CN108896306A - Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP - Google Patents
Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP Download PDFInfo
- Publication number
- CN108896306A CN108896306A CN201810252985.5A CN201810252985A CN108896306A CN 108896306 A CN108896306 A CN 108896306A CN 201810252985 A CN201810252985 A CN 201810252985A CN 108896306 A CN108896306 A CN 108896306A
- Authority
- CN
- China
- Prior art keywords
- atom
- omp
- signal
- dictionary
- bearing fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Abstract
The present invention relates to bearing failure diagnosis fields, disclose a kind of Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP, extract the precision recognized with fault type to promote bearing fault characteristics.The present invention constructs atom dictionary according to bearing fault vibration signal characteristics, optimization algorithm is incorporated in OMP method, the atom with signal best match to be analyzed is adaptively obtained in dictionary by optimization algorithm, obtained atom pair signal is utilized to be reconstructed, then Envelope Analysis is carried out to reconstruction signal, and then realizes the accurate accurate identification extracted with fault type of bearing fault characteristics.The present invention is suitable for rolling bearing fault diagnosis.
Description
Technical field
The present invention relates to bearing failure diagnosis fields, in particular to the bearing fault based on adaptive atom dictionary OMP is examined
Disconnected method.
Background technique
Critical mechanical component of the rolling bearing as rotating machinery is widely used in various industrial circles, runs shape
State monitoring and fault diagnosis is for guaranteeing equipment Reliability, safety accident being avoided to have great importance.However, Practical Project
In, since bearing fault characteristic information is often flooded by strong background noise and other labile elements, bearing fault characteristics letter
Breath has been extracted into a difficult task.
The rarefaction representation of signal is to decompose in excessively complete atom dictionary to signal, is decomposed compared to tradition based on base
Signal analysis method, such as：Short Time Fourier Transform, wavelet transformation etc., rarefaction representation have multiple advantages：(1) meet signal
The needs of rarefaction representation, the useful information for including in signal will focus on a small number of atoms, be conducive to the extraction of information；(2) full
The needs that sufficient signal adaptive indicates are sparse adaptively to select and signal immanent structure best from excessively complete dictionary
The atom matched indicates signal；(3) time-frequency characteristic of non-stationary signal can be effectively disclosed, as long as the atom in excessively complete dictionary has
There is good time-frequency locality, the non-stationary property of signal can be effectively disclosed using these atoms.Because of these advantages, signal
Rarefaction representation becomes a research hotspot of signal and field of image processing in recent years, and research is concentrated mainly on two o'clock：How
Construct the atom dictionary for signal immanent structure best match；The method for how designing and improving sparse signal representation improves
Computational efficiency.
Currently based on the reconstruction signal of Gabor atom match tracing (MP) method of genetic algorithm, the bearing completed is former
The accurate recognition effect of the extraction and fault type that hinder feature is poor, is increasingly difficult to meet production requirement now.
Summary of the invention
The technical problem to be solved by the present invention is to：A kind of bearing failure diagnosis based on adaptive atom dictionary OMP is provided
Method extracts the precision recognized with fault type to promote bearing fault characteristics.
To achieve the above object, the technical solution adopted by the present invention is that：It is constructed according to bearing fault vibration signal characteristics former
Sub- dictionary incorporates optimization algorithm in OMP method, is adaptively obtained with signal to be analyzed most in dictionary by optimization algorithm
Good matched atom utilizes obtained atom pair signal to be reconstructed, and then carries out Envelope Analysis to reconstruction signal, and then realize
The accurate accurate identification extracted with fault type of bearing fault characteristics.
Further, the present invention incorporates whale optimization algorithm (WOA) in OMP method, by WOA optimization algorithm in dictionary
In adaptively obtain and the atom of residue signal best match.In addition to WOA optimization algorithm, the present invention can also select grey wolf excellent
Change other optimization algorithms such as algorithm, locust optimization algorithm (GOA).
