetary gearboxes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN BOILER & PRESSURE VESSEL INSPECTION & TESTING INST CO LTD
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-24
AI Technical Summary
In existing technologies, early weak faults in planetary gearboxes are difficult to identify. Traditional wavelet transform methods lack adaptability, resulting in poor decomposition of non-stationary and nonlinear noisy signals, frequency band redundancy or component aliasing, and incorrect component selection leading to the omission of fault impact signals.
The planetary gearbox fault diagnosis method based on empirical wavelet transform calculates the fault characteristic frequency and meshing frequency by acquiring structural parameters, divides the initial frequency band using the minimum value method, calculates the comprehensive fault index by combining cross-correlation coefficient, kurtosis value and envelope spectrum amplitude, reconstructs the target frequency band and performs EWT transform, and selects the component with the largest IMF kurtosis value for envelope spectrum analysis.
It improves the adaptability and accuracy of EWT frequency band division, ensuring accurate identification of fault frequency bands under noise interference and weak fault scenarios, avoiding incorrect component selection, and improving the accuracy of fault diagnosis.
Smart Images
Figure CN122286186B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of rotating machinery fault diagnosis technology, specifically relating to a planetary gearbox fault diagnosis method and related equipment based on empirical wavelet transform. Background Technology
[0002] During operation, the vibration signals collected by a planetary gearbox are affected by interference from the installation environment, complex alternating loads, and time-varying transmission paths. Furthermore, early gear component faults are weak, have low signal-to-noise ratios, and are modulated by fault signals. This makes early, subtle faults in the planetary gearbox difficult to identify.
[0003] To extract effective weak fault features from planetary gearbox signals, researchers have recently studied the characteristics of amplitude-frequency modulation (AM-FM) signals from planetary gearboxes. Traditional wavelet transform methods, such as continuous wavelet transform and discrete wavelet transform, have the following shortcomings: the wavelet basis cannot be changed once selected, the scale cannot be varied, and there is a lack of adaptability. Researchers have proposed an adaptive signal decomposition method called empirical wavelet transform (EWT). EWT divides the signal spectrum amplitude into a set of maximum boundaries, defines these boundaries as orthogonal filter banks, and then decomposes the signal into a set of tightly supported AM-FM signal components. Under actual operating conditions, non-stationary and nonlinear noisy signals can lead to poor fault band performance in EWT decomposition, with the band containing redundant regions or being over-segmented, resulting in component aliasing; incorrect component selection can also lead to components that do not contain fault impulse signals. Summary of the Invention
[0004] In view of this, the present invention provides a planetary gearbox fault diagnosis method and related equipment based on empirical wavelet transform, which is used to solve the problems in the prior art where non-stationary and nonlinear noisy signals lead to poor fault band performance of EWT decomposition, redundant regions in the frequency band or excessive segmentation, resulting in component aliasing; and incorrect component selection leads to components not containing fault impact signals.
[0005] To achieve one or more of the above objectives or other objectives, in a first aspect, the present invention proposes a planetary gearbox fault diagnosis method based on empirical wavelet transform, comprising: acquiring the structural parameters of each component in the planetary gearbox to be tested, and determining the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters.
[0006] The number of initial frequency bands is calculated based on the fault characteristic frequency and the meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox to be tested is divided using the minimum value method to obtain the initial frequency bands. The comprehensive fault index of the initial frequency band is calculated by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When the initial frequency band is a faulty frequency band, the boundary of the initial frequency band is reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The target frequency band is then used to perform EWT transformation on the signal spectrum to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0007] Optionally, the components within the planetary gearbox to be tested include a sun gear, planet gears, and a ring gear. The step of determining the fault characteristic frequency and meshing frequency of each component within the planetary gearbox to be tested based on the structural parameters includes: The meshing frequency is determined based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the absolute rotational frequency of the sun gear, among the structural parameters mentioned above. The fault characteristic frequency of the sun gear in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of planet gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the planetary gears in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of teeth on the planetary gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the internal gear ring of the planetary gearbox under test is calculated based on the number of teeth on the gear ring, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the number of planet gears in the structural parameters.
