Fault diagnosis method and device for fan gearbox, electronic equipment and storage medium

Abstract

The invention relates to the technical field of wind turbine generator monitoring, and discloses a fault diagnosis method and device for a fan gear box, electronic equipment and a storage medium, and the method comprises the steps: obtaining a vibration signal of the fan gear box; calculating a power spectrum of the vibration signal; determining a first type of fault characteristic frequency and a second type of fault characteristic frequency respectively according to a first region and a second region in the power spectrum; performing multi-scale complex wavelet transform on the vibration signal and demodulating envelope to obtain a multi-scale complex wavelet envelope spectrum; analyzing the multi-scale complex wavelet envelope spectrum to obtain a third type of fault characteristic frequency; and performing fault diagnosis on the fan gearbox according to at least one of the first type of fault characteristic frequency, the second type of fault characteristic frequency and the third type of fault characteristic frequency to obtain a fault diagnosis result. Through the above mode, the vibration signals are analyzed in different modes, so that the vibration signals can be comprehensively analyzed, and a more complete fault characteristic frequency is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine monitoring, and in particular to a fault diagnosis method, device, electronic equipment and storage medium for a wind turbine gearbox. Background Art

[0002] With the continuous development of wind power technology, wind power generation will gradually leap from the current auxiliary energy to the main energy source. The purpose of fault identification of key components of wind turbines is to accurately and effectively identify the main faults in subsystems such as impellers, transmission chains, and generators, and guide the operation and maintenance of wind farms to reduce wind turbine downtime losses and improve grid stability.

[0003] When identifying wind turbine faults, it is necessary to extract key features from the operating vibration signals of the wind turbine to diagnose the fault. The gearbox is a crucial component of the wind turbine's transmission chain, and the health of its gears directly impacts the turbine's power generation efficiency and operational safety. However, the coupled frequencies of multiple components in a wind turbine gearbox are difficult to separate, and early faults and low-frequency fault signatures are often obscured in the vibration signals collected by vibration status monitoring systems. This makes comprehensive and accurate fault detection in wind turbine gearboxes difficult. Summary of the Invention

[0004] In view of this, the present invention provides a fault diagnosis method, device, electronic device and storage medium for a wind turbine gearbox to solve the problem that it is difficult to comprehensively and accurately detect faults in a wind turbine gearbox.

[0005] In a first aspect, the present invention provides a fault diagnosis method for a wind turbine gearbox, the method comprising: obtaining a vibration signal of the wind turbine gearbox; calculating a power spectrum of the vibration signal; determining a first type of fault characteristic frequency and a second type of fault characteristic frequency based on a first region and a second region in the power spectrum, respectively, wherein the energy of the first region is higher than the frequency of the second region; performing a multi-scale complex wavelet transform on the vibration signal and demodulating the envelope to obtain a multi-scale complex wavelet envelope spectrum; analyzing the multi-scale complex wavelet envelope spectrum to obtain a third type of fault characteristic frequency; performing fault diagnosis on the wind turbine gearbox based on at least one of the first type of fault characteristic frequency, the second type of fault characteristic frequency, and the third type of fault characteristic frequency to obtain a fault diagnosis result.

[0006] Since the running environment of the fan gearbox is complex and there are multiple component coupling frequencies, a single method cannot accurately extract the fault characteristic frequency, the fault diagnosis method of the fan gearbox provided in the embodiment of the application obtains the vibration signal of the fan gearbox, and then analyzes the vibration signal in different ways. First, the power spectrum of the vibration signal is calculated, the power spectrum is divided into a first region and a second region according to the energy level, the first region and the second region are analyzed respectively, and the first type of fault characteristic frequency and the second type of fault characteristic frequency are extracted. Second, the multi-scale complex wavelet transform is performed on the vibration signal and the envelope is demodulated to obtain the multi-scale complex wavelet envelope spectrum, the multi-scale complex wavelet envelope spectrum is analyzed to obtain the third type of fault characteristic frequency, and finally the fault diagnosis result is obtained according to the extracted fault characteristic frequency. Through the above-mentioned manner, the vibration signal is analyzed in different ways, the vibration signal can be comprehensively analyzed, and therefore more complete fault characteristic frequencies can be obtained. Moreover, in view of the problem that the multiple component frequencies are difficult to separate, the multi-scale decomposition and demodulation of the frequency band are realized based on the multi-scale complex wavelet envelope spectrum in the embodiment of the application, so that the fault characteristic frequency can be extracted from the mutually coupled frequencies, and the subsequent fault diagnosis is facilitated.

