Bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP

Abstract

The invention discloses a bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP, and belongs to the technical field of fault diagnosis. Determining an optimal decomposition layer number of discrete wavelet transform by adopting a correlation coefficient, and performing discrete wavelet transform on the original signal according to the determined optimal decomposition layer number to obtain a series of component signals; based on a second-order differential signal of each component signal after discrete wavelet transform, impact characteristics during bearing fault are described; performing 1D-LBP on the second-order differential signal by taking a moving window local average value as a criterion to obtain a new signal containing local feature information; and based on a spectral analysis method, analyzing the obtained local feature signal, extracting the feature frequency of the local feature signal, and extracting the bearing fault feature information and identifying the fault type according to a bearing fault feature frequency calculation formula. Noise components in the vibration signals are effectively suppressed, and effective monitoring of the running state of the bearing and accurate judgment of the composite fault type of the bearing can be achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of fault diagnosis, and particularly designs a bearing composite fault identification method based on the combination of wavelet transform, second-order difference and 1D-LBP. Background Art

[0002] Bearings are widely used in industries such as industry and aviation. They are very important components of rotating machinery. Their health status will directly affect the safe operation of the entire mechanical system. Therefore, bearing condition monitoring and fault diagnosis are of great significance to ensure the safe and stable operation of the equipment. The operating environment of bearings is complex. The collected vibration signals are usually nonlinear and non-stationary, and the fault information is easily submerged by irrelevant components and noise, and the fault characteristics are often difficult to extract accurately. At the same time, in actual engineering, bearing faults often manifest as composite faults with multiple faults coexisting at the same time. Compared with single faults, due to the mutual coupling between faults, the signals corresponding to composite faults are more complex, which further increases the difficulty of fault identification. Therefore, how to accurately extract composite fault features from vibration signals is still a major challenge in the field of bearing fault diagnosis.

[0003] In order to accurately extract the characteristics of bearing composite faults and accurately identify the fault types, a variety of time and frequency domain signal analysis methods have been applied to the field of bearing fault identification. Including research based on signal decomposition algorithms, such as wavelet transform, empirical mode decomposition, variational mode decomposition, etc.; research on various feature enhancement algorithms, such as minimum entropy deconvolution, Teager energy operator, etc.; research on various noise reduction algorithms, such as singular value decomposition noise reduction, autocorrelation function noise reduction and wavelet threshold noise reduction. These signal analysis methods have their own advantages, but they also have certain limitations. Especially when extracting features from bearing vibration signals, due to the very complex information contained in the signal, there will be problems such as mode aliasing, endpoint effect, the need to determine prior parameters, poor noise resistance, and difficulty in fully extracting features.

[0004] The above research mainly characterizes bearing fault information from the perspective of time and frequency domain signal analysis. In recent years, some scholars have introduced texture feature extraction methods in the field of image processing into the field of signal processing. Among them, the one-dimensional LBP (one dimension local binary pattern, 1D-LBP) algorithm developed on the basis of local binary pattern (local binary pattern, LBP) is mainly used in the field of speech signals and medical human physiological signals. There are relatively few studies in the field of fault recognition, but it shows good local feature extraction capabilities and helps to extract local fault information in the signal. The 1D-LBP algorithm decimal encodes the local binary signal of the one-dimensional signal to obtain a series of signals in the range of 0-255 that reflect the local characteristics of the signal, thereby representing the characteristic information in the signal. At present, the research on the 1D-LBP method in the field of fault recognition is mostly based directly on the original signal; due to the influence of component signals and noise that are not related to the fault, the fault information in the original signal is weak and complex; in addition, the 1D-LBP method itself is sensitive to noise, which is very likely to lead to insufficient local feature extraction and difficult to accurately identify the fault. Summary of the invention

[0005] In order to solve the above problems, the technical solution adopted by the present invention is: a bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP, comprising the following steps;

[0006] Obtain bearing vibration signal;

[0007] Determine the optimal number of decomposition levels of discrete wavelet transform based on the correlation coefficient;

[0008] With the optimal decomposition layer number, discrete wavelet transform is performed on the bearing vibration signal to obtain the approximate signal and detail signal.

[0009] Perform second-order difference operations on the approximate signal and the detail signal to obtain the corresponding second-order difference sequences, and describe the impact characteristics of the bearing failure.