[0008] Optionally, the step of dividing the signal spectrum of the planetary gearbox to be detected into initial frequency bands using the minimum value method based on the initial number of frequency bands includes: Envelope operation is performed on the signal spectrum of the planetary gearbox to be tested to obtain the envelope map; The envelope spectrum is divided using a minimum method based on the number of initial frequency bands to obtain the initial frequency bands.
[0009] Optionally, the step of calculating the comprehensive fault index of the initial frequency band using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band includes: The formula for calculating the cross-correlation coefficient is as follows:
[0010] Calculate the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, where, Component signal With the original signal cross-correlation coefficients, Where n is the length of the signal, and n is the index. and The original signals are respectively and component signals The mean; The formula for calculating the kurtosis value of a component signal is as follows:
[0011] Calculate the kurtosis values of the component signals in the initial frequency band, where, This represents the kurtosis value of the component signal; Calculation formula based on fault characteristic indicators:
[0012] Calculate fault characteristic indices based on theoretical fault characteristic frequencies and envelope spectrum amplitudes in the initial frequency band, where, FFI As a fault characteristic indicator, This represents the amplitude of the envelope spectrum in the initial frequency band. S represents the theoretical fault characteristic frequency, and S represents the envelope spectrum. The comprehensive fault index calculation formula is as follows:
[0013] Calculate the comprehensive fault index of the initial frequency band.
[0014] Optionally, the step of reconstructing the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band includes: The mathematical representation of the preset boundary merging rule is as follows:
[0015] in, Let i be the average comprehensive fault index of N component signals, where i represents the i-th signal component among the N component signals.
[0016] Optionally, the step of performing EWT transform on the signal spectrum according to the target frequency band to obtain the target EWT component signal includes: The target EWT component signal is obtained by performing EWT transformation on the signal spectrum based on the boundary data of the target frequency band.
[0017] Optionally, the step of determining whether the initial frequency band is a faulty frequency band based on the comprehensive fault index includes: The comprehensive fault index is matched with the comprehensive threshold. If the comprehensive fault index is greater than or equal to the preset threshold, the initial frequency band is determined to be a fault frequency band. If the comprehensive fault index is less than the preset threshold, then the cross-correlation coefficient is matched with the cross-correlation threshold, the kurtosis value is matched with the kurtosis value threshold, and the fault feature index is matched with the fault feature threshold. When the cross-correlation coefficient is greater than or equal to the cross-correlation threshold, and / or the kurtosis value is greater than or equal to the kurtosis value threshold, and / or the fault characteristic index is greater than or equal to the fault characteristic threshold, the initial frequency band is determined to be a fault frequency band.
[0018] Secondly, this application provides a planetary gearbox fault diagnosis device based on empirical wavelet transform, the device comprising: The basic calculation module is used to obtain the structural parameters of each component in the planetary gearbox under test, and to determine the fault characteristic frequency and meshing frequency of each component in the planetary gearbox under test based on the structural parameters. The partitioning module is used to calculate the number of initial frequency bands based on the fault characteristic frequency and the meshing frequency, and to partition the signal spectrum of the planetary gearbox to be tested according to the number of initial frequency bands by using the minimum value method to obtain the initial frequency bands; The first calculation module is used to calculate the comprehensive fault index of the initial frequency band by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The transformation module is used to determine whether the initial frequency band is a faulty frequency band based on the comprehensive fault index, and when the initial frequency band is a faulty frequency band, to reconstruct the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band, and to perform EWT transformation on the signal spectrum based on the target frequency band to obtain the target EWT component signal; The second calculation module is used to calculate the IMF kurtosis value of each target EWT component signal, and select the target EWT component signal with the largest IMF kurtosis value as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0019] Thirdly, this application provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the planetary gearbox fault diagnosis method based on empirical wavelet transform described above are performed.
[0020] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the planetary gearbox fault diagnosis method based on empirical wavelet transform as described above.
