A bearing composite fault diagnosis method and system

Abstract

The application discloses a bearing composite fault diagnosis method and system, first, a bearing composite fault vibration observation signal is acquired; then, the observation signal is subjected to short-time Fourier transform and cepstrum threshold processing, two-dimensional time-frequency mask blind source separation, inverse short-time Fourier transform is performed on the obtained time-frequency domain separation signal and band-pass filtering is performed, independent time domain estimation signals are obtained; then, the estimation signals are subjected to Hilbert envelope demodulation and Fourier transform, envelope spectra of the filtered signals are obtained; finally, each order characteristic frequency band of a target fault is searched, a harmonic energy impact index is constructed, and an impact pulse value is calculated; the calculated impact pulse value is compared with a threshold value, and whether the bearing has a target type fault is diagnosed.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of rolling bearing fault diagnosis, and particularly relates to a bearing composite fault diagnosis method and system. BACKGROUND

[0002] Rolling bearings play an important role in industrial production. Since they often work at high speed, heavy load and in complex environment, various forms of faults are inevitable, such as pitting, cracking and spalling of outer rings and rolling elements; and the degradation of bearing health state is often not a single point fault, but a composite fault. In fault diagnosis based on vibration signals, multiple source fault signals are coupled with each other, making it difficult to extract fault features and bringing great challenges to accurate bearing fault diagnosis.

[0003] At present, there are mainly two technical routes for bearing fault diagnosis based on vibration signals. One is to extract fault features by using signal processing methods, and then to identify faults by expert experience or shallow machine learning models; the other is to directly input signals into a trained deep neural network model to automatically extract features and complete fault identification and classification; however, the fault detection method based on signal processing is more dependent on expert experience and feature extraction quality, and the generalization ability of shallow machine learning model is usually poor; the fault diagnosis method based on deep learning has poor interpretability and relies on a large number of labeled samples for model pre-training; both of the above have non-negligible drawbacks. The impact pulse method can judge the health state of the bearing by detecting impact information, which has the advantages of simplicity and effectiveness; however, the traditional impact pulse method can only evaluate the health state of the bearing, but cannot realize accurate fault diagnosis and fault positioning.

[0004] In the problem of composite fault diagnosis, due to the convolution coupling effect of the transmission path, it is difficult to extract fault features and make accurate diagnosis. The classical signal processing method such as band-pass filtering can only filter out unexpected information in the specified frequency band, and cannot decompose the coupled resonance frequency band; traditional signal decomposition methods such as ensemble empirical mode decomposition (EEMD) and wavelet packet decomposition (WPD) can only decompose the signal according to a certain scale, and the decoupling effect of signals with similar characteristic frequencies is poor. SUMMARY

[0005] The technical problem to be solved by the application is to provide a bearing composite fault diagnosis method and system to solve the technical problems of low accuracy, high fault false alarm rate of existing bearing composite fault diagnosis, and the difficulty of traditional signal processing methods and impact pulse method in simply and efficiently realizing accurate diagnosis of bearing composite faults.

[0006] The application adopts the following technical solutions:

[0007] A bearing composite fault diagnosis method comprises the following steps:

[0008] First, obtain the vibration observation signal of the bearing complex fault;

[0009] Then, the observed signal is subjected to short-time Fourier transform and cepstral thresholding, and two-dimensional time-frequency masking blind source separation. The obtained time-frequency domain separated signal is subjected to inverse short-time Fourier transform and bandpass filtering to obtain an independent time-domain estimated signal.

[0010] Next, Hilbert envelope demodulation and Fourier transform are performed on the estimated signal to obtain the envelope spectrum of the filtered signal;

[0011] Finally, the characteristic frequency bands of the target fault were obtained through the search, and a harmonic energy impact index was constructed. And calculate the impact pulse value;

[0012] The calculated impact pulse value is compared with the threshold to diagnose whether the bearing has a target type of fault.

[0013] Preferably, performing short-time Fourier transform and cepstral thresholding on the observed signal specifically involves:

[0014] In the time-frequency domain, the observed signal The absolute value is expressed as Determine the cepstrum of the time-frequency logarithmic spectrum of the observed signal. The cepstral threshold is obtained by introducing a Fourier threshold. Determine the logarithmic amplitude spectrum.