[0007] In an optional embodiment, the first region is a region in which the energy in the power spectrum is higher than a first preset value, and the step of determining the first type of fault characteristic frequency according to the first region in the power spectrum comprises: comparing the frequency components in the first region with preset meshing frequencies, judging whether the frequency components correspond to the meshing frequencies, and the preset meshing frequencies are determined according to the meshing frequencies when the fan gearbox is running normally; if the frequency components do not correspond to the meshing frequencies, determining the first type of fault characteristic frequency according to the frequency components in the first region.

[0008] In an optional embodiment, the region in which the power spectrum contains sideband components is the second region, and the step of determining the second type of fault characteristic frequency according to the second region in the power spectrum comprises: performing demodulation envelope analysis on the sideband components of the power spectrum to obtain an envelope spectrum; analyzing a low frequency band of the envelope spectrum to identify low frequency modulation components in the low frequency band; and comparing the low frequency modulation components with a pre-established gear fault characteristic frequency table to obtain the second type of fault frequency characteristic of the fan gearbox, and the second type of fault frequency characteristic includes a medium-speed stage gear fault frequency characteristic and a high-speed stage gear fault frequency characteristic.

[0009] In an optional embodiment, the step of analyzing the multi-scale complex wavelet envelope spectrum to obtain the third type of fault characteristic frequency comprises: extracting a target complex wavelet envelope spectrum with an amplitude higher than a second preset value from the multi-scale complex wavelet envelope spectrum; and performing slice analysis on the target complex wavelet envelope spectrum in combination with the gear structure parameters of the fan gearbox to obtain the third type of fault frequency characteristic of the fan gearbox, and the third type of fault frequency characteristic includes a planetary gear fault frequency characteristic.

[0010] In an optional embodiment, a multi-scale complex wavelet transform is performed on the vibration signal and the envelope is demodulated to obtain a multi-scale complex wavelet envelope spectrum, including: performing a complex wavelet transform on the vibration signal at different scales to obtain envelope signals of the vibration signal at different scales; performing a Fourier transform on the envelope signal to obtain a multi-scale complex wavelet envelope spectrum.

[0011] In an optional embodiment, a slice analysis is performed on the target complex wavelet envelope spectrum in combination with the gear structural parameters of the wind gearbox to obtain the third type of fault frequency characteristics of the wind gearbox, including: determining the signal parameters of the planetary gears when they are normally engaged according to the structural parameters of the wind gearbox; performing a slice analysis on the target complex wavelet envelope spectrum to obtain the signal characteristics of the target complex wavelet envelope spectrum; and comparing the signal characteristics with the signal parameters to obtain the third type of fault frequency characteristics.

[0012] In a second aspect, the present invention provides a fault diagnosis device for a wind turbine gearbox, the device comprising: a signal acquisition module for acquiring a vibration signal of the wind turbine gearbox; a power spectrum calculation module for calculating the power spectrum of the vibration signal; a power spectrum analysis module for determining a first type of fault characteristic frequency and a second type of fault characteristic frequency according to a first area and a second area in the power spectrum, respectively, wherein the frequency of the first area is higher than the frequency of the second area; a wavelet transform module for performing a multi-scale complex wavelet transform on the vibration signal and demodulating the envelope to obtain a multi-scale complex wavelet envelope spectrum; a complex wavelet envelope spectrum analysis module for analyzing the multi-scale complex wavelet envelope spectrum to obtain a third type of fault characteristic frequency; a fault diagnosis module for performing fault diagnosis on the wind turbine gearbox according to at least one of the first type of fault characteristic frequency, the second type of fault characteristic frequency and the third type of fault characteristic frequency to obtain a fault diagnosis result.