Further, specific steps of the invention include：
Step 1：Acquire the vibration signal f of bearing；
Step 2：The decomposition number m of specified OMP method；
Step 3：Initialize residue signal R0F, even R0F=f, the value range of specified atom dictionary parameter, and initialize
WOA optimization algorithm；
Step 4, the search of WOA optimization algorithm and current residue signal R are utilizednThe atom of f best matchAtomFor
With the current maximum atom of residue signal inner product, n is the current decomposition number of OMP method；
Step 5, to atomIt is orthogonalized processing, obtains atom un；
Step 6, residue signal R is calculatednF is in atom unOn projection；
Step 7, judge whether OMP algorithm meets decomposition termination condition, if satisfied, then entering step 8；Otherwise step is utilized
6 projections acquired and current residue signal RnF obtains residue signal R next timen+1F, and enable n=n+1, return step 4 after
It is continuous to execute；
Projection calculated summation when step 8, to all previous decomposition, obtain projection and, and will projection and as reconstruction signal,
Then Envelope Analysis is carried out to reconstruction signal, differentiates bearing fault.
Specifically, step 1 acquires the vibration signal f of bearing by acceleration transducer.
Specifically, the expression formula of the atom constructed according to bearing fault vibration signal characteristics is：
In formula, γ=(s, p, u, ξ, θ) is atomic parameter group；S is scale factor, and p is damped coefficient, and u is shift factor,
ξ is frequency factor, and θ is phase factor, and t is the time.
Further, step 4 utilizes optimization algorithm search and current residue signal RnF best match atomProcess table
It is shown as：
In formula；Fitness indicates fitness function or objective function,Best obtained is decomposed for OMP n-th
With atom.
Further, atom u is obtained in step 5nProcess completed by Schmidt process, including：It enables firstThen
Further, the projection acquired in step 7 using step 6 and current residue signal RnF obtains next time residual
Remaining signal Rn+1The formula of f is：
The beneficial effects of the invention are as follows：The present invention can adaptively choose from atom dictionary best with signal to be analyzed
Matched atom, since the atom is according to designed by bearing fault vibration signal characteristics, can effectively extract bearing due to therefore
Shock characteristic caused by hindering, in addition the present invention incorporates WOA optimization algorithm in OMP method, can greatly improve the meter of OMP method
Efficiency and precision is calculated, to realize the Precise Diagnosis of bearing fault.
Detailed description of the invention
Fig. 1 is the flow chart of embodiment；
Fig. 2 is the time domain waveform of original vibration signal in embodiment；
Fig. 3 is the envelope spectrum of original vibration signal in embodiment；
Fig. 4 is the resulting reconstruction signal of embodiment；
Fig. 5 is the envelope spectrum of reconstruction signal obtained by embodiment；
Fig. 6 is traditional resulting reconstruction signal of Gabor dictionary pattern matching based on genetic algorithm；
Fig. 7 is the envelope spectrum of traditional resulting reconstruction signal of Gabor dictionary pattern matching based on genetic algorithm.
Specific embodiment
The present invention constructs atom dictionary according to bearing fault vibration signal characteristics, and WOA optimization algorithm is incorporated OMP method
In, the atom with signal best match to be analyzed is adaptively obtained in dictionary by WOA optimization algorithm, utilizes obtained original
Signal is reconstructed in son, then to reconstruction signal carry out Envelope Analysis, and then realize bearing fault characteristics it is accurate extraction and
The accurate identification of fault type.Orthogonal matching pursuit (OMP) method, can be secondary most in locally searching as a kind of sparse representation method
Excellent sparse decomposition, guarantee computational accuracy while algorithm complexity it is relatively low, therefore the present invention can effectively extract bearing due to
Shock characteristic caused by failure, and by the way that the computational efficiency and essence of OMP method will be can be further improved in WOA involvement OMP
Degree, to realize accurate, the efficient diagnosis of bearing fault.