[0021] Implementing the embodiments of the present invention will have the following beneficial effects: By acquiring the structural parameters of each component within the planetary gearbox under test, and determining the fault characteristic frequency and meshing frequency of each component based on these parameters, the number of initial frequency bands is calculated based on the fault characteristic frequency and meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox under test is divided using the minimum value method to obtain the initial frequency bands. A comprehensive fault index for the initial frequency band is calculated using the cross-correlation coefficient between the component signals and the original signal in the initial frequency band, the kurtosis value of the component signals in the initial frequency band, and a fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. Finally, the initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When dividing the frequency band, the boundaries of the initial frequency band are reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The signal spectrum is then subjected to EWT transformation based on the target frequency band to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain fault conclusions for each component within the planetary gearbox under test. This improves the adaptability and accuracy of the original EWT frequency band division, ensuring the effectiveness of the decomposed fault frequency band in noise interference and weak fault application scenarios. It also avoids the possibility that incorrect component selection will result in the components not containing fault impact signals. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0023] in: Figure 1 This is a flowchart of a planetary gearbox fault diagnosis method based on empirical wavelet transform provided in an embodiment of this application; Figure 2 This is a time-domain waveform of the fault vibration signal in a planetary gearbox fault diagnosis method based on empirical wavelet transform provided in an embodiment of this application. Figure 3 This is an initial boundary partitioning result diagram in a planetary gearbox fault diagnosis method based on empirical wavelet transform provided in an embodiment of this application; Figure 4 This is a boundary partitioning result diagram of the improved EWT in a planetary gearbox fault diagnosis method based on empirical wavelet transform provided in an embodiment of this application; Figure 5 This is the envelope spectrum result diagram in the planetary gearbox fault diagnosis method based on empirical wavelet transform provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of a planetary gearbox fault diagnosis device based on empirical wavelet transform provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of a storage medium provided in an embodiment of this application. Detailed Implementation
[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0025] like Figure 1 As shown, this application provides a planetary gearbox fault diagnosis method based on empirical wavelet transform, including: S101. Obtain the structural parameters of each component in the planetary gearbox to be tested, and determine the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters. S102. Calculate the initial number of frequency bands based on the fault characteristic frequency and the meshing frequency, and divide the signal spectrum of the planetary gearbox to be tested according to the initial number of frequency bands by using the minimum value method to obtain the initial frequency bands; S103. Calculate the comprehensive fault index of the initial frequency band by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. S104. Determine whether the initial frequency band is a faulty frequency band based on the comprehensive fault index, and when the initial frequency band is a faulty frequency band, reconstruct the boundary of the initial frequency band according to the comprehensive fault index and the preset boundary merging rule to obtain the target frequency band, and perform EWT transformation on the signal spectrum according to the target frequency band to obtain the target EWT component signal. S105. Calculate the IMF kurtosis value of each target EWT component signal, and select the target EWT component signal with the largest IMF kurtosis value as the sensitive EWT component signal. Perform envelope spectrum analysis on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0026] By acquiring the structural parameters of each component within the planetary gearbox under test, and determining the fault characteristic frequency and meshing frequency of each component based on these parameters, the number of initial frequency bands is calculated based on the fault characteristic frequency and meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox under test is divided using the minimum value method to obtain the initial frequency bands. A comprehensive fault index for the initial frequency band is calculated using the cross-correlation coefficient between the component signals and the original signal in the initial frequency band, the kurtosis value of the component signals in the initial frequency band, and a fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. Finally, the initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When dividing the frequency band, the boundaries of the initial frequency band are reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The signal spectrum is then subjected to EWT transformation based on the target frequency band to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain fault conclusions for each component within the planetary gearbox under test. This improves the adaptability and accuracy of the original EWT frequency band division, ensuring the effectiveness of the decomposed fault frequency band in noise interference and weak fault application scenarios. It also avoids the possibility that incorrect component selection will result in the components not containing fault impact signals.
[0027] In one possible implementation, the components within the planetary gearbox to be tested include a sun gear, planet gears, and a ring gear. The step of determining the fault characteristic frequency and meshing frequency of each component within the planetary gearbox to be tested based on the structural parameters includes: The meshing frequency is determined based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the absolute rotational frequency of the sun gear, among the structural parameters mentioned above. The fault characteristic frequency of the sun gear in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of planet gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the planetary gears in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of teeth on the planetary gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the internal gear ring of the planetary gearbox under test is calculated based on the number of teeth on the gear ring, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the number of planet gears in the structural parameters.