[0013] In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the fault diagnosis method for a wind gearbox according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the wind turbine gearbox fault diagnosis method of the first aspect or any corresponding embodiment thereof.

[0015] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the wind turbine gearbox fault diagnosis method according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a flow chart of a fault diagnosis method for a wind turbine gearbox according to an embodiment of the present invention;

[0018] Figure 2 is a flow chart of another method for diagnosing a fault of a wind turbine gearbox according to an embodiment of the present invention;

[0019] Figure 3 is a flow chart of another method for diagnosing a fault of a wind turbine gearbox according to an embodiment of the present invention;

[0020] Figure 4 is a structural block diagram of a fault diagnosis device for a wind turbine gearbox according to an embodiment of the present invention;

[0021] Figure 5 FIG. 4 is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0023] Signal processing is an important content of rotating machinery fault diagnosis. Vibration signal analysis and its application in rotating machinery fault diagnosis have become an important content in the field of scientific research at home and abroad, and some of them have become classic signal processing techniques, such as time domain features, frequency spectrum analysis and cepstrum analysis. However, these signal processing methods are mostly suitable for stationary signals, but the vibration signals of the wind turbine transmission chain are mostly non-stationary signals. Due to the inherent characteristics of wind speed, the wind turbine transmission chain is in variable speed and variable load working condition for a long time, and the vibration signals generated thereby are mostly non-stationary signals. Moreover, the transmission chain has many parts, and the vibration signal components are complex, so the feature extraction is challenging. Taking the gearbox in the wind turbine transmission chain as an example. Due to the variable speed, the rotation frequency of each shaft in the gearbox and the meshing frequency of each gear are changing all the time, and the corresponding fault frequency is also changing all the time. In addition, the speed of the planetary gear train is generally low, and its fault frequency is easily affected by other parts. Therefore, the feature extraction of the gearbox fault is very challenging.

[0024] In order to comprehensively and accurately detect the fault of the wind turbine gearbox, an embodiment of the present application provides a fault diagnosis method of the wind turbine gearbox.

[0025] According to the embodiment of the present application, a fault diagnosis method of the wind turbine gearbox is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] In this embodiment, a fault diagnosis method of the wind turbine gearbox is provided, Figure 1 The flowchart of the fault diagnosis method of the wind turbine gearbox according to the embodiment of the present application is shown in FIG. 1, which includes the following steps: Figure 1 As shown in the figure,

[0027] Step S101, acquiring the vibration signal of the wind turbine gearbox.

[0028] In an optional embodiment, a vibration sensor is arranged in the wind turbine gearbox, and the vibration signal of the wind turbine gearbox during operation is acquired by the vibration sensor.

[0029] Step S102, calculating the power spectrum of the vibration signal.

[0030] In an optional embodiment, the power spectrum of the vibration signal is calculated by using the pwelch function. The power spectrum can reveal the frequency components of the signal, and by analyzing the frequency components, the fault in the wind turbine gearbox can be diagnosed.

[0031] Step S103 , determining a first type fault characteristic frequency and a second type fault characteristic frequency according to the first region and the second region in the power spectrum, respectively, wherein the energy of the first region is higher than the frequency of the second region.

[0032] In an embodiment of the present invention, the power spectrum is divided into a first region and a second region according to the level of energy. Compared with the low-energy region, the high-energy region is easier to identify the fault characteristic frequency. Therefore, in a specific embodiment, after the power spectrum is divided into the first region and the second region, the first region and the second region can be analyzed in different ways, so as to extract the fault characteristic frequency in the first region and the second region, respectively.

