Gearbox fault diagnosis methods, devices, storage media and equipment

Abstract

This disclosure relates to a method, apparatus, storage medium, and device for gearbox fault diagnosis. The method includes: decomposing the original signal acquired from the gearbox into multiple modal components corresponding to the number of decompositions using variational mode decomposition (MODE). Based on the multiple modal components corresponding to each number of decompositions, an optimal number of decompositions is determined. From the multiple modal components corresponding to the optimal number of decompositions, the modal component with the largest convexity factor is determined as the target modal component, where the convexity factor characterizes the steepness of the modal component. Based on the envelope spectrum amplitude of the target modal component, it is determined whether a fault exists in the gearbox. This method accurately determines the number of decompositions for variational mode decomposition, avoids over- or under-decomposing the original gearbox signal, and can be effectively used for extracting gearbox fault characteristic frequencies, thereby accurately diagnosing gearbox faults.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data analysis, in particular, to a gear box fault judgment method and device, a storage medium and equipment. BACKGROUND

[0002] The planetary gear box is widely used in various transmission systems such as aviation, engineering machinery and wind power generation. Due to its complex working environment and surface bearing alternating load, the failure rate is high. It is of great significance to carry out fault diagnosis and monitoring on the planetary gear box to ensure the normal work and safe operation of the mechanical system. In the related technology, the fault diagnosis and monitoring of the gear box are often completed by analyzing the fault characteristic frequency.

[0003] In actual engineering application, the vibration signal of the planetary gear box is the coupling of multiple excitation factors, and its frequency component is very complex, which not only contains the rotation frequency of each component, the meshing frequency of the gear pair and its multiple frequency, but also contains the natural frequency excited by the equipment. The planetary gear not only meshes with the sun gear, but also meshes with other planetary gears. This meshing mode causes some characteristic frequencies to be very low. The relative position of the planetary gear to the sensor changes with the operation, and the vibration transmission path also changes constantly. Installation and manufacturing errors, planetary gear through effect, etc. will cause amplitude or frequency modulation of the signal, resulting in complex side frequency band. In addition, the influence of environmental noise, the fault characteristic frequency is easy to be submerged, thereby bringing great difficulty to the fault diagnosis of the gear box. SUMMARY

[0004] The purpose of the present disclosure is to provide a gear box fault judgment method, device, storage medium and equipment to solve the above technical problems.

[0005] To achieve the above purpose, in a first aspect, the present disclosure provides a gear box fault judgment method, comprising:

[0006] For each of the plurality of decomposition numbers, the original signal collected from the gear box is decomposed into a plurality of modal components corresponding to the decomposition number by a variational mode decomposition method;

[0007] Based on the plurality of modal components corresponding to each of the decomposition numbers, the optimal decomposition number is determined;

[0008] From the plurality of modal components corresponding to the optimal decomposition number, a modal component with the maximum convex flatness factor is determined as a target modal component, and the convex flatness factor represents the steepness of the modal component;

[0009] According to the envelope spectrum amplitude of the target modal component, it is determined whether the gear box has a fault.

[0010] Optionally, the decomposing the original signal collected from the gearbox into a plurality of modal components corresponding to the decomposition number by the variational modal decomposition method comprises:

[0011] The original signal is decomposed into a plurality of modal components corresponding to the decomposition number for any of the decomposition numbers;

[0012] The Fourier spectrum and the center frequency of each of the modal components are iteratively updated by an alternating multiplier method;

[0013] In a case where the Fourier spectrum and the center frequency of each of the modal components converge, a plurality of final modal components are obtained.

[0014] Optionally, the determining an optimal decomposition number based on the plurality of modal components corresponding to each of the decomposition numbers comprises:

[0015] For any of the decomposition numbers, a quality value of each of the modal components corresponding to the decomposition number is calculated according to the modal component;

[0016] A variation corresponding to the decomposition number is calculated according to the quality value of each of the modal components, the variation representing stability of the quality values of the plurality of modal components;

[0017] The decomposition number with the minimum variation is selected as the optimal decomposition number.