[0010] Get any second-order difference sequence, take the local average value of the moving window of the second-order difference sequence as the criterion, and use the one-dimensional local binary pattern method to get the decimal signal of the second-order difference sequence to characterize the local characteristic information of the bearing vibration signal;

[0011] Performing noise reduction processing on the decimal signal of the acquired second-order difference sequence to obtain a noise-reduced signal;

[0012] The spectrum analysis method is used to extract the prominent frequencies in the spectrum of the obtained denoised signal, and the bearing fault characteristic information is extracted and the fault type is identified based on the bearing fault characteristic frequency calculation formula.

[0013] Furthermore, the process of determining the optimal number of decomposition layers is as follows:

[0014] Let X t is the signal to be decomposed, H t is a component signal after discrete wavelet transform decomposition, then the correlation coefficient between the two is ρ XH , can be obtained by formula (1):

[0015]

[0016] Among them, Cov(X t ,H t ) is X t and H t The covariance of , Var(·) represents the variance of the signal;

[0017] The number of decomposition layers of discrete wavelet transform (DWT) is adaptively determined. When the Kth layer is reached and the correlation coefficient between the component signal and the original signal is less than the correlation coefficient threshold, the actual number of decomposition layers is determined to be K-1, that is, the optimal number of decomposition layers is updated to K=K-1.

[0018] Furthermore, the decomposed detail signal and the approximate signal are subjected to the following second-order difference operation: the detail signal d k (n i ) The second-order difference sequence F dk (n i ) is expressed as follows:

[0019] F dk (n i ) = d k (t j +1)-2d k (t j )+d k (t j -1)t j =2,3,…,n-1; n i =t j -1(2)

[0020] The approximate signal a K (t i ) is the second-order difference sequence F ak (t i ) is expressed as follows:

[0021] Fak (n i )=a k (t j +1)-2a k (t j )+a k (t j -1)t j =2,3,…,n-1; n i =t j -1(3)

[0022] Furthermore, the process of obtaining any second-order difference sequence, taking the local average value of the moving window of the second-order difference sequence as a criterion and adopting the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence is as follows:

[0023] The second-order difference sequence F of the detail signal dk (n i ) as an example;

[0024] (a) Let P ji (i=1,2,…8) are the 8 adjacent points of the jth moving window, calculate P ji The local mean Ed kj :

[0025]

[0026] (b) Taking the local average value Ed kj As the criterion, for the second-order difference sequence F dk (n i ) performing binarization based on the 1D-LBP algorithm to obtain a 1D-LBP signal;

[0027] Let the binarized sequence corresponding to the jth moving window be F(g ji ), g ji is the i-th point P in the j-th moving window i The value of and the local average value Ed kj The calculation process is shown in formulas (5)-(6).

[0028] g ji =P ji -Ed kj i=1,2,…,8 j=n-7(5)

[0029]

[0030] (c) The locally binarized sequence F(g ji ), and are successively reconverted into decimal signals 1D-LTS(j) that can reflect the signal texture characteristics.

[0031]

[0032] Furthermore, the window length of the moving window is 8, and the moving step length is 1.

[0033] Furthermore, the noise reduction process uses an autocorrelation function to perform noise reduction.

[0034] A bearing composite fault identification device based on wavelet transform, second-order difference and 1D-LBP, comprising:

[0035] Acquisition module: used to obtain bearing vibration signals;

[0036] Decomposition layer number module: used to determine the optimal decomposition layer number of discrete wavelet transform based on the correlation coefficient;

[0037] Discrete wavelet transform module: It is used to obtain the optimal number of decomposition layers, perform discrete wavelet transform on the bearing vibration signal, and obtain the approximate signal and detail signal.

[0038] Second-order difference operation module: used to perform second-order difference operation on the approximate signal and the detail signal, obtain the corresponding second-order difference sequence, and describe the impact characteristics of the bearing failure;

[0039] Signal quantization and decimal signal acquisition module: used to obtain any second-order difference sequence, take the local average value of the moving window of the second-order difference sequence as the criterion, and use the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence to characterize the local characteristic information of the bearing vibration signal;

[0040] Noise reduction module: used to perform noise reduction processing on the decimal signal of the acquired second-order difference sequence to obtain a noise-reduced signal;

[0041] Extraction and identification module: It is used to extract the prominent frequencies in the spectrum of the acquired noise-reduced signal by using the spectrum analysis method, and to extract the bearing fault characteristic information and identify the fault type according to the bearing fault characteristic frequency calculation formula.