[0033] When analyzing the first region, since the signal power is relatively strong, the fault characteristics are more obvious. By analyzing the frequency components in the first region in a simple manner, the first type of fault characteristic frequency can be extracted.

[0034] When analyzing the second region, since the low-energy region is more susceptible to interference from other noises, it is difficult to extract the fault characteristic frequency from the low-energy region. Therefore, the power spectrum in the second region needs to be further processed to obtain the second type of fault characteristic frequency.

[0035] For example, when analyzing the second area, filtering, noise reduction or enhancement can be performed on the second area to improve signal quality and reduce the impact of noise, and the preprocessed signal can be analyzed to extract the characteristic frequency of the second type of fault; wavelet transform or time-frequency analysis can also be performed on the power spectrum to obtain better frequency resolution and sensitivity to weak faults, and further analyze and extract the characteristic frequency of the second type of fault.

[0036] In an embodiment of the present invention, the power spectrum is divided into a first region with higher energy and a second region with lower energy, so that different methods can be selected according to the signal characteristics of the first region and the second region to extract the fault characteristic frequency therefrom, thereby enabling more accurate and comprehensive extraction of the fault characteristic frequency of the wind turbine gearbox.

[0037] Step S104: Perform multi-scale complex wavelet transform on the vibration signal and demodulate the envelope to obtain a multi-scale complex wavelet envelope spectrum. The envelope spectrum can highlight the amplitude information in the signal and is more sensitive to detecting fault characteristics.

[0038] Step S105 , analyzing the multi-scale complex wavelet envelope spectrum to obtain the third type fault characteristic frequency.

[0039] Multiscale complex wavelet envelope technology combines multiscale analysis of complex wavelet transforms with demodulation analysis of spectral envelopes to simultaneously decompose and demodulate vibration signals. By identifying the frequency components of the multiscale envelope spectrum, fault signatures are extracted and identified for the planetary, medium-speed, and high-speed gears in wind turbine gearboxes.

[0040] Step S106 , performing fault diagnosis on the wind turbine gearbox according to at least one of the first type fault characteristic frequency, the second type fault characteristic frequency, and the third type fault characteristic frequency to obtain a fault diagnosis result.

[0041] In an optional embodiment, after executing steps S101 to S105 above, if none of the first type fault characteristic frequency, the second type fault characteristic frequency, and the third type fault characteristic frequency are extracted, it is determined that there is no fault in the wind turbine gearbox.

[0042] In an optional embodiment, if at least one of the first type fault characteristic frequency, the second type fault characteristic frequency, and the third type fault characteristic frequency is extracted, it can be determined that a fault exists in the wind turbine gearbox.

[0043] Because vibration signals can be affected by other factors, in an optional embodiment, after extracting the first, second, or third type of fault characteristic frequency, relevant technologies can be used to further analyze the fault frequency to obtain a fault diagnosis result. For example, after obtaining the fault characteristic frequency, the amplitude and phase information of the fault characteristic frequency are extracted. The severity of the fault is determined by the increase in amplitude, and the fault location or type is determined by the change in phase.

[0044] Due to the complex operating environment of the wind turbine gearbox and the presence of multiple component coupling frequencies, a single method cannot accurately extract the fault characteristic frequency. The fault diagnosis method for the wind turbine gearbox provided in the embodiment of the present invention, after obtaining the vibration signal of the wind turbine gearbox, adopts different methods to analyze the vibration signal. First, the power spectrum of the vibration signal is calculated, and the power spectrum is divided into a first region and a second region according to the energy level. The first region and the second region are analyzed respectively to extract the first type of fault characteristic frequency and the second type of fault characteristic frequency; secondly, the vibration signal is subjected to multi-scale complex wavelet transform and envelope demodulation to obtain a multi-scale complex wavelet envelope spectrum. The multi-scale complex wavelet envelope spectrum is analyzed to obtain the third type of fault characteristic frequency. Finally, the fault diagnosis result is obtained based on the extracted fault characteristic frequency. Through the above method, different methods are used to analyze the vibration signal separately, which can comprehensively analyze the vibration signal, thereby obtaining a more complete fault characteristic frequency. In addition, in order to solve the problem that the frequency coupling of multiple components is difficult to separate, the embodiment of the present invention adopts a multi-scale complex wavelet envelope spectrum to realize frequency band automatic multi-scale decomposition and demodulation, so that the fault characteristic frequency can be extracted from the mutually coupled frequencies, which is convenient for subsequent fault diagnosis.