[0018] Optionally, the calculating the quality value of each of the modal components corresponding to the decomposition number according to the modal component comprises:

[0019] A maximum center frequency and a minimum center frequency in the plurality of modal components corresponding to the decomposition number are determined;

[0020] A target bandwidth is obtained according to a difference between the maximum center frequency and the minimum center frequency;

[0021] For each of the modal components, a ratio of the center frequency corresponding to the modal component to the target bandwidth is calculated as the quality value of the modal component.

[0022] Optionally, the calculating the variation corresponding to the decomposition number according to the quality value of each of the modal components comprises:

[0023] A difference between the quality values of each of two adjacent modal components is calculated;

[0024] The variation corresponding to the decomposition number is calculated according to the difference between the quality values of each of two adjacent modal components.

[0025] Optionally, the method further comprises: determining, from the plurality of modal components corresponding to the optimal decomposition number, a modal component with a maximum convexity factor as a target modal component, wherein the convexity factor represents a steepness of the modal component.

[0026] For each of the modal components corresponding to the optimal decomposition number, the method further comprises: calculating a fourth-order central moment and a variance corresponding to the modal component.

[0027] The method further comprises: calculating a ratio of the fourth-order central moment to a square of the variance as the convexity factor corresponding to the modal component.

[0028] Optionally, the method further comprises: determining, according to an envelope spectrum amplitude of the target modal component, whether the gearbox has a fault.

[0029] The method further comprises: obtaining a corresponding envelope spectrum based on a Fourier spectrum of the target modal component, and determining a fault characteristic frequency according to a frequency corresponding to a maximum amplitude in the envelope spectrum.

[0030] The method further comprises: determining that the gearbox has a fault if the fault characteristic frequency is not within a preset frequency range.

[0031] In a second aspect, the present disclosure provides a gearbox fault determination device, comprising:

[0032] A variational modal decomposition module is configured to decompose, by a variational modal decomposition method, an original signal collected from a gearbox into a plurality of modal components corresponding to a plurality of decomposition numbers respectively.

[0033] An optimal number solving module is configured to determine an optimal decomposition number based on the plurality of modal components corresponding to each of the decomposition numbers.

[0034] A target component determining module is configured to determine, from the plurality of modal components corresponding to the optimal decomposition number, a modal component with a maximum convexity factor as a target modal component, wherein the convexity factor represents a steepness of the modal component.

[0035] A fault analysis module is configured to determine, according to an envelope spectrum amplitude of the target modal component, whether the gearbox has a fault.

[0036] In a third aspect, the present disclosure provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of the method of the first aspect.

[0037] In a fourth aspect, the present disclosure provides an electronic device, comprising:

[0038] A memory having a computer program stored thereon.

[0039] a processor configured to execute the computer program in the memory to implement the steps of the method of the first aspect.

[0040] In the technical solution, the original signal of the gearbox is decomposed into a plurality of modal components corresponding to a plurality of decomposition numbers respectively, and then the optimal decomposition number is found based on the plurality of modal components corresponding to each decomposition number. In this way, different original signals can be adaptively decomposed to accurately decompose different original signals into corresponding modal components, which can avoid over-decomposing or under-decomposing the original signal of the gearbox, can be effectively used for extracting the fault feature frequency of the gearbox, and thus can accurately judge the fault of the gearbox.

[0041] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0042] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, which together with the following detailed description, serve to explain the present disclosure. In the drawings:

[0043] Figure 1 A flow chart of a gearbox fault judgment method provided by an example embodiment is shown;

[0044] Figure 2 A flow chart of a specific implementation of step S110 in an example embodiment is shown;

[0045] Figure 3 A flow chart of a specific implementation of step S120 in an example embodiment is shown;

[0046] Figure 4 A flow chart of a specific implementation of step S121 in an example embodiment is shown;

[0047] Figure 5 A schematic diagram of a gearbox fault judgment device provided by an example embodiment is shown;

[0048] Figure 6 A block diagram of an electronic device provided by an example embodiment is shown. DETAILED DESCRIPTION

[0049] The specific implementation of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0050] It should be noted that all the actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the corresponding data protection regulations and policies of the country where the device is located, and with the authorization given by the corresponding device owner.