[0028] For example, through the formula:
[0029]
[0030]
[0031]
[0032] Determine the fault characteristic frequencies and meshing frequencies of each component in the planetary gearbox to be tested; Specifically, Given the meshing frequency, the rotational speed of the input shaft (sun gear shaft) of the planetary gearbox is... , For planetary carrier frequency switching, The absolute rotational frequency of the sun gear. This represents the number of teeth on the gear ring. The number of teeth on the sun gear. Where N is the number of teeth on the planetary gears, and N is the total number of planetary gears. The characteristic frequency of sun gear failure. The characteristic frequency of planetary gear failure. The fault characteristic frequency of the gear ring is given.
[0033] In one possible implementation, the step of dividing the signal spectrum of the planetary gearbox to be detected into initial frequency bands using the minimum value method based on the initial number of frequency bands includes: Envelope operation is performed on the signal spectrum of the planetary gearbox to be tested to obtain the envelope map; The envelope spectrum is divided using a minimum method based on the number of initial frequency bands to obtain the initial frequency bands.
[0034] For example, an envelope operation is performed on the signal spectrum, and the minimum value method is used as the boundary to divide the initial frequency band. Specifically, the selection of the minimum value of the envelope line needs to satisfy the following: [Selection based on the minimum value of the envelope line] A boundary, NN The initial number of frequency bands; the difference between the selected minimum and the adjacent envelope maximum satisfies the maximum; In one possible implementation, the step of calculating the comprehensive fault index of the initial frequency band using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band includes: The formula for calculating the cross-correlation coefficient is as follows:
[0035] Calculate the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, where, Component signal With the original signal cross-correlation coefficients, Where n is the length of the signal, and n is the index. and The original signals are respectively and component signals The mean; The formula for calculating the kurtosis value of a component signal is as follows:
[0036] Calculate the kurtosis values of the component signals in the initial frequency band, where, This represents the kurtosis value of the component signal; Calculation formula based on fault characteristic indicators:
[0037] Calculate fault characteristic indices based on theoretical fault characteristic frequencies and envelope spectrum amplitudes in the initial frequency band, where, FFI As a fault characteristic indicator, This represents the amplitude of the envelope spectrum in the initial frequency band. S represents the theoretical fault characteristic frequency, and S represents the envelope spectrum. The comprehensive fault index calculation formula is as follows:
[0038] Calculate the comprehensive fault index of the initial frequency band.
[0039] For example, the cross-correlation coefficient illustrates the similarity between the component signal and the original fault signal. The larger the cross-correlation value of the component signal, the more original fault information it contains. The larger the kurtosis value, the more severe the impact generated in the signal. The larger the fault characteristic index value, the more fault impact components the envelope demodulated component signal contains.
[0040] In one possible implementation, the step of reconstructing the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band includes: The mathematical representation of the preset boundary merging rule is as follows:
[0041] in, Let i be the average comprehensive fault index of N component signals, where i represents the i-th signal component among the N component signals.
[0042] In one possible implementation, the step of performing EWT transform on the signal spectrum according to the target frequency band to obtain the target EWT component signal includes: The target EWT component signal is obtained by performing EWT transformation on the signal spectrum based on the boundary data of the target frequency band.
[0043] For example, the improved EWT boundary is constructed using the initial boundary merging rule as follows:
[0044] in, Let i be the average comprehensive fault index of N component signals, where i is the i-th signal component of the N component signals.
[0045] The improved EWT component signal is obtained by performing an EWT transform on the original signal using the frequency band formed by the improved EWT boundary, as follows: The signal spectrum is divided into M components using EWT, as follows:
[0046] In the formula Therefore A bandpass filter with boundary conditions, where .
[0047] In one possible implementation, the step of determining whether the initial frequency band is a faulty frequency band based on the comprehensive fault index includes: The comprehensive fault index is matched with the comprehensive threshold. If the comprehensive fault index is greater than or equal to the preset threshold, the initial frequency band is determined to be a fault frequency band. If the comprehensive fault index is less than the preset threshold, then the cross-correlation coefficient is matched with the cross-correlation threshold, the kurtosis value is matched with the kurtosis value threshold, and the fault feature index is matched with the fault feature threshold. When the cross-correlation coefficient is greater than or equal to the cross-correlation threshold, and / or the kurtosis value is greater than or equal to the kurtosis value threshold, and / or the fault characteristic index is greater than or equal to the fault characteristic threshold, the initial frequency band is determined to be a fault frequency band.