[0045] In this embodiment, a fault diagnosis method for a wind turbine gearbox is provided. Figure 2 FIG. 1 is a flow chart of a fault diagnosis method for a wind turbine gearbox according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0046] Step S201: Obtain the vibration signal of the wind turbine gearbox. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0047] Step S202: Calculate the power spectrum of the vibration signal. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0048] Step S203 , determining a first type fault characteristic frequency and a second type fault characteristic frequency according to the first region and the second region in the power spectrum, respectively, wherein the energy of the first region is higher than the frequency of the second region.

[0049] Specifically, the first region is a region in the power spectrum where energy is higher than a first preset value, and the region in the power spectrum containing sideband components is the second region. The above step S203 includes:

[0050] Step S2031, compare the frequency component in the first area with the preset meshing frequency. If the frequency component does not correspond to the preset meshing frequency, determine the first type of fault characteristic frequency based on the frequency component in the first area; if the frequency component corresponds to the preset meshing frequency, determine that the frequency component is the meshing frequency, and the preset meshing frequency is based on the meshing frequency during normal operation of the wind turbine gearbox.

[0051] Due to the short excitation cycle, the energy of the gear meshing frequency is often higher. Therefore, when the wind turbine gearbox is operating normally, the excitation source of the frequency component with higher energy should be the meshing frequency. If this part of the frequency component does not correspond to the meshing frequency, it is considered that there may be a fault in the operation of the wind turbine gearbox. The frequency is determined to be the first fault characteristic frequency. Further analysis of the first fault characteristic frequency is required to determine whether the wind turbine gearbox has a fault.

[0052] Step S2032: Perform demodulation envelope analysis on the sideband components of the power spectrum to obtain an envelope spectrum.

[0053] In an optional embodiment, the presence of sidebands may be caused by noise when collecting vibration signals and the interaction of multiple frequency components in the wind turbine gearbox. Sideband components have low frequencies and are highly loaded. Therefore, in this embodiment of the present invention, demodulation envelope analysis of the sideband components of the power spectrum can reduce signal complexity, making complex signals with homoharmonics, heteroharmonics, and multiple sideband components easier to analyze, thereby improving the accuracy and efficiency of fault diagnosis.

[0054] Step S2033: Analyze the low-frequency band of the envelope spectrum to identify the low-frequency modulation components in the low-frequency band.

[0055] In mechanical equipment, certain faults may cause low-frequency modulation of the signal. For example, gear wear, bearing defects, shaft imbalance, etc. may all produce specific modulation patterns in the low-frequency band of the envelope spectrum. By analyzing the low-frequency modulation components, these mechanical faults can be detected and diagnosed.

[0056] In step S2034, the low-frequency modulation component is analyzed and compared with a pre-established gear fault characteristic frequency table to obtain the second type of fault frequency characteristics of the wind turbine gearbox. The second type of fault frequency characteristics include medium-speed gear fault frequency characteristics and high-speed gear fault frequency characteristics.

[0057] In an optional embodiment, a gear fault characteristic frequency table is established based on the vibration signals when the medium-speed gear and the high-speed gear are in a fault state, and the low-frequency modulation component obtained in step S2033 is compared with the established gear fault characteristic frequency table. If there is a fault characteristic frequency corresponding to the low-frequency modulation component in the fault characteristic frequency table, the medium-speed gear fault frequency characteristics and the high-speed gear fault frequency characteristics can be determined based on the low-frequency modulation component.