[0051] In the related art, the fault diagnosis and monitoring of the gearbox are often completed by analyzing the fault characteristic frequency, and the extraction of the fault characteristic frequency is often realized by a variational mode decomposition (VMD). However, the decomposition number of VMD is often artificially set and has certain instability. When the decomposition number is too large, the high and low components will be fused, affecting the extraction of the fault characteristic frequency; when the decomposition number is too small, the components with specific sparse characteristics cannot be decomposed, so it is particularly important to control the decomposition number of VMD.

[0052] Therefore, the present disclosure provides a gearbox fault judgment method, which accurately controls the decomposition number of VMD, avoids excessive or insufficient decomposition of the original signal of the gearbox, and can accurately identify the fault characteristic frequency of the gearbox.

[0053] Figure 1 A flowchart of a gearbox fault judgment method provided by an example embodiment is shown. As shown in the figure, Figure 1 The method comprises:

[0054] S110, for a plurality of decomposition numbers, respectively, the original signal collected from the gearbox is decomposed into a plurality of modal components corresponding to the decomposition number by a variational mode decomposition method.

[0055] The decomposition number is a positive integer, and the original signal is decomposed into several modal components when the decomposition number is several. According to the empirical value, when the decomposition number is a positive integer not greater than 10, the effect of the decomposed modal component is best. For example, if the decomposition number is set to 2, the original signal collected from the gearbox is decomposed into 2 modal components by the variational mode decomposition method.

[0056] Specifically, the plurality of decomposed modal components are discrete, and are modal components with specific sparse properties in the bandwidth in the frequency domain, and each modal component is a limited bandwidth with a center frequency. The essence of variational mode decomposition is to find each modal component with the smallest bandwidth sum under the constraint that the sum of each modal component is equal to the original signal.

[0057] In an optional embodiment, all the modal components decomposed include a modal component representing an effective signal and a modal component representing noise, wherein a modal component similar to the original signal is determined as the modal component representing the effective signal, and a modal component greatly different from the original signal is determined as the modal component representing the noise. The modal component representing the noise is removed, and the remaining modal components representing the effective signal are taken as the plurality of modal components corresponding to the decomposition number, and only the remaining modal components representing the effective signal are processed in a subsequent step, so as to achieve the effect of noise reduction.

[0058] In S120, the optimal decomposition number is determined based on the plurality of modal components corresponding to each decomposition number.

[0059] The optimal decomposition number is determined to adaptively determine the decomposition number of the modal components of the variational modal decomposition, to accurately extract the fault feature frequency of the gearbox, and further accurately determine the fault of the gearbox. The modal components corresponding to the optimal decomposition number can better analyze the fault feature frequency of the gearbox.

[0060] In S130, one modal component with the maximum convex flatness factor is determined from the plurality of modal components corresponding to the optimal decomposition number as a target modal component, and the convex flatness factor represents the steepness of the modal component.

[0061] For each modal component corresponding to the optimal decomposition number, a corresponding convex flatness factor is calculated, which represents the steepness of the corresponding modal component. The larger the convex flatness factor, the steeper the corresponding modal component, and the greater the possibility of the occurrence of the fault of the gearbox. Therefore, the modal component with the maximum convex flatness factor is selected as the target modal component for the extraction of the fault feature frequency.

[0062] In a specific implementation, the above step S130 includes: for each modal component corresponding to the optimal decomposition number, calculating a fourth-order central moment and a variance corresponding to the modal component; and calculating a ratio of the fourth-order central moment to the square of the variance as the convex flatness factor corresponding to the modal component.

