The traditional orthogonal matching pursuit algorithm exploits only the overall sparsity of signals without considering the effects caused by structural characteristics. To this end, this paper proposes an enhanced Bayesian sparse representation (EBSR) of mechanical fault signals by structural feature-oriented matching redundant dictionary construction. First, an EBSR model which can improve sparse reconstruction results is proposed. The proposed model improves the recovery accuracy and robustness of the sparse representation by using the structural information as a priori information. Subsequently, a composite dictionary is designed combining a Sin-Chirplet dictionary with an Impulse dictionary, and a multi-group and multi-strategy grey wolf optimizer algorithm is employed to enable the composite dictionary match the structural features of the fault signal and reduce its redundancy degree. Finally, the optimized matching composite dictionary is introduced into the EBSR algorithm, endowing it with an efficient atom selection strategy and reducing the complexity of the sparse representation. The simulation and experimental results demonstrated that the proposed method can effectively reduce the interference from background noise and impurity frequencies, verifying the effectiveness and applicability of the proposed method for the sparse representation of mechanical faults.
HeGDingKLinH. Fault feature extraction of rolling element bearings using sparse representation. J Sound Vibr2016; 366: 514–527.
2.
LiuZTangXWangX, et al. Wind turbine blade bearing fault diagnosis under fluctuating speed operations via Bayesian augmented Lagrangian analysis. IEEE Trans Ind Inf2021; 17: 4613–4623.
3.
ZengXLuXLiuZ, et al. An adaptive fractional stochastic resonance method based on weighted correctional signal-to-noise ratio and its application in fault feature enhancement of wind turbine. ISA Trans2022; 120: 18–32.
4.
XuYZhangKMaC, et al. Adaptive Kurtogram and its applications in rolling bearing fault diagnosis. Mech Syst Signal Process2019; 130: 87–107.
5.
YuanJJiangHZhaoQ, et al. Dual-mode noise-reconstructed EMD for weak feature extraction and fault diagnosis of rotating machinery. IEEE Access2019; 7: 173541–173548.
6.
WangLLiuZMiaoQ, et al. Time-frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis. Mech Syst Signal Process2018; 103: 60–75.
7.
YuanJWangYPengY, et al. Weak fault detection and health degradation monitoring using customized standard multiwavelets. Mech Syst Signal Process2017; 94: 384–399.
8.
YanW-JYangLYangX, et al. Statistical modeling for fast Fourier transform coefficients of operational vibration measurements with non-Gaussianity using complex-valued t distribution. Mech Syst Signal Process2019; 132: 293–314.
9.
TaoHWangPChenY, et al. An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks. J Franklin Inst2020; 357: 7286–7307.
10.
TaoXRenCWuY, et al. Bearings fault detection using wavelet transform and generalized Gaussian density modeling. Measurement2020; 155: 107557.
11.
AminVSZhangYDHimedB. Sparsity-based time-frequency representation of FM signals with burst missing samples. Signal Process2019; 155: 25–43.
12.
MallatSGZhangZ. Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process1993; 41: 3397–3415.
13.
ChenZHuangCLinS. A new sparse representation framework for compressed sensing MRI. Knowledge-Based Syst2020; 188: 104969.
14.
TroppJAGilbertAC. Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inf Theory2007; 53: 4655–4666.
15.
WuRHuangWChenD. The exact support recovery of sparse signals with noise via orthogonal matching pursuit. IEEE Signal Process Lett2013; 20: 403–406.
16.
DonohoDLTsaigYDroriI, et al. Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit. IEEE Trans Inf Theory2012; 58: 1094–1121.
17.
ZayyaniHBabaie-ZadehMJuttenC. Bayesian pursuit algorithm for sparse representation. In: 2009 ieee international conference on acoustics, speech and signal processing, Taipei, Taiwan, 2009, pp. 1549–1552.
18.
SchniterPPotterLCZinielJ. Fast Bayesian matching pursuit. In: 2008 IEEE information theory and applications workshop, 2008, San Diego, CA, USA pp. 326–333.