[0042] A computer device comprises: a processor and a memory, wherein the memory stores a program module, and wherein the program module runs on the processor to implement the method described above.

[0043] A readable storage medium stores a program module, wherein the program module can implement the method when executed in a processor.

[0044] The present invention provides a bearing composite fault identification method based on the combination of wavelet transform, second-order difference and 1D-LBP. Considering that wavelet transform can reduce the influence of noise on the extraction of weak fault information to a certain extent through frequency domain filtering; at the same time, considering that bearing faults are often accompanied by impact characteristics; the second-order difference of the signal reflects the speed of change of the signal slope, that is, the larger the absolute value of the second-order difference of the signal, the more obvious the impact characteristics of the signal corresponding to the position are. Therefore, the second-order difference of the signal can be used to describe the impact characteristics of the bearing fault; in addition, the 1D-LBP method is used to quantize the second-order difference of the decomposed component signal (rather than the entire vibration signal) instead of binarizing the signal itself, which can further improve the ability of 1D-LBP to identify weak fault characteristics and its robustness to noise.

[0045] Taking into account that the correlation coefficient can reflect the correlation between signals, the correlation coefficient between the component signal after discrete wavelet transform and the original signal is used as a criterion to adaptively determine the number of decomposition layers of discrete wavelet transform; secondly, the present invention takes into account the characteristics that bearing failures are often accompanied by impact characteristics, and utilizes the sensitivity of the second-order differential signal to the impact signal. The impact characteristics of the bearing failure are described based on the second-order differential signal of each component signal after discrete wavelet transform; and the second-order differential signal is subjected to 1D-LBP based on the local average value as the criterion to obtain a new signal containing local feature information.

[0046] On this basis, a method combining wavelet transform, second-order difference and 1D-LBP was proposed, which not only effectively suppressed the noise component in the vibration signal, but also highlighted the fault feature information; from the perspective of "texture feature" extraction, it realized effective monitoring of the bearing operating status, realized accurate extraction of bearing fault feature information, and accurately judged the composite fault type of the bearing, which has certain engineering application value.

[0047] (1) Considering that discrete wavelet transform has a good denoising effect, the accurate determination of its decomposition level is an important prerequisite for effective signal decomposition; the correlation coefficient reflects the correlation between signals, and the correlation coefficient is used to adaptively determine the decomposition level of discrete wavelet transform.

[0048] (2) Considering the fact that bearing failure is often accompanied by impact characteristics, the sensitivity of the second-order difference signal to the impact signal is utilized, and the impact characteristics of the bearing failure are described based on the second-order difference signal of each component signal after discrete wavelet transform.

[0049] (3) In order to further highlight the impact characteristics of bearing failure, 1D-LBP is performed on the second-order difference signal based on the local average value to obtain a new signal containing local information.

[0050] (4) The spectral analysis method is used to extract the features of the signal containing local texture information, thereby realizing the extraction of the characteristic frequency of the bearing fault and the accurate identification of the fault type. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative labor.

[0052] Figure 1 A block diagram of the method for adaptively determining the number of decomposition layers of discrete wavelet transform according to an embodiment of the present invention;

[0053] Figure 2 A block diagram of the bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP in an embodiment of the present invention;

[0054] Figure 3 Application of an embodiment of the present invention in intermediate bearing fault identification, wherein (a) is the simulation signal time domain, (b) is the noise signal time domain, (c) is the mixed signal of (a) and (b), (d) is the frequency spectrum of Figure (c), (b1) is the component signal of Figure (c) after DWT, (b2) is the 1D-LTS signal of Figure (b1), (c1) is the autocorrelation function diagram of D5 in (b2), (d1) is the frequency spectrum of Figure (c1), (c2) is the autocorrelation function diagram of A5 in Figure (b2), (d2) is the frequency spectrum of Figure (c2), and (d3) is a local enlarged diagram of Figure (d2). DETAILED DESCRIPTION

[0055] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0056] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] A bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP, characterized in that it comprises the following steps:

[0058] Step 1: Obtain bearing vibration signal;

[0059] Step 2: Determine the bearing vibration signal x(t i ) The optimal number of decomposition levels K, t of discrete wavelet transform (DWT) i =1,2,…,N, where N is the signal length;