[0063] Specifically, the calculation formula of the convex flatness factor C is as follows:

[0064]

[0065] The modal component is a discrete signal composed of a plurality of discrete points; in the formula, C i represents the convex flatness factor of the i-th modal component in the plurality of modal components corresponding to the optimal decomposition number, and m represents the number of discrete points in the i-th modal component in the modal component; x t represents the vibration amplitude corresponding to the t-th discrete point in the i-th modal component in the modal component; represents the average vibration amplitude of all discrete points in the i-th modal component in the modal component.

[0066] S140, determining whether the gearbox has a fault according to the envelope spectrum amplitude of the target modal component.

[0067] In a specific implementation, step S140 includes: obtaining a corresponding envelope spectrum based on the Fourier spectrum of the target modal component, and determining a fault characteristic frequency according to a frequency corresponding to a maximum amplitude in the envelope spectrum; and determining that the gearbox has a fault if the fault characteristic frequency is not within a preset frequency range. The preset frequency range represents a range of normal frequencies of the gearbox.

[0068] In an optional embodiment, after obtaining a corresponding envelope spectrum based on the Fourier spectrum of the target modal component, it is determined whether a maximum amplitude in the envelope spectrum is outside a preset amplitude range, where the preset amplitude range represents a normal amplitude range. If the maximum amplitude in the envelope spectrum is outside the preset amplitude range, the frequency corresponding to the maximum amplitude in the envelope spectrum is determined as the fault characteristic frequency.

[0069] It should be understood that the preset amplitude range and the preset frequency range can be flexibly set according to actual needs or set according to empirical values.

[0070] In the above technical solution, the original signal of the gearbox is first decomposed into a corresponding number of modal components for each decomposition number, and then the optimal decomposition number is found based on the modal components corresponding to each decomposition number. This can adaptively decompose different original signals to accurately decompose different original signals into a corresponding number of modal components, which can avoid over-decomposing or under-decomposing the original signal of the gearbox, and can be effectively used for extracting the fault characteristic frequency of the gearbox, thereby accurately judging the fault of the gearbox.

[0071] Figure 2 A flowchart showing the specific implementation of step S110 in an example embodiment is shown. As shown in Figure 2 the method includes:

[0072] S111, for any decomposition number, decomposing the original signal into a plurality of modal components corresponding to the decomposition number.

[0073] S112, updating the Fourier spectrum and the center frequency of each modal component by alternating multiplier method iteration.

[0074] For example, the Fourier spectrum U i (ω) and the center frequency ω i of each modal component are updated by alternating multiplier method iteration, and the formula is as follows:

[0075]

[0076]

[0077] wherein i represents the i-th modal component in the plurality of modal components corresponding to the decomposition number, j represents the j-th modal component in the plurality of modal components corresponding to the decomposition number, a represents a penalty factor, and ω represents a frequency, ω n+1 i represents the center frequency of the i-th modal component after the n+1 iteration, X n+1 i represents the Fourier spectrum of the i-th modal component after the n+1 iteration, X(ω) represents the Fourier spectrum of the original signal, and λ(ω) represents the Fourier spectrum of the Lagrange penalty factor.

[0078] S113, obtaining the final plurality of modal components in a case where the Fourier spectrum and the center frequency of each modal component converge.

[0079] As can be seen from the above process, the iteration optimization is performed by the alternating multiplier method, and each modal component with the converged Fourier spectrum and center frequency is obtained through continuous iteration, so as to obtain the decomposition result of the current variational modal decomposition.

[0080] Figure 3 A flow chart showing the specific implementation of step S120 in an example embodiment is shown. As shown in the flow chart, Figure 3 the method comprises:

[0081] S121, for any decomposition number, calculating the quality value of each modal component according to the modal component corresponding to the decomposition number.