[0015] Preferably, inverse short-time Fourier transform for:

[0016]

[0017] in, t For time, f For frequency, for, Inverted frequency index n For signal channel index, For the first n The observed signal of the channel.

[0018] Preferably, the cepstrum of the time-frequency logarithmic spectrum of the observed signal. for:

[0019]

[0020]

[0021] in, For the Fourier transform in the frequency direction, for, for, is the frequency scale.

[0022] Preferably, the two-dimensional time-frequency mask blind source separation is specifically:

[0023] For the signal time-frequency domain convolution mixing process in the form of , the demixing process is , is a dimensional mixing matrix, is a source signal, is a separation matrix to be solved, is an estimated signal; by solving the demixing matrix to recover the source signal, the group threshold operator is used to time-frequency mask the mask, and blind source separation of the observed signal is realized.

[0024] Preferably, the demixing matrix is solved.

[0025]

[0026] wherein, is the number of observed signal channels, is the frequency scale of the Fourier transform, is a loss function.

[0027] Preferably, the group threshold operator is specifically as follows:

[0028]

[0029] wherein, is a non-negative scalar dependent on the input .

[0030] Preferably, the impact pulse value is:

[0031]

[0032] wherein, is the rotational speed of the shaft, is a harmonic energy impact index, is the inner diameter of the bearing.

[0033] Preferably, the harmonic energy impact index is:

[0034]

[0035] wherein, is the i order characteristic frequency band.

[0036] In a second aspect, an embodiment of the present application provides a bearing compound fault diagnosis system, comprising:

[0037] a signal module configured to acquire a bearing compound fault vibration observation signal;

[0038] a processing module configured to perform short-time Fourier transform and cepstrum threshold processing on the observation signal, two-dimensional time-frequency mask blind source separation, inverse short-time Fourier transform on the obtained time-frequency domain separation signal, and band-pass filtering to obtain an independent time domain estimation signal;

[0039] a transform module configured to perform Hilbert envelope demodulation and Fourier transform on the estimation signal to obtain an envelope spectrum of the filtered signal;

[0040] a construction module configured to search for each order characteristic frequency band of a target fault and construct a harmonic energy impact index and calculate an impact pulse value;

[0041] a judgment module configured to compare the calculated impact pulse value with a threshold value to diagnose whether the bearing has a target type fault.

[0042] In a third aspect, a computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the bearing compound fault diagnosis method when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium comprising a computer program, and the computer program implements the steps of the bearing compound fault diagnosis method when executed by a processor.

[0044] In a fifth aspect, a chip comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the bearing compound fault diagnosis method when executing the computer program.

[0045] In a sixth aspect, an embodiment of the present application provides an electronic device comprising a computer program, and the computer program implements the steps of the bearing compound fault diagnosis method when executed by the electronic device.

[0046] Compared with the prior art, the present application has at least the following beneficial effects:

[0047] The bearing composite fault diagnosis method utilizes an effective signal processing method, improves the traditional impact pulse method by constructing an effective impact index, can comprehensively utilize the advantages of the signal processing method and the impact pulse method, and simply and effectively completes the bearing accurate fault diagnosis task through the vibration signal, and solves the problem that the traditional impact pulse method can only evaluate the bearing health state and cannot perform accurate fault diagnosis.

[0048] Further, by performing short-time Fourier transform on the observation signal, a logarithmic amplitude spectrum is obtained, the time domain convolution effect in the observation signal can be eliminated, and the sparsity of the signal is enhanced in the time-frequency domain; the logarithmic amplitude spectrum is further processed by a cepstrum threshold, the dominant signal with a harmonic structure can be enhanced, and other noise components are weakened.

[0049] Further, the enhanced observation signal is subjected to two-dimensional time-frequency masking blind source separation, the independent single fault signal can be accurately separated from the composite fault observation signal without the fault source and vibration transmission path information, and then the single fault diagnosis method is utilized to realize the composite fault diagnosis.

[0050] It can be understood that the beneficial effects of the above-mentioned second aspect can be referred to the related description in the above-mentioned first aspect, which will not be repeated here.