[0048] This application provides a specific embodiment of a planetary gearbox fault diagnosis method based on empirical wavelet transform. Specifically, a planetary gearbox fault diagnosis experimental platform is constructed, and the structural parameters of the planetary gearbox are shown in Table 1. A portion of a tooth on the sun gear is removed using wire cutting technology to represent the fault. During the experiment, the faulty sun gear is installed inside the planetary gearbox, and experimental data is collected. Accelerometers are installed at vertical, horizontal, and axial measuring points on the planetary gearbox housing. The motor input speed is 1800 r / min, the data sampling frequency is set to 12800 Hz, and the sampling duration is 2 s.
[0049] Table 1. Gear parameters in the planetary gearbox (unit: gear)
[0050] The vibration signal of the planetary gearbox in the fault diagnosis test bench was collected using an accelerometer, and the result was as follows: Figure 2 The time-domain waveform is shown below. Figure 2 It is evident that regular periodic impact characteristics are difficult to observe in the time-domain waveform of the vibration signal, while the amplitudes of noise and other irrelevant interference frequencies are more prominent. Therefore, traditional time-domain analysis methods cannot extract characteristic information representing the health status of the gearbox from the original fault signal.
[0051] Calculate the fault characteristic frequencies and meshing frequencies of the corresponding parts based on the structural parameters of the planetary gearbox. According to Table 1 and the calculation formula below, the characteristic frequency of sun gear failure can be obtained. The meshing frequency is 341.25 Hz.
[0052]
[0053]
[0054]
[0055]
[0056] In the above formula, the rotational speed of the input shaft of the planetary gearbox, i.e., the sun gear shaft, is: , For planetary carrier frequency switching, The absolute rotational frequency of the sun gear. This represents the number of teeth on the gear ring. The number of teeth on the sun gear. Where N is the number of teeth on the planetary gears, and N is the total number of planetary gears. The characteristic frequency of sun gear failure. The characteristic frequency of planetary gear failure. The fault characteristic frequency of the gear ring is given.
[0057] Calculate the number of initial frequency bands This ensures that the resonant frequency band of the meshing frequency is preserved to the maximum extent. An envelope operation is performed on the signal spectrum, and the initial frequency band is delineated using the minimum value method as the boundary. The selection of the minimum value of the envelope line must meet the following conditions: [The selection is based on the minimum value of the envelope line.] The boundary condition is met; the difference between the selected minimum and the adjacent maximum of the envelope is maximized. The initial number of frequency bands is calculated as N = 12800 / (4 78.75)≈40, resulting in the following: Figure 3 The initial boundary delineation result is shown in the figure.
[0058] Calculate the comprehensive fault index of the initial frequency band signal to distinguish between faulty and non-faulty frequency bands in the initial frequency band; the formula is as follows;
[0059]
[0060]
[0061]
[0062] in, The theoretical fault characteristic frequency; Component signal With the original signal cross-correlation coefficients, The cross-correlation coefficient represents the length of the signal. It indicates the similarity between the component signal and the original fault signal. The larger the cross-correlation coefficient of the component signal, the more original fault information it contains. This represents the kurtosis value of the component signal; the larger the kurtosis value, the more severe the impact generated in the signal. In the fault feature index (FFI)... This represents the amplitude of the envelope spectrum in the frequency band. The larger the value, the more fault impact components are contained in the component signal of the envelope demodulation.
[0063] An improved EWT boundary is constructed based on the boundary merging rule. The signal is then subjected to EWT transform to obtain the empirical wavelet component signal, such as... Figure 4As shown. The formula is as follows:
[0064] in, This is the average comprehensive failure index.
[0065] The kurtosis value of each component is calculated, and the component with the largest kurtosis value is selected as the sensitive component for envelope spectrum analysis to draw a fault conclusion. From step S5, it can be seen that EWT decomposes into 6 components. The component with the largest kurtosis value is selected as the sensitive component for envelope spectrum analysis, yielding the following results: Figure 5 The results show that the fault characteristic frequency of the sun gear can be clearly observed, indicating that the fault is caused by the sun gear.