[0082] The quality value reflects the resonance degree of the modal component signal, and the greater the quality value, the better the frequency aggregation of the modal component signal, and the higher the resonance property.

[0083] S122, calculating the variation corresponding to the decomposition number according to the quality value of each modal component, the variation representing the stability of the quality values of the plurality of modal components.

[0084] The size of the variation reflects the stability of the group of modal component data.

[0085] In the specific implementation, the above step S122 comprises: calculating the difference value of the quality values of each adjacent two modal components; and calculating the variation corresponding to the decomposition number according to the difference value of the quality values of each adjacent two modal components.

[0086] Specifically, the variation S k is calculated according to the following formula:

[0087]

[0088] wherein k represents the decomposition number of the variational mode decomposition, i represents the i-th mode component in the plurality of mode components corresponding to the decomposition number, Q i represents the quality value of the i-th mode component in the plurality of mode components corresponding to the decomposition number, Q i+1 represents the quality value of the i-th mode component in the plurality of mode components corresponding to the decomposition number, Q i represents the quality value of the adjacent next mode component.

[0089] S123, selecting the decomposition number with the minimum variation as the optimal decomposition number.

[0090] Since the variation is used to measure the stability of the group of mode component data, the optimal decomposition number is the decomposition number corresponding to the most stable group of mode component data.

[0091] From the above process, by selecting the decomposition number corresponding to the most stable group of mode components, the optimal value of the decomposition number of the variational mode decomposition can be adaptively determined, and the optimal mode component of the variational mode decomposition can be obtained, which can be further effectively used for extracting the fault feature frequency of the gearbox.

[0092] Figure 4 A flow chart showing the specific implementation of step S121 in an example embodiment is shown. As Figure 4 shown, the method comprises:

[0093] S1211, determining the maximum center frequency and the minimum center frequency in the plurality of mode components corresponding to the decomposition number according to the plurality of mode components.

[0094] S1212, obtaining the target bandwidth according to the difference between the maximum center frequency and the minimum center frequency.

[0095] wherein the calculation formula of the target bandwidth BW is as follows:

[0096] BW = ω max - ω min

[0097] wherein ω max represents the maximum center frequency in the plurality of mode components corresponding to the decomposition number; and ω min represents the minimum center frequency in the plurality of mode components corresponding to the decomposition number.

[0098] S1213, calculating the ratio of the center frequency corresponding to each mode component to the target bandwidth as the quality value of the mode component.

[0099] wherein the calculation formula of the quality value Q i is as follows:

[0100]

[0101] ωi= ω0+ (i- 1) BW Q i ωi= ω0+ (i- 1) BW Q i ωi= ω0+ (i- 1) BW Q

[0102] From the above process, by calculating the ratio of the center frequency of each modal component corresponding to the target bandwidth, the quality value of each modal component is obtained, which can provide accurate data for subsequent calculation of variation.

[0103] Figure 5 A schematic diagram of a gearbox fault judgment device provided by an example embodiment is shown. As shown in the figure, the gearbox fault judgment device 500 includes a variational mode decomposition module 510, an optimal number solving module 520, a target component determining module 530, and a fault analysis module 540. Figure 5

[0104] The variational mode decomposition module 510 is configured to decompose the original signal collected from the gearbox into a plurality of modal components corresponding to each decomposition number by using the variational mode decomposition method.

[0105] The optimal number solving module 520 is configured to determine the optimal decomposition number based on the plurality of modal components corresponding to each decomposition number.

[0106] The target component determining module 530 is configured to determine a modal component with the largest convexity factor from the plurality of modal components corresponding to the optimal decomposition number as the target modal component, wherein the convexity factor represents the steepness of the modal component.

[0107] The fault analysis module 540 is configured to determine whether the gearbox has a fault according to the envelope spectrum amplitude of the target modal component.