Based on above-mentioned thought, embodiment provides a kind of Method for Bearing Fault Diagnosis, and workflow is as shown in Figure 1, specific
Steps are as follows：
Step 1：Bearing vibration signal f is acquired by acceleration transducer.According to bearing fault vibration signal characteristics institute structure
The expression formula for the atom made is：
In formula, t is the time, and atomic parameter group is γ (s, p, u, ξ, θ), and the meaning and value interval that parameter indicates are as follows：
S --- scale factor, s ∈ [1, N] (N is signal sampling points)；
P --- damped coefficient, p ∈ (0,1)；
U --- shift factor, u ∈ [0, N-1]；
ξ --- frequency factor, value interval usually cover bearing resonance frequency i.e. ξ ∈ [0,6000]；
θ --- phase factor, θ ∈ [0,2 π]
Step 2：The decomposition number m of specified OMP method.
Step 3：Initialize residue signal R0F, even R0F=f, the value range of specified atom dictionary parameter, and initialize
WOA optimization algorithm, including whale population quantity and WOA algorithm maximum number of iterations.
Step 4, the search of WOA optimization algorithm and current residue signal R are utilizednThe atom of f best matchAtomFor
With the current maximum atom of residue signal inner product, n is the current decomposition number of OMP method.Using optimization algorithm search and currently
Residue signal RnThe atom of f best matchProcedural representation be：
In formula；Fitness indicates fitness function or objective function,Best obtained is decomposed for OMP n-th
With atom.
Step 5, using Schmidt process to atomIt is orthogonalized, obtains atom un。unAcquisition process
Including：
It enables firstThen it is obtained by following equation：
Step 6, current residue signal R is calculatednF is in atom unOn projection, i.e.,
Step 7, judge whether OMP algorithm meets decomposition termination condition, if satisfied, then entering step 8；Otherwise step is utilized
6 projections acquiredAnd current residue signal RnF obtains residue signal R next timen+1F, and n=n+1 is enabled,
Return step 4 continues to execute.Obtain residue signal R next timen+1The formula of f is：
Projection calculated summation when step 8, to all previous decomposition, obtain projection and, and will projection and as reconstruction signal
fReconstruct, i.e.,
Then to reconstruction signal fReconstructEnvelope Analysis is carried out, differentiates bearing fault.
Below in conjunction with specific example --- certain housing washer fault diagnosis further illustrates embodiment.Test axis
It is as shown in table 1 below to hold specification：
1 test bearing specification of table
When test, motor drives test bearing rotation, and wherein motor turn is frequently 30.9Hz, signal sampling frequencies 10kHz,
Sampling number N=4096, test bearing outer ring fault characteristic frequency, which can be obtained, according to bearing specification and motor turn frequency is：Fo=
79.3Hz。
The first step：Original vibration signal f (the unit g), Fig. 2, Fig. 3 of test bearing vibration are obtained by acceleration transducer
The respectively time domain waveform and envelope spectrum of original vibration signal f.As seen from the figure, depositing due to noise and other interference components
Apparent periodic shock, while envelope spectrum axis bearing outer-ring fault signature are being difficult to observe by vibration signal time domain waveform
Frequency is almost flooded by the strong jamming frequency of surrounding, and therefore, it is difficult to carry out accurate discrimination to bearing fault.
Second step：The maximum of specified OMP algorithm decomposes number, this example m=70.
Third step：Initialize residue signal, i.e. R0F=f；Atomic parameter value range is specified as follows：s∈[1,4096],p
∈(0,1),u∈[0,4096-1],ξ∈[0,6000],θ∈[0,2π]；The whale population number and maximum number of iterations of WOA algorithm
Respectively 30 and 10.
The calculation method of 4-8 through the above steps, finally obtained reconstruction signal time domain waveform are as shown in Figure 4.It can by Fig. 4
Know, the periodic shock of bearing outer ring failure has obtained accurate extraction, and the time interval of periodic shock is bearing outer ring failure
The inverse of characteristic frequency.Pass through the reconstruction signal f to Fig. 4ReconstructEnvelope Analysis is carried out, the packet of the reconstruction signal shown in fig. 5 is obtained
Network is composed, and can be clearly observed very much bearing outer ring fault characteristic frequency F in envelope spectrumoAnd its frequency multiplication (2Fo、3Fo).Therefore, may be used
Test bearing is judged there are outer ring failure, diagnostic result is consistent with experimental program, it was demonstrated that the validity of embodiment.