[0051] In summary, the advanced blind source separation method is utilized to separate and decouple the composite fault observation signal, and then the improved impact pulse method is used to perform fault diagnosis on the estimated signal, so that the bearing composite fault diagnosis can be accurately and automatically completed, the accuracy, convenience and automation degree of the bearing composite fault diagnosis are improved, the fault false alarm rate is reduced, and the engineering application requirements are met.

[0052] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 A method flowchart is provided for the present application;

[0054] Figure 2 A bearing fault test bench is provided;

[0055] Fig. 3 is a test bearing, wherein (a) is normal, (b) is an inner ring crack, and (c) is an outer ring crack;

[0056] Fig. 4 is a time-domain waveform of the observation signal and its envelope spectrum, wherein (a) is an estimated channel 1 and (b) is an estimated channel 2;

[0057] Fig. 5 is a time-domain waveform of the estimated signal and its envelope spectrum, wherein (a) is an estimated channel 1 and (b) is an estimated channel 2;

[0058] Fig. 6 is a calculated impact pulse value of the estimated signal, wherein (a) is an estimated channel 1 and (b) is an estimated channel 2;

[0059] Fig. 7 is a comparison diagram of directly calculating the impact pulse value of the observation signal, wherein (a) is an estimated channel 1 and (b) is an estimated channel 2;

[0060] Figure 8 A schematic diagram of a computer device according to an embodiment of the present application is provided;

[0061] Figure 9 A block diagram of a chip according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0063] In the description of the present application, it should be understood that the terms "include" and "contain" indicate the existence of described features, whole, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0064] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, unless otherwise clear from the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0065] It should be further understood that the term "and / or" used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations, for example, A and / or B can represent three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0066] It should be understood that, although the terms first, second, third, etc. can be employed in describing the preset ranges, etc. in the embodiments of the present application, the preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, the first preset range can also be referred to as the second preset range, and similarly, the second preset range can also be referred to as the first preset range, without departing from the scope of the embodiments of the present application.

[0067] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "when it is determined" or "in response to determining" or "when [a stated condition or event] is detected" or "in response to detecting [a stated condition or event]."

[0068] Various structural diagrams according to the disclosed embodiments of the present application are shown in the accompanying drawings. These diagrams are not drawn to scale, in which certain details are exaggerated for the purpose of clarity, and certain details can be omitted. The shapes of various regions, layers, and the relative sizes and positional relationships between them shown in the diagrams are only exemplary, and in actuality, they can deviate due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, and relative positions can be additionally designed according to actual needs by those skilled in the art.

[0069] The present application provides a bearing compound fault diagnosis method, which uses an effective signal processing method to extract target impact components from vibration signals, constructs an effective impact index to improve the traditional impact pulse method, can integrate the advantages of signal processing method and impact pulse method, and simply and effectively completes the precise fault diagnosis task of bearings through vibration signals; an advanced blind source separation method is used to separate and decouple the compound fault observation signals to obtain independent single fault estimation signals, and then an improved impact pulse method is used for fault diagnosis, which can improve the precision of bearing compound fault precise diagnosis and reduce the fault false alarm rate.

[0070] Referring to Figure 1 , the present application provides a bearing compound fault diagnosis method, which comprises the following steps:

[0071] S1, acquiring a bearing compound fault vibration observation signal;

[0072] S2, transforming the filtered time domain observation signal into a time-frequency domain and taking a logarithm to obtain a time-frequency domain logarithmic spectrum by using a short-time Fourier transform, and enhancing a harmonic structure of the observation signal by using a cepstrum threshold method;

[0073] In the time-frequency domain, the absolute value of the observation signal is expressed as , the cepstrum of the log-spectrogram of the observed signal is written as

[0074] (1)

[0075] (2)

[0076] where n is the signal channel index, t is the time, f is the frequency, is the inverse frequency index, is the Fourier transform in the frequency direction.

[0077] By introducing a Fourier threshold:

[0078] (3)

[0079] The cepstrum threshold is obtained as

[0080] (4)

[0081] In equation (3), is the inverse Fourier transform in the frequency direction:

[0082] (5)

[0083] In equation (5), is a general sparse-promoting thresholding operator, which can be selected by a soft threshold.