[0066] Secondly, such as Figure 6 As shown, this application provides a planetary gearbox fault diagnosis device based on empirical wavelet transform, the device comprising: The basic calculation module 201 is used to obtain the structural parameters of each component in the planetary gearbox to be tested, and to determine the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters. The segmentation module 202 is used to calculate the number of initial frequency bands based on the fault characteristic frequency and the meshing frequency, and to segment the signal spectrum of the planetary gearbox to be tested according to the number of initial frequency bands by using the minimum value method to obtain the initial frequency bands; The first calculation module 203 is used to calculate the comprehensive fault index of the initial frequency band by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The transformation module 204 is used to determine whether the initial frequency band is a faulty frequency band based on the comprehensive fault index, and when the initial frequency band is a faulty frequency band, to reconstruct the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band, and to perform EWT transformation on the signal spectrum based on the target frequency band to obtain the target EWT component signal; The second calculation module 205 is used to calculate the IMF kurtosis value of each target EWT component signal, and select the target EWT component signal with the largest IMF kurtosis value as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0067] In one possible implementation, such as Figure 7As shown, this application embodiment provides an electronic device 300, including: a memory 310, a processor 320, and a first computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the first computer program 311, it performs the following: acquiring the structural parameters of each component in the planetary gearbox to be tested, and determining the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters. The number of initial frequency bands is calculated based on the fault characteristic frequency and the meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox to be tested is divided using the minimum value method to obtain the initial frequency bands. The comprehensive fault index of the initial frequency band is calculated by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When the initial frequency band is a faulty frequency band, the boundary of the initial frequency band is reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The target frequency band is then used to perform EWT transformation on the signal spectrum to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0068] In one possible implementation, such as Figure 8 As shown, this application embodiment provides a computer-readable storage medium 400, on which a second computer program 411 is stored. When the second computer program 411 is executed by a processor, it performs the following: acquiring the structural parameters of each component in the planetary gearbox to be tested, and determining the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters. The number of initial frequency bands is calculated based on the fault characteristic frequency and the meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox to be tested is divided using the minimum value method to obtain the initial frequency bands. The comprehensive fault index of the initial frequency band is calculated by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When the initial frequency band is a faulty frequency band, the boundary of the initial frequency band is reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The target frequency band is then used to perform EWT transformation on the signal spectrum to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
[0069] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0070] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
[0071] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.
[0072] Computer program code for performing the operations of this invention can be written in one or more programming languages or a combination thereof. These programming languages include object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0073] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.
[0074] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.
[0075] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.
Claims
1. A fault diagnosis method for planetary gearboxes based on empirical wavelet transform, characterized in that, include: Obtain the structural parameters of each component in the planetary gearbox to be tested, and determine the fault characteristic frequency and meshing frequency of each component in the planetary gearbox to be tested based on the structural parameters. The number of initial frequency bands is calculated based on the fault characteristic frequency and the meshing frequency. Then, based on the number of initial frequency bands, the signal spectrum of the planetary gearbox to be tested is divided using the minimum value method to obtain the initial frequency bands. The comprehensive fault index of the initial frequency band is calculated by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The initial frequency band is determined to be a faulty frequency band based on the comprehensive fault index. When the initial frequency band is a faulty frequency band, the boundary of the initial frequency band is reconstructed according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band. The target frequency band is then used to perform EWT transformation on the signal spectrum to obtain the target EWT component signal. The IMF kurtosis value of each target EWT component signal is calculated, and the target EWT component signal with the largest IMF kurtosis value is selected as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
2. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The components within the planetary gearbox to be tested include a sun gear, planet gears, and a ring gear. The step of determining the fault characteristic frequencies and meshing frequencies of each component within the planetary gearbox to be tested based on the structural parameters includes: The meshing frequency is determined based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the absolute rotational frequency of the sun gear, among the structural parameters mentioned above. The fault characteristic frequency of the sun gear in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of planet gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the planetary gears in the planetary gearbox to be tested is calculated based on the number of teeth on the ring gear, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, the number of teeth on the planetary gears, and the meshing frequency in the structural parameters. The fault characteristic frequency of the internal gear ring of the planetary gearbox under test is calculated based on the number of teeth on the gear ring, the number of teeth on the sun gear, the rotational speed of the sun gear shaft, and the number of planet gears in the structural parameters.
3. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The step of dividing the signal spectrum of the planetary gearbox to be detected into initial frequency bands using the minimum value method based on the initial number of frequency bands includes: Envelope operation is performed on the signal spectrum of the planetary gearbox to be tested to obtain the envelope map; The envelope spectrum is divided using a minimum method based on the number of initial frequency bands to obtain the initial frequency bands.
4. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The step of calculating the comprehensive fault index of the initial frequency band using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band includes: The formula for calculating the cross-correlation coefficient is as follows: Calculate the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, where, Component signal With the original signal cross-correlation coefficients, Where n is the length of the signal, and n is the index. and The original signals are respectively and component signals The mean; The formula for calculating the kurtosis value of a component signal is as follows: Calculate the kurtosis values of the component signals in the initial frequency band, where, This represents the kurtosis value of the component signal; Calculation formula based on fault characteristic indicators: Calculate fault characteristic indices based on theoretical fault characteristic frequencies and envelope spectrum amplitudes in the initial frequency band, where, FFI As a fault characteristic indicator, This represents the amplitude of the envelope spectrum in the initial frequency band. S represents the theoretical fault characteristic frequency, and S represents the envelope spectrum. The comprehensive fault index calculation formula is as follows: Calculate the comprehensive fault index of the initial frequency band.
5. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The step of reconstructing the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band includes: The mathematical representation of the preset boundary merging rule is as follows: in, Let i be the average comprehensive fault index of N component signals, where i represents the i-th signal component among the N component signals.
6. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The step of performing EWT transform on the signal spectrum according to the target frequency band to obtain the target EWT component signal includes: The target EWT component signal is obtained by performing EWT transformation on the signal spectrum based on the boundary data of the target frequency band.
7. The planetary gearbox fault diagnosis method based on empirical wavelet transform as described in claim 1, characterized in that, The step of determining whether the initial frequency band is a faulty frequency band based on the comprehensive fault index includes: The comprehensive fault index is matched with the comprehensive threshold. If the comprehensive fault index is greater than or equal to the preset threshold, the initial frequency band is determined to be a fault frequency band. If the comprehensive fault index is less than the preset threshold, then the cross-correlation coefficient is matched with the cross-correlation threshold, the kurtosis value is matched with the kurtosis value threshold, and the fault feature index is matched with the fault feature threshold. When the cross-correlation coefficient is greater than or equal to the cross-correlation threshold, and / or the kurtosis value is greater than or equal to the kurtosis value threshold, and / or the fault characteristic index is greater than or equal to the fault characteristic threshold, the initial frequency band is determined to be a fault frequency band.
8. A planetary gearbox fault diagnosis device based on empirical wavelet transform, characterized in that, The device includes: The basic calculation module is used to obtain the structural parameters of each component in the planetary gearbox under test, and to determine the fault characteristic frequency and meshing frequency of each component in the planetary gearbox under test based on the structural parameters. The partitioning module is used to calculate the number of initial frequency bands based on the fault characteristic frequency and the meshing frequency, and to partition the signal spectrum of the planetary gearbox to be tested according to the number of initial frequency bands by using the minimum value method to obtain the initial frequency bands; The first calculation module is used to calculate the comprehensive fault index of the initial frequency band by using the cross-correlation coefficient between the component signals in the initial frequency band and the original signal, the kurtosis value of the component signals in the initial frequency band, and the fault characteristic index based on the theoretical fault characteristic frequency and the envelope spectrum amplitude in the initial frequency band. The transformation module is used to determine whether the initial frequency band is a faulty frequency band based on the comprehensive fault index, and when the initial frequency band is a faulty frequency band, to reconstruct the boundary of the initial frequency band according to the comprehensive fault index and a preset boundary merging rule to obtain the target frequency band, and to perform EWT transformation on the signal spectrum based on the target frequency band to obtain the target EWT component signal; The second calculation module is used to calculate the IMF kurtosis value of each target EWT component signal, and select the target EWT component signal with the largest IMF kurtosis value as the sensitive EWT component signal. Envelope spectrum analysis is performed on the sensitive EWT component signal to obtain the fault conclusion for each component in the planetary gearbox to be tested.
9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the planetary gearbox fault diagnosis method based on empirical wavelet transform as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the planetary gearbox fault diagnosis method based on empirical wavelet transform as described in any one of claims 1 to 7.