The superiority of method in order to further illustrate the present invention, Fig. 6, Fig. 7 give Gabor of the tradition based on genetic algorithm
The reconstruction signal and its envelope spectrum of atom match tracing (MP) method.4,6 and Fig. 5 of comparison diagram, 7 respectively, it is clear that embodiment is in axis
Hold better effect in fault diagnosis.Meanwhile the fortune of embodiment and tradition based on genetic algorithm Gabor atom match tracing MP method
The row time is respectively 19.87 seconds and 24.04 seconds, it is seen that embodiment computational efficiency is higher, about the 1.21 of the latter times.
Claims (8)
1. the Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP, which is characterized in that according to bearing fault vibration signal
Feature construction atom dictionary, will optimization algorithm incorporate OMP method in, by optimization algorithm in dictionary adaptively obtain with to
The atom for analyzing signal best match, utilizes obtained atom pair signal to be reconstructed, and then carries out envelope point to reconstruction signal
Analysis, and then realize the accurate accurate identification extracted with fault type of bearing fault characteristics.
2. the Method for Bearing Fault Diagnosis as described in claim 1 based on adaptive atom dictionary OMP, which is characterized in that will
WOA optimization algorithm incorporates in OMP method, is adaptively obtained and residue signal best in dictionary by WOA optimization algorithm
The atom matched.
3. the Method for Bearing Fault Diagnosis as claimed in claim 2 based on adaptive atom dictionary OMP, which is characterized in that tool
Body step includes：
Step 1：Acquire the vibration signal f of bearing；
Step 2：The decomposition number m of specified OMP method；
Step 3：Initialize residue signal R0F, even R0F=f, the value range of specified atom dictionary parameter, and initialize WOA
Optimization algorithm；
Step 4, the search of WOA optimization algorithm and current residue signal R are utilizednThe atom of f best matchAtomFor with work as
The preceding maximum atom of residue signal inner product, n are the current decomposition number of OMP method；
Step 5, to atomIt is orthogonalized processing, obtains atom un；
Step 6, current residue signal R is calculatednF is in atom unOn projection；
Step 7, judge whether OMP algorithm meets decomposition termination condition, if satisfied, then entering step 8；Otherwise it is asked using step 6
The projection obtained and current residue signal RnF obtains residue signal R next timen+1F, and n=n+1 is enabled, return step 4 continues
It executes；
Projection calculated summation when step 8, to all previous decomposition, obtain projection and, and will projection and as reconstruction signal, then
Envelope Analysis is carried out to reconstruction signal, differentiates bearing fault.
4. the Method for Bearing Fault Diagnosis as claimed in claim 3 based on adaptive atom dictionary OMP, which is characterized in that step
Rapid 1 acquires the vibration signal f of bearing by acceleration transducer.
5. the Method for Bearing Fault Diagnosis as claimed in claim 3 based on adaptive atom dictionary OMP, which is characterized in that root
The expression formula of the atom constructed according to bearing fault vibration signal characteristics is：
In formula, γ=(s, p, u, ξ, θ) is atomic parameter group；S is scale factor, and p is damped coefficient, and u is shift factor, and ξ is
Frequency factor, θ are phase factor, and t is the time.
6. the Method for Bearing Fault Diagnosis as claimed in claim 5 based on adaptive atom dictionary OMP, which is characterized in that step
Rapid 4 utilize the search of WOA optimization algorithm and current residue signal RnF best match atomProcedural representation be：
In formula；Fitness indicates fitness function or objective function,It is former that best match obtained is decomposed for OMP n-th
Son.