[0084] The log-amplitude spectrum of the observed signal is converted into the cepstrum by Fourier transform. By thresholding the cepstrum coefficients and performing inverse Fourier transform, the enhanced log-amplitude spectrum is obtained. The cepstrum thresholding enhances the dominant signal with harmonic structure and weakens other components.

[0085] S3, construct a two-dimensional time-frequency masking function of the Wiener type, and perform blind source separation on the observed signal with enhanced harmonic structure obtained in step S2;

[0086] For a signal time-frequency domain convolution mixing process in the form of , the demixing process is , is a dimensional mixing matrix, is a source signal, is a separation matrix to be solved, is an estimated signal.

[0087] The key of this step is to solve the demixing matrix to recover the source signals, the solution is based on the statistical independence of the source signals, and the measure of independence can be reduced to the following minimization problem:

[0088] (6)

[0089] Such minimization problems are solved by a primal-dual splitting (PDS) algorithm:

[0090] (7)

[0091] where, is the variable to be optimized, I and J is the objective function, L is a bounded linear operator.

[0092] Since I and J are non-differentiable functions, the proximal operator of the following form is used instead of the gradient method:

[0093] (8)

[0094] denotes the variable value that minimizes . is a temporary variable in the iteration process, is the variable to be optimized, is the step size.

[0095] Since the proximal operator of the sparse inducing penalty function as shown in equation (8) can also be represented by a threshold operator. The proximal operator of the 1-2 mixed norm is represented by a group threshold operator as follows:

[0096] (9)

[0097] where, is a threshold parameter, denotes replacing negative values with zero, denotes the th element of the array.

[0098] Further, the group threshold operator is time-frequency masked by a mask of the following form:

[0099] (10)

[0100] Thus, the group threshold operator as shown in equation (10) is represented as:

[0101] (11) ​

[0102] where, is a non-negative scalar depending on the input .

[0103] So far, the implicit source model is defined by using the general time-frequency mask, and the blind source separation of the observed signal is realized.

[0104] S4, the separated signal is transformed to the time domain by using the inverse short-time Fourier transform, and band-pass filtering is performed to obtain an independent time-domain estimated signal ;

[0105] S5, the estimated signal obtained in step S4 is subjected to Hilbert envelope demodulation, and then Fourier transform is performed to obtain the envelope spectrum of the filtered signal ;

[0106] S6, the fault characteristic frequency of the bearing and its high-order harmonics are calculated according to the vehicle speed and bearing parameters , and each order characteristic frequency band of the target fault is searched in the envelope spectrum obtained in step S4 with the center frequency and the radius (a is a fixed coefficient) ;

[0107] S7, the maximum value in each order characteristic frequency band is selected and the square sum is calculated to construct a harmonic energy impact index , and then the impact pulse value is calculated, and the calculated impact pulse value is compared with the threshold value to diagnose whether the bearing has the target type fault.

[0108] The harmonic energy impact index constructed is calculated as follows:

[0109] (12)

[0110] where, is the i order characteristic frequency band.

[0111] The calculation method of the impact pulse value is as follows:

[0112] (13)

[0113] where, is the rotating speed of the shaft (r / min), and D is the inner diameter of the bearing (mm).

[0114] For general industrial bearings, some international industry standards stipulate that if , the bearing should be replaced.

[0115] In another embodiment of the present application, a bearing compound fault diagnosis system is provided, which can be used to implement the bearing compound fault diagnosis method described above, and specifically, the bearing compound fault diagnosis system comprises a signal module, a processing module, a transformation module, a construction module and a judgment module.

[0116] The signal module acquires a bearing compound fault vibration observation signal.

[0117] The processing module performs short-time Fourier transform and cepstrum threshold processing, two-dimensional time-frequency mask blind source separation on the observation signal, inverse short-time Fourier transform and band-pass filtering on the obtained time-frequency domain separation signal, and obtains an independent time domain estimation signal.

[0118] The transformation module performs Hilbert envelope demodulation and Fourier transform on the estimation signal, and obtains an envelope spectrum of the filtered signal.

[0119] The construction module searches for each order characteristic frequency band of the target fault, and constructs a harmonic energy impact index. The judgment module compares the calculated impact pulse value with a threshold value, and diagnoses whether the bearing has a target type fault.

[0120] The judgment module compares the calculated impact pulse value with a threshold value, and diagnoses whether the bearing has a target type fault.