[0108] Optionally, the variational mode decomposition module 510 is further configured to decompose the original signal into a plurality of modal components corresponding to each decomposition number, to update the Fourier spectrum and the center frequency of each modal component by using the alternating multiplier method, and to obtain the final plurality of modal components when the Fourier spectrum and the center frequency of each modal component converge.

[0109] The optimal number solving module 520 is further configured to calculate the quality value of each modal component corresponding to each decomposition number based on the modal components corresponding to the decomposition number, to calculate the variation corresponding to the decomposition number based on the quality value of each modal component, wherein the variation represents the stability of the quality value of the plurality of modal components, and to select the decomposition number with the smallest variation as the optimal decomposition number.​

[0110] The optimal number solving module 520 is further configured to determine a maximum central frequency and a minimum central frequency in the plurality of modal components according to the plurality of modal components corresponding to the decomposition number, to obtain a target bandwidth according to a difference between the maximum central frequency and the minimum central frequency, and to calculate, for each modal component, a ratio between a central frequency corresponding to the modal component and the target bandwidth as a quality value of the modal component.

[0111] The optimal number solving module 520 is further configured to calculate a difference between the quality values of each two adjacent modal components, and to calculate a variation corresponding to the decomposition number according to the difference between the quality values of each two adjacent modal components.

[0112] The target component determining module 530 is further configured to calculate, for each modal component corresponding to the optimal decomposition number, a fourth-order central moment and a variance corresponding to the modal component, and to calculate a ratio between the fourth-order central moment and a square of the variance as a convexity degree factor corresponding to the modal component.

[0113] The fault analysis module 540 is further configured to obtain a corresponding envelope spectrum based on the Fourier spectrum of the target modal component, to determine a fault characteristic frequency according to a frequency corresponding to a maximum amplitude in the envelope spectrum, and to determine that the gearbox has a fault if the fault characteristic frequency is not within a preset frequency range.

[0114] As to the apparatus in the above-described embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0115] Figure 6 A block diagram of an electronic device according to an example embodiment is shown. Referring to Figure 6 , the electronic device 600 includes a processor 601, which can be one or more in number, and a memory 602 for storing a computer program executable by the processor 601. The computer program stored in the memory 602 can include one or more than one module each corresponding to a set of instructions. In addition, the processor 601 can be configured to execute the computer program to perform the gearbox fault determination method described above.

[0116] In addition, the electronic device 600 can further include a power supply component 603, which can be configured to perform power management of the electronic device 600, and a communication component 604, which can be configured to implement communication of the electronic device 600, such as wired or wireless communication. In addition, the electronic device 600 can further include an input / output (I / O) interface 605. The electronic device 600 can operate based on an operating system stored in the memory 602, such as Windows ServerTM Mac OSX TM Unix TM Linux TM and so on.

[0117] In another exemplary embodiment, a computer readable storage medium including program instructions is also provided, which when executed by a processor, implement the steps of the gearbox fault determination method described above. For example, the non-transitory computer readable storage medium can be the memory 602 described above including program instructions, which can be executed by the processor 601 of the electronic device 600 to complete the gearbox fault determination method described above.

[0118] In another exemplary embodiment, a computer program product is also provided, which contains a computer program capable of being executed by a programmable device, the computer program having code portions for executing the gearbox fault determination method described above when executed by the programmable device.

[0119] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept scope of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0120] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction, and in order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0121] In addition, various different embodiments of the present disclosure can also be combined in any manner, as long as it does not deviate from the idea of the present disclosure, it should also be considered as disclosed by the present disclosure.

