Sparse Envelope Spectra for Feature Extraction of Bearing Faults Based on NMF
Source abstract
Abstract
Periodic impulses and the oscillation response signal are the vital feature indicators of rolling bearing faults. However, finding the suitable feature frequency band is usually difficult due to the interferences of other components and multiple resonance regions. According to the characteristics of non-negative matrix factorization (NMF) on a spectrogram, the feature extraction method from a sparse envelope spectrum for rolling bearing faults is proposed in this paper. On the basis of the time–frequency distribution (TFD) of the periodic transient oscillations, the basic matrix can be interpreted as the spectral bases, and the time weight matrix corresponding to spectral bases can be extracted by NMF. Because the bases and the weights have a one-to-one correspondence, the frequency band filtering with the basic component and the time domain envelope of the weight vector are calculated respectively. Then, the sparse envelope spectrum can be derived by the inner product of the above results. The effectiveness of the proposed method is verified by simulations and experiments. Compared with band-pass filtering and spectral kurtosis methods, and considering the time weights and corresponding the spectral bases for the periodic transient oscillations, the weak fault-rated feature can be enhanced in the sparse spectrum, while other components and noise are weakened. Therefore, the proposed method can reduce the requirement of selecting frequency band filtering.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Xi’an 710049, China
State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710054, China
Funding
National Natural Science Foundation of China · China Postdoctoral Science Foundation
References (38)
Show source-provided references
1. Towards automatic detection of local bearing defects in rotating machines10.1016/j.ymssp.2003.12.004 ↗
2. Detection of defects in rolling element bearings by vibration monitoring
3. Reif, Z., and Lai, M. (1989). Detection of Developing Bearing Failures by Means of Vibration, The American Society of Mechanical Engineers.
4. Rolling element bearing fault diagnosis using wavelet packets10.1016/S0963-8695(01)00044-5 ↗
5. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics10.1016/j.jsv.2005.03.007 ↗
6. Early fault detection in automotive ball bearings using the minimum variance cepstrum10.1016/j.ymssp.2013.02.017 ↗
7. Vibration monitoring of rolling element bearings by the high-frequency resonance technique—A review10.1016/0301-679X(84)90076-8 ↗
8. The spectral kurtosis: A useful tool for characterising non-stationary signals10.1016/j.ymssp.2004.09.001 ↗
9. The spectral kurtosis: Application to the vibratory surveillance and diagnostics of rotating machines10.1016/j.ymssp.2004.09.002 ↗
10. A novel method for the optimal band selection for vibration signal demodulation and comparison with the kurtogram10.1016/j.ymssp.2010.05.018 ↗
11. Estimation of modal parameters using the sparse component analysis based underdetermined blind source separation10.1016/j.ymssp.2013.11.018 ↗
12. Modal parameter identification through gabor expansion of response signals10.1016/S0022-460X(02)01381-0 ↗
13. A study of joint time-frequency analysis-based modal analysis10.1109/TIM.2006.884137 ↗
14. Modal identification based on the time–frequency domain decomposition of unknown-input dynamic tests10.1016/j.ijmecsci.2013.03.005 ↗
15. Rolling element bearing faults diagnosis based on optimal morlet wavelet filter and autocorrelation enhancement10.1016/j.ymssp.2009.11.011 ↗
16. Wavelet based demodulation of vibration signals generated by defects in rolling element bearings10.1155/2002/592436 ↗
17. Wodecki, J., Kruczek, P., Wyłomańska, A., Bartkowiak, A., and Zimroz, R. (September, January 29). Novel method of informative frequency band selection for vibration signal using nonnegative matrix factorization of short-time fourier transform. Proceedings of the 2017 IEEE 11th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED), Tinos, Greece.10.1109/DEMPED.2017.8062345 ↗
18. Local fault detection of rolling element bearing components by spectrogram clustering with semi-binary NMF
19. Feature spectrum extraction algorithm for rolling bearings based on spectrogram and constrained nmf
20. Grais, E.M., and Erdogan, H. (2011, January 6–8). Single channel speech music separation using nonnegative matrix factorization and spectral masks. Proceedings of the 2011 17th International Conference on Digital Signal Processing (DSP), Corfu, Greece.10.1109/ICDSP.2011.6004924 ↗
21. King, B., Févotte, C., and Smaragdis, P. (2012, January 23–26). Optimal cost function and magnitude power for nmf-based speech separation and music interpolation. Proceedings of the 2012 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Santander, Spain.10.1109/MLSP.2012.6349726 ↗
22. Speech enhancement under low snr conditions via noise estimation using sparse and low-rank nmf with kullback–leibler divergence10.1109/TASLP.2015.2427520 ↗
23. Topographic nmf for data representation10.1109/TCYB.2013.2294215 ↗
24. Raj, B., Singh, R., and Virtanen, T. (2011, January 27–31). Phoneme-dependent nmf for speech enhancement in monaural mixtures. Proceedings of the Twelfth Annual Conference of the International Speech Communication Association, Florence, Italy.10.21437/Interspeech.2011-427 ↗
25. Kalayeh, M.M., Idrees, H., and Shah, M. (2014, January 23–28). Nmf-knn: Image annotation using weighted multi-view non-negative matrix factorization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.31 ↗
26. Fast nonnegative matrix factorization: An active-set-like method and comparisons10.1137/110821172 ↗
27. Ding, C., He, X., Simon, H., and Jin, R. (2005). On the equivalence of nonnegative matrix factorization and k-means-spectral clustering. Proceedings of the 2005 SIAM International Conference on Data Mining, SIAM.10.1137/1.9781611972757.70 ↗
28. Lin, C.J. (2007). Projected Gradient Methods for Nonnegative Matrix Factorization, MIT Press.10.1162/neco.2007.19.10.2756 ↗
29. On the convergence of the block nonlinear gauss–seidel method under convex constraints10.1016/S0167-6377(99)00074-7 ↗
30. Algorithms and applications for approximate nonnegative matrix factorization10.1016/j.csda.2006.11.006 ↗
31. Kim, D., Sra, S., and Dhillon, I.S. (2007). Fast newton-type methods for the least squares nonnegative matrix approximation problem. Proceedings of the 2007 SIAM International Conference on Data Mining, SIAM.10.1137/1.9781611972771.31 ↗
32. Kim, J., and Park, H. (2008, January 15–19). Toward faster nonnegative matrix factorization: A new algorithm and comparisons. Proceedings of the Eighth IEEE International Conference on Data Mining, ICDM ‘08, Pisa, Italy.10.1109/ICDM.2008.149 ↗
33. Fast algorithm for the solution of large-scale non-negativity-constrained least squares problems
34. Cichocki, A., Zdunek, R., Phan, A.H., and Amari, S.-I. (2009). Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-Way Data Analysis and Blind Source Separation, John Wiley & Sons.10.1002/9780470747278 ↗
35. Application of an improved maximum correlated kurtosis deconvolution method for fault diagnosis of rolling element bearings10.1016/j.ymssp.2017.01.033 ↗
36. Compressed sensing based on dictionary learning for extracting impulse components10.1016/j.sigpro.2013.04.018 ↗
37. Case Western Reserve University (2019, January 15). Bearing Data Center Website. Available online: https://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website.
38. Rolling element bearing diagnostics using the case western reserve university data: A benchmark study10.1016/j.ymssp.2015.04.021 ↗