[0058] Step S204: Perform multi-scale complex wavelet transform on the vibration signal and demodulate the envelope to obtain a multi-scale complex wavelet envelope spectrum. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0059] Step S205: Analyze the multi-scale complex wavelet envelope spectrum to obtain the third type of fault characteristic frequency. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0060] Step S206: Perform fault diagnosis on the wind turbine gearbox based on at least one of the first type fault characteristic frequency, the second type fault characteristic frequency, and the third type fault characteristic frequency to obtain a fault diagnosis result. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0061] In this embodiment, a fault diagnosis method for a wind turbine gearbox is provided. Figure 3 FIG. 1 is a flow chart of a fault diagnosis method for a wind turbine gearbox according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0062] Step S301: Obtain the vibration signal of the wind turbine gearbox. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0063] Step S302: Calculate the power spectrum of the vibration signal. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0064] Step S303 , determining a first type fault characteristic frequency and a second type fault characteristic frequency according to the first region and the second region in the power spectrum, respectively, wherein the energy of the first region is higher than the frequency of the second region.

[0065] Step S304 , performing multi-scale complex wavelet transform on the vibration signal and demodulating the envelope to obtain a multi-scale complex wavelet envelope spectrum.

[0066] Specifically, the above step S304 includes:

[0067] Step S3041 : performing complex wavelet transform on the vibration signal at different scales to obtain envelope signals of the vibration signal at different scales.

[0068] Step S3042: Perform Fourier transform on the envelope signal to obtain a multi-scale complex wavelet envelope spectrum.

[0069] In an optional embodiment, the vibration signal is subjected to complex wavelet transform using the following formula:

[0070] wt C (a,τ)=wt R (a,τ)+jwt I (a,τ)

[0071] in,

[0072]

[0073] In the above two equations, a and τ represent the scale factor and time shift factor respectively, x(t) represents the vibration signal, and t represents time. Represents the wavelet transform function.

[0074] Modulo the complex wavelet transform result to obtain the corresponding envelope signal:

[0075]

[0076] The envelope signal is Fourier transformed using the following formula to obtain the scaled complex wavelet envelope spectrum:

[0077]

[0078] Step S305 , analyzing the multi-scale complex wavelet envelope spectrum to obtain the third type fault characteristic frequency.

[0079] Specifically, the above step S305 includes:

[0080] Step S3051 : extracting a target complex wavelet envelope spectrum having an amplitude higher than a second preset value from the multi-scale complex wavelet envelope spectrum.

[0081] Complex wavelet transform is a special form of wavelet transform. Based on the bandpass filtering characteristics of wavelet transform, complex wavelet transform can obtain the complex wavelet envelope spectrum at each scale while performing multi-scale decomposition of the signal, so that the characteristic information of different fault sources can be clearly discovered.

[0082] In an optional embodiment, after determining the multi-scale complex wavelet envelope spectrum, the energy distribution of each scale in the envelope spectrum is analyzed. The energy of each scale can be calculated and compared with other scales. The scale with the highest energy is selected for slice analysis. These scales are usually related to fault features because faults can cause the energy of the signal to increase at a particular scale.

[0083] Step S3052, slice analysis of the target complex wavelet envelope spectrum is performed in combination with the gear structure parameters of the fan gearbox to obtain a third type of fault frequency feature of the fan gearbox. The third type of fault frequency feature includes a planetary gear fault frequency feature.

[0084] In an optional embodiment, when performing slice analysis on the selected scale with higher energy, the changes in signal characteristics such as amplitude, frequency, phase, etc. can be observed. According to the results of slice analysis, when identifying the fault features of the planetary gear of the gearbox, common fault features include tooth surface wear, tooth root crack, tooth breakage, etc. Whether a fault exists can be determined by comparing with known fault patterns.

[0085] Specifically, the above step S3052 includes:

[0086] Step a1, determining the signal parameters when the planetary gear is normally engaged according to the structure parameters of the fan gearbox.