[0060] Step 3: To obtain the optimal decomposition level, perform discrete wavelet transform on the bearing vibration signal to obtain the approximate signal a K (t i ) and detail signal d k (t i ), k=1,2,…K,t i =1,2,…,n;

[0061] Step 4: Randomly approximate signal a K (t i ) or detail signal d k (t i ) to perform second-order difference operations, and obtain the corresponding second-order difference sequences F dk (n i ) or F ak (t i ), describing the impact characteristics of bearing failure;

[0062] Step 5: Obtain any second-order difference sequence, take the local average value of the second-order difference sequence moving window as the criterion, adopt one dimension local binary pattern (1D-LBP), and obtain the decimal signal 1D-LTS(j) of the second-order difference sequence, j=1,2,…,n-7, which is used to describe the local characteristic information of the bearing vibration signal; the window length of the moving window is 8, and the moving step length is 1;

[0063] Step 6: To further reduce the influence of noise, the decimal signal of the acquired second-order difference sequence is subjected to noise reduction processing to obtain the noise-reduced signal DE-1D-LTS;

[0064] Step 7: For the obtained denoised signal DE-1D-LTS, a spectrum analysis method is used to extract the prominent frequencies in the spectrum, and the bearing fault characteristic information is extracted and the fault type is identified based on the bearing fault characteristic frequency calculation formula.

[0065] Step 1 / Step 2 / Step 3 / Step 4 / Step 5 / Step 6 / Step 7 are executed in sequence;

[0066] Furthermore, the correlation coefficient is determined as follows:

[0067] Let X t is the signal to be decomposed, H t is a component signal after discrete wavelet transform decomposition, then the correlation coefficient between the two is ρ XH , can be obtained by formula (1):

[0068]

[0069] Among them, Cov(X t ,H t ) is X t and H t The covariance of , Var(·) represents the variance of the signal;

[0070] Adaptively determine the number of decomposition layers of discrete wavelet transform. When the Kth layer is reached and the correlation coefficient between the component signal and the original signal is less than the correlation coefficient threshold, the actual number of decomposition layers is K-1, that is, the optimal number of decomposition layers is updated to K=K-1. Figure 1 As shown in the figure, D1, D2, ..., Dk represent the detail signals of the 1st to the Kth layers of DWT, and Ak represents the approximate signal of DWT.

[0071] The correlation coefficient threshold is set to 0.2 (0.2 is taken as an example, but is not limited to this value).

[0072] Furthermore, the detail signal d k (n i ) The following second-order difference operation is used, and the detail signal d k (n i ) The second-order difference sequence F dk (n i ) is expressed as follows:

[0073] F dk (n i ) = d k (t j +1)-2d k 9t j )+d k (t j -1)t j =2,3,…,n-1; n i =t j -1(2)

[0074] The approximate signal a K (t i) is the second-order difference sequence F ak (t i ) is expressed as follows:

[0075] F ak (n i )=a k (t j +1)-2a k (t j )+a k (t j -1)t j =2,3,…,n-1; n i =t j -1(3)

[0076] The process of obtaining any second-order difference sequence, taking the local average value of the moving window of the second-order difference sequence as the criterion, and adopting the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence is as follows:

[0077] The second-order difference sequence F of the detail signal dk (n i ) as an example;

[0078] (a) Let P ji (i=1,2,…8) are the 8 adjacent points of the jth moving window, calculate P ji The local mean Ed kj :

[0079]

[0080] (b) Taking the local average value Ed kj As the criterion, for the second-order difference sequence F dk (n i ) performing binarization based on the 1D-LBP algorithm to obtain a 1D-LBP signal;

[0081] Let the binarized sequence corresponding to the jth moving window be F(g ji ), g ji is the i-th point P in the j-th moving window i The value of and the local average value Ed kj The calculation process is shown in formulas (5)-(6).

[0082] g ji =P ji -Ed kj i=1,2,…,8 j=n-7(5)

[0083]

[0084] (c) The locally binarized sequence F(g ji ), and are successively reconverted into decimal signals 1D-LTS(j) that can reflect the signal texture characteristics.

[0085]

[0086] In order to further reduce the influence of noise, the denoising of the acquired 1D-LTS signal by taking its autocorrelation function is not limited to this denoising method, and the denoised signal is recorded as DE-1D-LTS.