[0121] In another embodiment of the present application, a terminal device is provided, which comprises a processor and a memory, the memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function; the processor in the embodiment of the present application can be used for the operation of the bearing compound fault diagnosis method, which comprises:

[0122] Firstly, the bearing compound fault vibration observation signal is acquired; then the observation signal is subjected to short-time Fourier transform and cepstrum threshold processing, two-dimensional time-frequency mask blind source separation, the time-frequency domain separation signal obtained is subjected to inverse short-time Fourier transform and band-pass filtering to obtain independent time-domain estimation signals; then the estimation signals are subjected to Hilbert envelope demodulation and Fourier transform to obtain the envelope spectrum of the filtered signals; finally, the characteristic frequency bands of the target fault are searched to construct a harmonic energy impact index , and the impact pulse value is calculated; the calculated impact pulse value is compared with a threshold value to diagnose whether the bearing has the target type fault.

[0123] Please refer to Figure 8 , the terminal device is a computer device, the computer device 60 of the embodiment includes a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61, and the computer program 63 realizes the fluid composition calculation method in the reservoir stimulation wellbore in the embodiment when executed by the processor 61. To avoid repetition, details are not repeated here. Alternatively, the computer program 63 realizes the functions of each model / unit in the bearing compound fault diagnosis system of the embodiment when executed by the processor 61. To avoid repetition, details are not repeated here.

[0124] The computer device 60 can be a desktop computer, a notebook computer, a palm computer, and a cloud server, etc. The computer device 60 can include, but is not limited to, the processor 61 and the memory 62. Those skilled in the art can understand that Figure 8 The computer device 60 is only an example and does not constitute a limitation on the computer device 60, and can include more or fewer components than shown, or combine certain components, or different components, for example, the computer device can also include an input / output device, a network access device, a bus, etc.

[0125] The processor 61 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0126] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or a memory of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, and the like.

[0127] Further, the memory 62 can include both an internal storage unit and an external storage device of the computer device 60. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0128] Referring to Figure 9 , the terminal device is an electronic device 600 in the form of a general computing device. The components of the electronic device can include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.

[0129] The storage unit stores program codes that can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present application described in the method part of the present specification. For example, the processing unit 610 can perform the steps as shown in Figure 1 .

[0130] The storage unit 620 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 6201 and / or a cache memory 6202, and can further include a read-only memory (ROM) 6203.

[0131] The storage unit 620 can further include a program / utility 6204 having a set of (at least one) program modules 6205, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment.

[0132] The bus 630 can be one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit bus, or a local bus using any of a variety of bus architectures.

[0133] The electronic device 600 can also communicate with one or more external devices 700 such as a keyboard, a pointing device, a Bluetooth device, or an audio device. Communication can also occur with one or more devices that enable a user to interact with the electronic device 600, and / or one or more devices that enable the electronic device 600 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 650. Still yet, the electronic device 600 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet through a network adapter 660. The network adapter 660 can communicate with the other components of the electronic device 600 via the bus 630. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with the electronic device 600. For example, a microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc. can be used in conjunction with the electronic device 600.

[0134] In still another embodiment of the present application, the present application also provides a storage medium, specifically a computer readable storage medium, which is a memory device in the terminal device, used for storing programs and data. It can be understood that the computer readable storage medium herein can include the built-in storage medium in the terminal device, and of course can also include the extended storage medium supported by the terminal device. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions adapted to be loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs. It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory.

[0135] The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to realize the corresponding steps of the bearing compound fault diagnosis method in the above embodiments; the one or more instructions stored in the computer readable storage medium are loaded and executed by the processor to perform the following steps:

[0136] First, the bearing compound fault vibration observation signal is obtained; then the observation signal is subjected to short-time Fourier transform and cepstrum threshold processing, two-dimensional time-frequency mask blind source separation, the obtained time-frequency domain separation signal is subjected to inverse short-time Fourier transform and band-pass filtering to obtain independent time domain estimation signals; then the estimation signals are subjected to Hilbert envelope demodulation and Fourier transform to obtain the envelope spectrum of the filtered signal; finally, the characteristic frequency bands of the target fault are searched to construct a harmonic energy impact index And the impact pulse value is calculated; the calculated impact pulse value is compared with a threshold value, and whether the bearing has a target type of failure is diagnosed.