7. the Method for Bearing Fault Diagnosis as claimed in claim 3 based on adaptive atom dictionary OMP, which is characterized in that step
Atom u is obtained in rapid 5nProcess completed by Schmitt orthogonalization method, including：It enables firstThen
8. the Method for Bearing Fault Diagnosis as claimed in claim 7 based on adaptive atom dictionary OMP, which is characterized in that step
The projection acquired in rapid 7 using step 6 and current residue signal RnF obtains residue signal R next timen+1The formula of f is：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252985.5A CN108896306A (en) | 2018-03-26 | 2018-03-26 | Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252985.5A CN108896306A (en) | 2018-03-26 | 2018-03-26 | Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108896306A true CN108896306A (en) | 2018-11-27 |
Family
ID=64342316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810252985.5A Pending CN108896306A (en) | 2018-03-26 | 2018-03-26 | Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108896306A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109507292A (en) * | 2018-12-26 | 2019-03-22 | 西安科技大学 | A kind of method for extracting signal |
| CN109738519A (en) * | 2019-01-04 | 2019-05-10 | 国网四川省电力公司广安供电公司 | A kind of denoising method of transformer high-voltage bushing lead ultrasound detection |
| CN110136165A (en) * | 2019-05-17 | 2019-08-16 | 河南科技学院 | A kind of mutation movement method for tracking target based on the optimization of adaptive whale |
| CN111582128A (en) * | 2020-04-30 | 2020-08-25 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
| CN111665050A (en) * | 2020-06-04 | 2020-09-15 | 燕山大学 | Rolling bearing fault diagnosis method based on clustering K-SVD algorithm |
| CN112613573A (en) * | 2020-12-30 | 2021-04-06 | 五邑大学 | Rolling bearing fault diagnosis method based on self-adaptive termination criterion OMP |
| CN112988918A (en) * | 2021-04-06 | 2021-06-18 | 中车青岛四方机车车辆股份有限公司 | Bearing fault dictionary construction method, analysis method and system |
| CN114739669A (en) * | 2022-03-07 | 2022-07-12 | 西安交通大学 | Rolling bearing state monitoring method and device based on terahertz radar |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927761A (en) * | 2014-05-05 | 2014-07-16 | 重庆大学 | Fault weak signal feature extraction method based on sparse representation |
| CN105258947A (en) * | 2015-11-06 | 2016-01-20 | 北京航空航天大学 | Compressed sensing-based antifriction bearing fault diagnosis method under working condition disturbance condition |
| CN105424359A (en) * | 2015-11-25 | 2016-03-23 | 华南理工大学 | Sparse-decomposition-based hybrid fault feature extraction method of gear wheel and bearing |
| CN107368809A (en) * | 2017-07-20 | 2017-11-21 | 合肥工业大学 | A kind of bearing fault sorting technique based on rarefaction representation and dictionary learning |
-
2018
- 2018-03-26 CN CN201810252985.5A patent/CN108896306A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927761A (en) * | 2014-05-05 | 2014-07-16 | 重庆大学 | Fault weak signal feature extraction method based on sparse representation |
| CN105258947A (en) * | 2015-11-06 | 2016-01-20 | 北京航空航天大学 | Compressed sensing-based antifriction bearing fault diagnosis method under working condition disturbance condition |
| CN105424359A (en) * | 2015-11-25 | 2016-03-23 | 华南理工大学 | Sparse-decomposition-based hybrid fault feature extraction method of gear wheel and bearing |
| CN107368809A (en) * | 2017-07-20 | 2017-11-21 | 合肥工业大学 | A kind of bearing fault sorting technique based on rarefaction representation and dictionary learning |
Non-Patent Citations (1)
| Title |
|---|
| XIN ZHANG ET AL: "Bearing fault diagnosis using a whale optimization algorithm-optimized orthogonal matching pursuit with a combined time–frequency atom dictionary", 《MECHANICAL SYSTEMS AND SIGNAL PROCESSING》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109507292B (en) * | 2018-12-26 | 2021-08-06 | 西安科技大学 | Signal extraction method |
| CN109507292A (en) * | 2018-12-26 | 2019-03-22 | 西安科技大学 | A kind of method for extracting signal |
| CN109738519A (en) * | 2019-01-04 | 2019-05-10 | 国网四川省电力公司广安供电公司 | A kind of denoising method of transformer high-voltage bushing lead ultrasound detection |
| CN109738519B (en) * | 2019-01-04 | 2021-08-17 | 国网四川省电力公司广安供电公司 | Denoising method for ultrasonic detection of lead of high-voltage bushing of transformer |