Claims

1. A gear case failure determination method characterized by comprising: The method comprises the following steps: decomposing the original signal collected from the gearbox into a plurality of modal components corresponding to the decomposition number by a variational modal decomposition method respectively for a plurality of decomposition numbers; determining an optimal decomposition number based on the plurality of modal components corresponding to each decomposition number; determining a modal component with the maximum convex flatness factor from the plurality of modal components corresponding to the optimal decomposition number as a target modal component, wherein the convex flatness factor represents the steepness of the modal component; determining whether the gearbox has a fault according to the envelope spectrum amplitude of the target modal component; the step of determining the optimal decomposition number based on the plurality of modal components corresponding to each decomposition number comprises: calculating the quality value of each modal component corresponding to the decomposition number according to the modal component corresponding to the decomposition number for any decomposition number; calculating the variation corresponding to the decomposition number according to the quality value of each modal component, wherein the variation represents the stability of the quality value of the plurality of modal components; selecting the decomposition number with the minimum variation as the optimal decomposition number; the step of calculating the quality value of each modal component corresponding to the decomposition number according to the modal component corresponding to the decomposition number comprises: determining the maximum central frequency and the minimum central frequency in the plurality of modal components corresponding to the decomposition number; obtaining a target bandwidth according to the difference between the maximum central frequency and the minimum central frequency; calculating the ratio of the central frequency corresponding to the modal component to the target bandwidth as the quality value of the modal component for each modal component.

2. The method of claim 1, wherein, the step of decomposing the original signal collected from the gearbox into a plurality of modal components corresponding to the decomposition number by a variational modal decomposition method comprises: decomposing the original signal into a plurality of modal components corresponding to the decomposition number for any decomposition number; iteratively updating the Fourier spectrum and the central frequency of each modal component by an alternating multiplier method; obtaining the final plurality of modal components in the case that the Fourier spectrum and the central frequency of each modal component are converged.

3. The method of claim 1, wherein, the step of calculating the variation corresponding to the decomposition number according to the quality value of each modal component comprises: calculating the difference between the quality values of each adjacent two modal components; calculating the variation corresponding to the decomposition number according to the difference between the quality values of each adjacent two modal components.

4. The method of claim 1, wherein, the step of determining a modal component with the maximum convex flatness factor from the plurality of modal components corresponding to the optimal decomposition number as a target modal component comprises: calculating the fourth-order central moment and the variance corresponding to the modal component for each modal component corresponding to the optimal decomposition number; calculating the ratio of the fourth-order central moment to the square of the variance as the convex flatness factor corresponding to the modal component.

5. The method of claim 1, wherein, the step of determining whether the gearbox has a fault according to the envelope spectrum amplitude of the target modal component comprises: obtaining the corresponding envelope spectrum based on the Fourier spectrum of the target modal component, and determining a fault characteristic frequency according to the frequency corresponding to the maximum amplitude in the envelope spectrum; determining whether the fault feature frequency is in a preset frequency range, and if not, determining that the gearbox has a fault.

6. A gear box failure determination device characterized by comprising: The method comprises the steps of: a variational mode decomposition module configured to decompose an original signal collected from the gearbox into a plurality of modal components corresponding to a plurality of decomposition numbers respectively by using a variational mode decomposition method; an optimal number solving module configured to determine an optimal decomposition number based on the plurality of modal components corresponding to each of the decomposition numbers; a target component determining module configured to determine a modal component with a maximum convexity factor from the plurality of modal components corresponding to the optimal decomposition number as a target modal component, the convexity factor representing a steepness of the modal component; a fault analysis module configured to determine whether the gearbox has a fault according to an envelope spectrum amplitude of the target modal component; the optimal number solving module is further configured to, for any of the decomposition numbers, determine a maximum central frequency and a minimum central frequency in the plurality of modal components corresponding to the decomposition number, and obtain a target bandwidth according to a difference between the maximum central frequency and the minimum central frequency; for each of the modal components, calculate a ratio of a central frequency corresponding to the modal component to the target bandwidth as a quality value of the modal component; calculate a variation corresponding to the decomposition number according to the quality value of each of the modal components, the variation representing a stability of the quality values of the plurality of modal components; select the decomposition number with the minimum variation as the optimal decomposition number.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-5.

8. An electronic device, comprising: The method comprises the steps of: a memory having a computer program stored thereon; a processor configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-5.

Images