[0137] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0138] Application examples

[0139] Step 1: bearing fault test is carried out by using a bearing fault test bench, vibration signals of bearing faults are obtained, a three-axis acceleration sensor is used as a sensor, a sampling frequency is 25.6 kHz, and the test bench is as shown in Figure 2 .

[0140] The test bearing is as shown in Fig. 3, has two types of fault, outer ring crack and inner ring crack, and bearing parameters are as shown in Table 1. The test working condition is 1300 rpm, the inner ring fault characteristic frequency is 116 Hz, and the outer ring fault characteristic frequency is 76 Hz.

[0141] Table 1 Bearing parameters

[0142]

[0143] Two types of fault signals are convoluted and mixed to obtain a composite fault observation signal of two channels, and a time domain waveform and an envelope spectrum thereof are as shown in Fig. 4. It can be seen that due to the convolution effect, different fault characteristic frequencies in the envelope spectrum of the observation signal are mixed with each other; and due to the influence of noise, the amplitude of the fault characteristic frequency is low, the amplitude of the noise component is high, and the fault feature extraction effect is poor.

[0144] Step 2: the short-time Fourier transform is used to transform the filtered time domain observation signal into a time-frequency domain and take a logarithm to obtain a time-frequency domain logarithmic spectrum, and further calculate a cepstrum. In the time-frequency domain, the absolute value of the observation signal is expressed as , a Fourier threshold is introduced to obtain a cepstrum threshold , wherein is a Fourier inverse transform in the frequency direction, is a general sparse promotion threshold operator, which can be selected by a soft threshold.

[0145] The enhanced log amplitude spectrum is obtained by thresholding the cepstrum coefficients and inverse Fourier transform. The cepstrum threshold processing enhances the dominant signal with harmonic structure and weakens other components.

[0146] Step 3: Construct a two-dimensional time-frequency masking function of the Wiener type, and perform blind source separation on the observed signal with enhanced harmonic structure obtained in step 2. The key of this step is to solve the demixing matrix to recover the source signal, and the basis for solving is that the source signals are statistically independent. The proximity operator is expressed by a group threshold operator, and the final group threshold operator is obtained. An implicit source model is defined by using a general time-frequency masking function, and blind source separation is realized on the observed signal.

[0147] Step 4: Transform the separated signal into the time domain by using the inverse short-time Fourier transform, and perform band-pass filtering to obtain an independent time-domain estimated signal .

[0148] Step 5: Perform Hilbert envelope demodulation on the estimated signal obtained in step 4 , and then perform Fourier transform to obtain the envelope spectrum of the filtered signal .

[0149] The estimated signal time-domain waveform and its envelope spectrum obtained through steps 3-5 are shown in FIG. 5. It can be seen that, after separation and decoupling, the inner ring fault estimated signal and the outer ring fault estimated signal are obtained respectively, and the obvious fault characteristic frequency, sideband and high-order harmonic are extracted in the envelope spectrum of each estimated signal, and the noise is also weakened.

[0150] Step 6: Calculate the fault characteristic frequency and high-order harmonic of the bearing according to the vehicle speed and bearing parameters , search for the target fault characteristic frequency band of each order in the envelope spectrum obtained in step 5 with the center frequency and the radius (a is a fixed coefficient) .

[0151] Step 7: Select the maximum value in each characteristic frequency band and calculate the square sum to construct a harmonic energy impact index , and then calculate the impact pulse value.

[0152] The alarm threshold is 50 dB. The calculated impact pulse value is compared with the threshold value to diagnose whether the bearing has a target type fault. The impact pulse value calculated from the estimated signal is shown in FIG. 6. It can be seen that the method proposed in the application accurately detects the inner ring and outer ring compound fault, and prevents false alarms of other faults.​

[0153] In summary, the bearing composite fault diagnosis method and system can separate the high signal-to-noise ratio inner ring fault and outer ring fault estimation signals through the feature enhancement and two-dimensional time-frequency masking blind source separation of the semi-physical simulation observation signals in the bearing inner ring and outer ring composite fault diagnosis application example; then the target impact component is extracted from the estimation signal, the feature frequency band is searched, an impact energy index is constructed, the inner ring and outer ring composite faults are accurately detected, and the false alarm of other faults is prevented.