| CN110136165A (en) * | 2019-05-17 | 2019-08-16 | 河南科技学院 | A kind of mutation movement method for tracking target based on the optimization of adaptive whale |
| CN111582128B (en) * | 2020-04-30 | 2022-05-03 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
| CN111582128A (en) * | 2020-04-30 | 2020-08-25 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
| CN111665050A (en) * | 2020-06-04 | 2020-09-15 | 燕山大学 | Rolling bearing fault diagnosis method based on clustering K-SVD algorithm |
| CN112613573A (en) * | 2020-12-30 | 2021-04-06 | 五邑大学 | Rolling bearing fault diagnosis method based on self-adaptive termination criterion OMP |
| CN112613573B (en) * | 2020-12-30 | 2023-10-31 | 五邑大学 | Rolling bearing fault diagnosis method based on self-adaptive termination criterion OMP |
| CN112988918A (en) * | 2021-04-06 | 2021-06-18 | 中车青岛四方机车车辆股份有限公司 | Bearing fault dictionary construction method, analysis method and system |
| CN112988918B (en) * | 2021-04-06 | 2022-10-21 | 中车青岛四方机车车辆股份有限公司 | Bearing fault dictionary construction method, analysis method and system |
| CN114739669A (en) * | 2022-03-07 | 2022-07-12 | 西安交通大学 | Rolling bearing state monitoring method and device based on terahertz radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108896306A (en) | Method for Bearing Fault Diagnosis based on adaptive atom dictionary OMP | |
| Feng et al. | Atomic decomposition and sparse representation for complex signal analysis in machinery fault diagnosis: A review with examples | |
| Wang et al. | Constrained independent component analysis and its application to machine fault diagnosis | |
| Wang et al. | A novel weighted sparse representation classification strategy based on dictionary learning for rotating machinery | |
| CN112101245B (en) | Short-time Fourier transform mechanical impact feature extraction method based on frequency domain window function | |
| Wang et al. | Transients extraction based on averaged random orthogonal matching pursuit algorithm for machinery fault diagnosis | |
| CN106895985B (en) | The fault-signal noise reduction of high-speed rod-rolling mill reconstructs characteristic recognition method | |
| CN109374293B (en) | Gear fault diagnosis method | |
| Zhao et al. | Fast sparsity-assisted signal decomposition with nonconvex enhancement for bearing fault diagnosis | |
| CN111582128B (en) | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary | |
| Chen et al. | Fault identification method for planetary gear based on DT-CWT threshold denoising and LE | |
| Antoni et al. | Cyclostationarity in condition monitoring: 10 years after | |
| CN111665050B (en) | Rolling bearing fault diagnosis method based on clustering K-SVD algorithm | |
| Ma et al. | An improved time-frequency analysis method for instantaneous frequency estimation of rolling bearing | |
| Liu et al. | Maximum correntropy criterion-based blind deconvolution and its application for bearing fault detection | |
| Feng et al. | A fault diagnosis for rolling bearing based on multilevel denoising method and improved deep residual network | |
| Gong et al. | Application of optimized multiscale mathematical morphology for bearing fault diagnosis | |
| Zhou et al. | Sparse dictionary analysis via structure frequency response spectrum model for weak bearing fault diagnosis | |
| Zhao et al. | A feature extraction method based on LMD and MSE and its application for fault diagnosis of reciprocating compressor | |
| Johansson | Wavelet Theory and some of its Applications | |
| Xiong et al. | Early fault diagnosis of rolling bearings based on parameter-adaptive multipoint optimal minimum entropy deconvolution adjusted and dynamic mode decomposition | |
| Yan et al. | Impact of wavelet basis on vibration analysis for rolling bearing defect diagnosis | |
| CN113704688B (en) | Method for recovering missing vibration signals based on variable decibels leaf parallel factor decomposition | |
| He et al. | An automatic abrupt information extraction method based on singular value decomposition and higher-order statistics | |
| CN112613573B (en) | Rolling bearing fault diagnosis method based on self-adaptive termination criterion OMP |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |
|
| RJ01 | Rejection of invention patent application after publication |