[0087] In an optional embodiment, the number of teeth and the modulus determine the geometry and size of the gear. Different combinations of the number of teeth and the modulus will affect the meshing characteristics and transmission ratio of the gear. When engaging with different meshing characteristics and transmission ratios, the signal parameters of the gear will also be different.

[0088] Step a2, slice analysis of the target complex wavelet envelope spectrum to obtain the signal characteristics of the target complex wavelet envelope spectrum.

[0089] In an optional embodiment, the changes in signal characteristics such as amplitude, frequency, phase, etc. after slicing.

[0090] Step a3, comparing the signal characteristics with the signal parameters to obtain the third type of fault frequency feature.

[0091] Step S306, performing fault diagnosis on the fan gearbox according to at least one of the first type of fault feature frequency, the second type of fault feature frequency, and the third type of fault feature frequency to obtain a fault diagnosis result.

[0092] This embodiment also provides a fault diagnosis device for a wind turbine gearbox. This device is used to implement the above-mentioned embodiments and preferred implementations. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0093] This embodiment provides a fault diagnosis device for a wind turbine gearbox, such as Figure 4 Shown, including:

[0094] The signal acquisition module 401 is used to obtain the vibration signal of the wind turbine gearbox.

[0095] The power spectrum calculation module 402 is used to calculate the power spectrum of the vibration signal.

[0096] The power spectrum analysis module 403 is configured to determine a first type fault characteristic frequency and a second type fault characteristic frequency according to a first region and a second region in the power spectrum, respectively, wherein the frequency in the first region is higher than the frequency in the second region.

[0097] The wavelet transform module 404 is used to perform multi-scale complex wavelet transform on the vibration signal and demodulate the envelope to obtain a multi-scale complex wavelet envelope spectrum.

[0098] The complex wavelet envelope spectrum analysis module 405 is used to analyze the multi-scale complex wavelet envelope spectrum to obtain the third type fault characteristic frequency.

[0099] The fault diagnosis module 406 is configured to perform fault diagnosis on the wind turbine gearbox according to at least one of the first type fault characteristic frequency, the second type fault characteristic frequency, and the third type fault characteristic frequency to obtain a fault diagnosis result.

[0100] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0101] The fault diagnosis device for the wind turbine gearbox in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0102] An embodiment of the present invention further provides an electronic device having the above Figure 4 The fault diagnosis device of the wind turbine gearbox is shown.

[0103] See also Figure 5 , Figure 5is a structural diagram of an electronic device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0104] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0105] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0106] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0107] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0108] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 can be connected by a bus or otherwise, Figure 5 The connection by the bus is taken as an example.

[0109] The input device 30 can receive inputted digital or character information, and generate key signal inputs related to user settings and function controls of the electronic device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device includes, but is not limited to, a liquid crystal display, a light emitting diode, a display, and a plasma display. In some alternative embodiments, the display device can be a touch screen.

[0110] The embodiments of the present application also provide a computer readable storage medium, the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0111] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, the operation of the computer can invoke or provide the method and / or technical solutions according to the present application. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file, etc. Correspondingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer executes the corresponding compiled program after compiling the instructions, or the computer reads and executes the instructions, or the computer executes the corresponding installed program after reading and installing the instructions. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0112] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A fault diagnosis method for a wind turbine gearbox, characterized in that: The method comprises: Obtain the vibration signal of the wind turbine gearbox; Calculating a power spectrum of the vibration signal; Determining a first type fault characteristic frequency and a second type fault characteristic frequency according to a first region and a second region in the power spectrum, respectively, wherein the energy of the first region is higher than the frequency of the second region; Performing a multi-scale complex wavelet transform on the vibration signal and demodulating the envelope to obtain a multi-scale complex wavelet envelope spectrum; Analyzing the multi-scale complex wavelet envelope spectrum to obtain a third type of fault characteristic frequency; A fault diagnosis is performed on the wind turbine gearbox according to at least one of the first type of fault characteristic frequency, the second type of fault characteristic frequency, and the third type of fault characteristic frequency to obtain a fault diagnosis result.