[0087] According to the spectrum of the denoised signal DE-1D-LTS, the characteristic information of the intermediate bearing composite fault is extracted according to the calculation formula of the intermediate bearing fault characteristic frequency in Table 1 (taking the high and low pressure rotors rotating in the same direction as an example), and the composite fault type of the bearing is judged.

[0088] Table 1 Parameters represented by each symbol and calculation formula of each characteristic frequency of intermediate bearing

[0089]

[0090]

[0091] Example 1: In order to prove the effectiveness of this method, it was verified based on the simulation signal. The composite fault of the outer ring friction cage and the inner ring friction cage of the intermediate bearing was randomly analyzed. The low-pressure and high-pressure speeds were randomly selected as 3500r / min and 12000r / min (the low-pressure and high-pressure rotation directions rotate in the same direction). The intermediate bearing with geometric parameters shown in Table 2 was used as an example for verification.

[0092] Table 2 Intermediate bearing geometric parameters

[0093]

[0094] According to the geometric parameters of the intermediate bearing, the high and low pressure rotation frequencies and the fault characteristic frequency calculation formula shown in Table 1, the characteristic frequencies of the simulation signal in this state are: F H =200Hz, F L =58.3Hz, f o =1945.3Hz, f i =2304.7Hz, f b =831.8Hz, F or =64.8Hz, F ir =76.8Hz.

[0095] Let y ) (t) is the intermediate bearing fault simulation signal; A 1 is the inner ring friction cage fault signal amplitude (A1 =0.2); A 2 is the outer ring friction cage fault signal amplitude (A 2 =0.4); F L 、F H are low pressure and high pressure rotation frequencies respectively (amplitudes are expressed as A 3 , A 4 Indicates; Randomly pick A 3 =A 4 =0.6, greater than the fault signal amplitude); f n1 is the system natural frequency (f n1 =1000); g is the damping coefficient (g = 0.2); y 0 is the displacement constant (y 0 =1); N sampling points (N = 8192*3); t 0 is the single cycle sampling time; t is the sampling time; K is the number of repetitions; and the sampling frequency is 3.2KHz. In this embodiment, the signal amplitude and parameters are randomly set. Then the intermediate bearing fault simulation signal y 0 (t) is:

[0096]

[0097] In order to solve the problem of a large amount of noise in the vibration signals collected in engineering practice, the simulation signal y 0 A Gaussian white noise with a signal-to-noise ratio of -20 is added to (t), and the added noise signal is s(t). The final fault signal y(t) is:

[0098] y(t)=y 0 (t)+s(t) (9)

[0099] In this embodiment, the threshold value for adaptively determining the number of decomposition layers of DWT is 0.2 as an example, the denoising method is autocorrelation denoising as an example, and the spectrum analysis is spectrum analysis as an example, but in actual application, it is not limited to the threshold value, the spectrum analysis method and the denoising method. According to the method of the present invention, the simulation signal of the intermediate bearing composite fault is analyzed, and the results are as follows Figure 3 shown. Figure 3 (a) Corresponding simulation signal y ) (t); Figure 3 (b) Corresponding noise signal s(t); Figure 3 (c)-(d) are the intermediate bearing fault signals y(t) and their spectrum after adding noise. Table 3 is based on Figure 1 The method obtains the correlation coefficients between the lower component signals of different decomposition levels and the original signal. As shown in Table 3, the optimal decomposition level of the discrete wavelet transform in this embodiment is 5 (6-1=5).

[0100] Figure 3 (b1) is for Figure 3 (c) The approximate signal A5 and detail signals D1-D5 of each layer obtained by discrete wavelet transform. Figure 3 (b2) shows the decimal signal 1D-LTS obtained by the proposed method. Due to space limitations, only the autocorrelation function and spectrum of the component signal with the best performance are shown. Figure 3 (c1)-(c2) are the autocorrelation functions of 1D-LTS corresponding to D5 and A5; Figure 3 (d1)-(d2) is Figure 3 Spectrum of (c1)-(c2).