[0154] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0155] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0156] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0157] In the embodiments of the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other manners. For example, the embodiments of the apparatus / terminal described above are merely schematic, and the division of the modules or units is merely logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0158] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0159] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into a unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0160] The integrated module / unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include or exclude content according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0161] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0162] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0163] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps in one or more flow or blocks

[0164] The above merely provides the technical idea of the present application, and cannot be used to limit the protection scope of the present application. Any modification made according to the technical idea of the present application, on the basis of the technical solutions, falls within the protection scope of the claims of the present application.

Claims

1. A bearing compound fault diagnosis method characterized by, The method comprises the following steps: Obtaining a bearing compound fault vibration observation signal; Performing short-time Fourier transform and cepstrum threshold processing on the observation signal, and performing two-dimensional time-frequency mask blind source separation, performing inverse short-time Fourier transform on the obtained time-frequency domain separation signal and band-pass filtering to obtain an independent time-domain estimation signal; Performing Hilbert envelope demodulation and Fourier transform on the estimation signal to obtain an envelope spectrum of the filtered signal; The search obtains each order characteristic frequency band of the target fault, and constructs a harmonic energy impact index And calculates an impact pulse value, the impact pulse value Is: wherein, is the rotational speed of the shaft, is the harmonic energy impact index, is the bearing inner diameter, the harmonic energy impact index is: wherein is a 2nd i order characteristic frequency band; Comparing the calculated impact pulse value with a threshold value to diagnose whether the bearing has a target type fault.

2. The bearing compound fault diagnosis method according to claim 1, characterized in that, The short-time Fourier transform and cepstrum threshold processing on the observation signal specifically comprises: In the time-frequency domain, the absolute value of the observation signal is expressed as , and the cepstrum of the observation signal time-frequency logarithmic spectrum is determined ; A cepstrum threshold is obtained by introducing a Fourier threshold ; determine the log amplitude spectrum.

3. The bearing compound fault diagnosis method according to claim 2, characterized in that, inverse short-time fourier transform is: wherein, t is time, f is frequency, is, is the inverse frequency index, n is the signal channel index, is the observation signal of the n channel.

4. The bearing compound fault diagnosis method according to claim 2, characterized in that, Cepstrum of observed signal time-frequency log spectrum Is: wherein is the Fourier transform in the frequency direction, is the frequency scale.

5. The bearing compound fault diagnosis method of claim 1, wherein, The two-dimensional time-frequency mask blind source separation specifically comprises: For the form The signal time-frequency domain convolution mixing process, its demixing process is as follows: , for 3D mixing matrix As the source signal, Let be the separation matrix to be solved. To estimate the signal, the unmixing matrix is ​​calculated. The source signal is recovered, and the group threshold operator is masked in time and frequency to achieve blind source separation of the observed signal.

6. The bearing compound fault diagnosis method according to claim 5, characterized in that, Solving mixed matrices The objective function used is: wherein, is the number of observed signal channels, is the frequency scale of the Fourier transform, is the loss function.

7. The bearing compound fault diagnosis method according to claim 5, characterized in that, The group threshold operator specifically comprises the following: wherein is a non-negative scalar depending on the input x.

8. A bearing compound fault diagnosis system characterized by, The method comprises the following steps: The signal module obtains a bearing compound fault vibration observation signal; The processing module performs short-time Fourier transform and cepstrum threshold processing on the observation signal, and performs two-dimensional time-frequency mask blind source separation, performs inverse short-time Fourier transform on the obtained time-frequency domain separation signal and band-pass filtering to obtain an independent time-domain estimation signal; The transform module performs Hilbert envelope demodulation and Fourier transform on the estimation signal to obtain an envelope spectrum of the filtered signal; The construction module searches for each order characteristic frequency band of the target fault, and constructs a harmonic energy impact index , and calculates an impact pulse value, the impact pulse value is: wherein, is the rotational speed of the shaft, is the harmonic energy impact index, is the bearing inner diameter, the harmonic energy impact index is: wherein is a first i order characteristic frequency band; The judgment module compares the calculated impact pulse value with a threshold value to diagnose whether the bearing has a target type fault.

Images