2. The method according to claim 1, characterized in that The first region is a region in the power spectrum where energy is higher than a first preset value, and the step of determining a first type fault characteristic frequency according to the first region in the power spectrum includes: comparing the frequency component in the first region with a preset meshing frequency to determine whether the frequency component corresponds to the meshing frequency, wherein the preset meshing frequency is based on the meshing frequency of the wind turbine gearbox during normal operation; If the frequency component does not correspond to the meshing frequency, the first type fault characteristic frequency is determined according to the frequency component in the first region.

3. The method according to claim 1, characterized in that The region containing the sideband component in the power spectrum is the second region, and the step of determining the characteristic frequency of the second type of fault according to the second region in the power spectrum includes: Performing demodulation envelope analysis on the sideband components of the power spectrum to obtain an envelope spectrum; Analyzing the low frequency band of the envelope spectrum to identify the low frequency modulation components in the low frequency band; The low-frequency modulation component is analyzed and compared with a pre-established gear fault characteristic frequency table to obtain the second type of fault frequency characteristics of the wind turbine gearbox, where the second type of fault frequency characteristics include medium-speed gear fault frequency characteristics and high-speed gear fault frequency characteristics.

4. The method according to claim 1, wherein The analysis of the multi-scale complex wavelet envelope spectrum to obtain the third type of fault characteristic frequency includes: Extracting a target complex wavelet envelope spectrum having an amplitude higher than a second preset value from the multi-scale complex wavelet envelope spectrum; The target complex wavelet envelope spectrum is sliced ​​and analyzed in combination with the gear structure parameters of the wind turbine gearbox to obtain the third type of fault frequency characteristics of the wind turbine gearbox, wherein the third type of fault frequency characteristics include planetary gear fault frequency characteristics.

5. The method according to claim 1, wherein The step of performing a multi-scale complex wavelet transform on the vibration signal and demodulating the envelope to obtain a multi-scale complex wavelet envelope spectrum includes: Performing complex wavelet transform on the vibration signal at different scales to obtain envelope signals of the vibration signal at different scales; Performing Fourier transform on the envelope signal to obtain the multi-scale complex wavelet envelope spectrum.

6. The method according to claim 4, characterized in that The target complex wavelet envelope spectrum is sliced ​​and analyzed in combination with the gear structure parameters of the wind turbine gearbox to obtain the third type fault frequency characteristics of the wind turbine gearbox, including: Determining signal parameters when the planetary gears are normally engaged according to the structural parameters of the wind turbine gearbox; Performing slice analysis on the target complex wavelet envelope spectrum to obtain signal characteristics of the target complex wavelet envelope spectrum; The signal characteristics are compared with the signal parameters to obtain the third type of fault frequency characteristics.

7. A fault diagnosis device for a wind turbine gearbox, characterized in that: The device comprises: Signal acquisition module, used to obtain the vibration signal of the wind turbine gearbox; A power spectrum calculation module, used to calculate the power spectrum of the vibration signal; A power spectrum analysis module, configured to determine a first type fault characteristic frequency and a second type fault characteristic frequency according to a first region and a second region in the power spectrum, respectively, wherein the frequency of the first region is higher than the frequency of the second region; A wavelet transform module is used to perform multi-scale complex wavelet transform on the vibration signal and demodulate the envelope to obtain a multi-scale complex wavelet envelope spectrum; A complex wavelet envelope spectrum analysis module, configured to analyze the multi-scale complex wavelet envelope spectrum to obtain a third type fault characteristic frequency; The fault diagnosis module is used to perform fault diagnosis on the wind turbine gearbox according to at least one of the first type of fault characteristic frequency, the second type of fault characteristic frequency and the third type of fault characteristic frequency to obtain a fault diagnosis result.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fault diagnosis method for a wind turbine gearbox according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the fault diagnosis method for a wind turbine gearbox according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the fault diagnosis method for a wind turbine gearbox according to any one of claims 1 to 6.

Images