[0101] Table 3 Correlation coefficient between detail signal and original signal after DWT - Example 1

[0102] Detail signal D1 D2 D3 D4 D5 D6 Correlation coefficient 0.696 0.501 0.359 0.263 0.201 0.130

[0103] from Figure 3 It can be found from the analysis of (d1)-(d3) that after the simulation signal is processed by the method proposed by the present invention, the following obvious characteristic frequency components can be observed:

[0104] 1) In Figure 3 In (d1)-(d3), there are significant frequencies of 284 Hz (284 / 2=142≈141.6=(64.8+76.8)), 624.7 Hz ((627.7+64.8) / 9=76.94) and 1424 Hz (1424 / 10=142.4≈141.6=(64.8+76.8)). These frequencies correspond to the characteristic frequencies of the composite fault of the inner and outer rings of the cage friction, marked as squares.

[0105] 2) In Figure 3 In (d2)-(d3), there are prominent frequencies of 1330Hz (1330-6*200) / 2=65.0), 718Hz (718 / 11=65.3) and 1308Hz (1308 / 20=65.4) corresponding to the characteristic frequencies of the retainer friction outer ring fault, which are marked as diamonds. At the same time, there are prominent frequencies of 1351Hz (1351-6*200) / 2=75.5) and 1381Hz (1381 / 18=76.7) corresponding to the characteristic frequencies of the retainer friction inner ring fault, which are marked as circles.

[0106] From the analysis of 1)-2), it can be found that the intermediate bearing has a composite fault of friction between the cage and the inner ring and between the cage and the outer ring, which is completely consistent with the set fault type. In other words, the typical frequency extracted by the present invention is completely consistent with the fault type of the intermediate bearing set by the simulation signal, and can be used to determine the composite fault of the intermediate bearing.

[0107] It can be seen that: according to the fault identification method based on wavelet transform, second-order difference and 1D-LBP proposed by the present invention, the noise component is effectively suppressed in the spectrum analysis of the obtained signal. Based on the simulation signal, the typical frequency components in the signal spectrum obtained by the method of the present invention are mainly manifested as characteristic frequencies corresponding to the intermediate bearing fault type, realizing the accurate identification of the bearing composite fault type. At the same time, the present invention is also applicable to the fault identification of other types of bearings, and has excellent engineering application value.

[0108] A bearing composite fault identification device based on wavelet transform, second-order difference and 1D-LBP, comprising:

[0109] Acquisition module: used to obtain bearing vibration signals;

[0110] Decomposition layer number module: used to determine the optimal decomposition layer number of discrete wavelet transform based on the correlation coefficient;

[0111] Discrete wavelet transform module: It is used to obtain the optimal number of decomposition layers, perform discrete wavelet transform on the bearing vibration signal, and obtain the approximate signal and detail signal.

[0112] Second-order difference operation module: used to perform second-order difference operation on the approximate signal and the detail signal, obtain the corresponding second-order difference sequence, and describe the impact characteristics of the bearing failure;

[0113] Signal quantization and decimal signal acquisition module: used to obtain any second-order difference sequence, take the local average value of the moving window of the second-order difference sequence as the criterion, and use the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence to characterize the local characteristic information of the bearing vibration signal;

[0114] Noise reduction module: used to perform noise reduction processing on the decimal signal of the acquired second-order difference sequence to obtain a noise-reduced signal;

[0115] Extraction and identification module: It is used to extract the prominent frequencies in the spectrum of the acquired noise-reduced signal by using the spectrum analysis method, and to extract the bearing fault characteristic information and identify the fault type according to the bearing fault characteristic frequency calculation formula.

[0116] A computer device comprises: a processor and a memory, wherein the memory stores a program module, and wherein the program module runs on the processor to implement the method described above.

[0117] A readable storage medium stores a program module, wherein the program module can implement the method when executed in a processor.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP, characterized in that: The steps include: Obtain bearing vibration signal; Determine the optimal number of decomposition levels of discrete wavelet transform based on the correlation coefficient; With the optimal decomposition layer number obtained, discrete wavelet transform is performed on the bearing vibration signal to obtain the approximate signal and the detail signal; Perform second-order difference operations on the approximate signal and the detail signal to obtain the corresponding second-order difference sequences, and describe the impact characteristics of the bearing failure. Get any second-order difference sequence, take the local average value of the moving window of the second-order difference sequence as the criterion, and use the one-dimensional local binary pattern method to get the decimal signal of the second-order difference sequence to characterize the local characteristic information of the bearing vibration signal; Performing noise reduction processing on the decimal signal of the acquired second-order difference sequence to obtain a noise-reduced signal; The spectrum analysis method is used to extract the prominent frequencies in the spectrum of the obtained denoised signal, and the bearing fault characteristic information is extracted and the fault type is identified based on the bearing fault characteristic frequency calculation formula.