19.
C.HerzetA.DrémeauBayesian pursuit algorithms. In: 2010 18th European signal processing conference, Aalborg, Denmark, 2010, pp. 1474–1478.
20.
WangSHuangWZhuZK. Transient modeling and parameter identification based on wavelet and correlation filtering for rotating machine fault diagnosis. Mech Syst Signal Process2011; 25: 1299–1320.
21.
DingYHeWChenB, et al. Detection of faults in rotating machinery using periodic time-frequency sparsity. J. Sound Vibr2016; 382: 357–378.
22.
FanWCaiGZhuZK, et al. Sparse representation of transients in wavelet basis and its application in gearbox fault feature extraction. Mech Syst Signal Process2015; 56–57: 230–245.
23.
HeZFeiXMengQ. Signal decomposition with matching pursuits and technology of extracting machinery fault feature based on impulse time-frequency atom. J Vib Shock2003; 2: 28–31. DOI: 10.13465/j.cnki.jvs. 2003.02.008.
24.
PiW. Fuqiang, Generalized demodulation method based on multi-scale chirplet and sparse signal decomposition and its application to gear fault diagnosis. J Mech Eng2010; 46: 59–64. DOI:10.3901/jme.2010.15.059.
25.
CuiLWangJLeeS. Matching pursuit of an adaptive impulse dictionary for bearing fault diagnosis. J. Sound Vibr2014; 333: 2840–2862.
26.
DuZChenXZhangH, et al. Sparse feature identification based on union of redundant dictionary for wind turbine gearbox fault diagnosis. IEEE Trans Ind Electron2015; 62: 6594–6605.
27.
DebKPratapAAgarwalS, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput2002; 6: 182–197.
28.
KennedyJEberhartR. Particle swarm optimization. In: Proceedings of ICNN’95 – international conference on neural networks, Perth, WA, Australia, 1995, pp. 1942–1948.
29.
MirjaliliSMirjaliliSMLewisA. Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
30.
TuQChenXLiuX. Multi-strategy ensemble grey wolf optimizer and its application to feature selection. Appl Soft Comput2019; 76: 16–30.
31.
PatiYCRezaiifarRKrishnaprasadPS. Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. In: Proceedings of 27th Asilomar conference on signals, systems and computers, Pacific Grove, CA, USA, 1993, pp. 40–44.
32.
HerzetCDrémeauA. Bayesian pursuit algorithms. In: European signal processing conference, Aalborg, Danemark, 2010, pp. 1474–1478.
33.
DrémeauAHerzetCDaudetL. Structured Bayesian orthogonal matching pursuit. In: ICASSP, IEEE international conference on acoustics, speech and signal processing – proceedings, Kyoto, Japan, 2012, pp. 3625–3628.
34.
BultanA. A four-parameter atomic decomposition of chirplets. IEEE Trans Signal Process1999; 47: 731–745.
35.
ZhuHZhangSNZhaoHC. Single-channel source separation of radar fuze mixed signal using advanced adaptive decomposition. Wuli Xuebao/Acta Phys Sin2014; 63: 058401.
36.
WangXZhouYTianY, et al. Sparse Decomposition for frequency modulation radar signal based on advanced genetic algorithm and Sin-Chirplet atom. Shanghai Jiaotong Daxue Xuebao/J Shanghai Jiaotong Univ2017; 51: 1124–1130.
37.
BlumensathTDaviesME. Sampling theorems for signals from the union of finite-dimensional linear subspaces. IEEE Trans Inf Theory2009; 55: 1872–1882.
38.
ZhaoMJiaX. A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery. Mech Syst Signal Process2017; 94: 129–147.
39.
CaiGChenXHeZ. Sparsity-enabled signal decomposition using tunable Q-factor wavelet transform for fault feature extraction of gearbox. Mech Syst Signal Process2013; 41: 34–53.
40.
AntoniJ. The spectral kurtosis: a useful tool for characterising non-stationary signals. Mech Syst Signal Process2006; 20: 282–307.