2. The bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP according to claim 1 is characterized in that: The process of determining the optimal number of decomposition layers is as follows: Let X t is the signal to be decomposed, H t is a component signal after discrete wavelet transform decomposition, then the correlation coefficient between the two is ρ XH , can be obtained by formula (1): Among them, Cov(X t ,H t ) is X t and H t The covariance of , Var(·) represents the variance of the signal; The number of decomposition layers of discrete wavelet transform is adaptively determined. When the Kth layer is reached and the correlation coefficient between the component signal and the original signal is less than the correlation coefficient threshold, the actual number of decomposition layers is determined to be K-1, that is, the optimal number of decomposition layers is updated to K=K-1.

3. The bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP according to claim 1 is characterized in that: The decomposed detail signal and the approximate signal are operated by the following second-order difference operation. The detail signal d k (n i ) The second-order difference sequence F dk (n i ) is expressed as follows: F dk (n i )=d k (t j +1)-2d k (t j )+d k (t j -1) t j =2,3,…,n-1; n i =t j -1 (2) The approximate signal a K (t i ) is the second-order difference sequence F ak (t i ) is expressed as follows: F ak (n i )=a k (t j +1)-2a k (t j )+a k (t j -1) t j =2,3,…,n-1; n i =t j -1 (3)。 4. The bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP according to claim 1 is characterized in that: The process of obtaining any second-order difference sequence, taking the local average value of the moving window of the second-order difference sequence as the criterion, and adopting the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence is as follows: The second-order difference sequence D of the detail signal dk (n i ) as an example; (a) Let P ji (i=1,2,…8) are the 8 adjacent points of the jth moving window, calculate P ji The local mean Ed kj : (b) Taking the local average value Ed kj As the criterion, for the second-order difference sequence F dk (n i ) performing binarization based on the 1D-LBP algorithm to obtain a 1D-LBP signal; Let the binarized sequence corresponding to the jth moving window be F(g ji ), g ji is the i-th point P in the j-th moving window i The value of and the local average value Ed kj The calculation process is shown in formulas (5)-(6). g ji =P ji -Ed kj i=1,2,…,8 j=n-7 (5) (c) The locally binarized sequence F(g ji ), and are successively reconverted into decimal signals 1D-LTS(j) that can reflect the signal texture characteristics.

5. The bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP according to claim 1 is characterized in that: The window length of the moving window is 8, and the moving step length is 1.

6. The bearing composite fault identification method based on wavelet transform, second-order difference and 1D-LBP according to claim 1 is characterized in that: The noise reduction process uses an autocorrelation function to perform noise reduction.

7. A bearing composite fault identification device based on wavelet transform, second-order difference and 1D-LBP, characterized in that: include: Acquisition module: used to obtain bearing vibration signals; Decomposition layer number module: used to determine the optimal decomposition layer number of discrete wavelet transform based on the correlation coefficient; Discrete wavelet transform module: used to implement discrete wavelet transform on the bearing vibration signal to obtain the approximate signal and detail signal in order to obtain the optimal decomposition layer number; Second-order difference operation module: used to perform second-order difference operation on the approximate signal and the detail signal, obtain the corresponding second-order difference sequence, and describe the impact characteristics of the bearing failure; Signal quantization and decimal signal acquisition module: used to obtain any second-order difference sequence, take the local average value of the moving window of the second-order difference sequence as the criterion, and use the one-dimensional local binary pattern method to obtain the decimal signal of the second-order difference sequence to characterize the local characteristic information of the bearing vibration signal; Noise reduction module: used to perform noise reduction processing on the decimal signal of the acquired second-order difference sequence to obtain a noise-reduced signal; Extraction and identification module: It is used to extract the prominent frequencies in the spectrum of the acquired noise-reduced signal by using the spectrum analysis method, and to extract the bearing fault characteristic information and identify the fault type according to the bearing fault characteristic frequency calculation formula.

8. A computer device comprising: A processor and a memory, wherein the memory stores a program module, wherein the program module runs on the processor to implement the method according to any one of claims 1 to 6.

9. A readable storage medium storing a program module, characterized in that: The program module is executed in a processor to implement the method according to any one of claims 1 to 6.

Images