It is important to diagnose the bearing fault to prevent the serious accident of equipment. This paper introduces a bearing fault identification scheme based on envelope power spectrum analysis, linear discriminate analysis and continuous hidden Markov model. First the envelope power spectrum features are extracted from amplitude demodulated vibration signals from fault bearings. Then, linear discriminate analysis is employed to reduce the feature dimensions, which are helpful for improving the computing speed and diagnosing accuracy. At last, the new linear discriminate analysis features are input into continuous hidden Markov model to train the models under different conditions, respectively. In bearing fault identification, test data are input into the pretrained continuous hidden Markov models, and the bearing state can be detected by the output of continuous hidden Markov model. To validate the effectiveness of the proposed method, experimental samples of four bearing conditions at different fault sizes and loads are utilized to test the continuous hidden Markov model and back-propagation neural network. The result shows that continuous hidden Markov model and linear discriminate analysis-based method have higher accuracy and efficiency than back-propagation neural network.
GeMDuRZhangG. Fault diagnosis using support vector machine with an application in sheet metal stamping operations. Mech Syst Signal Process2004; 18: 143–159.
2.
LouXLoparoKA. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech Syst Signal Process2004; 18: 1077–1095.
3.
LeiYHeZZiY. Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs. Mech Syst Signal Process2007; 21: 2280–2294.
4.
CongFChenJDongG. Short-time matrix series based singular value decomposition for rolling bearing fault diagnosis. Mech Syst Signal Process2013; 34: 218–230.
5.
WilliamPEHoffmanMW. Identification of bearing faults using time domain zero-crossings. Mech Syst Signal Process2011; 25: 3078–3088.
6.
ZhouRBaoWLiN. Mechanical equipment fault diagnosis based on redundant second generation wavelet packet transform. Digital Signal Process2010; 20: 276–288.
7.
YuJ. Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models. Mech Syst Signal Process2011; 25: 2573–2588.
8.
ImmovilliFCocconcelliMBelliniA. Detection of generalized-roughness bearing fault by spectral-kurtosis energy of vibration or current signals. IEEE Trans Ind Electron2009; 56: 4710–4717.
9.
PanYChenJLiX. Spectral entropy—a complementary index for rolling element bearing performance degradation assessment. J Mech Eng Syst2009; 223: 1223–1231.
10.
SunWChenJLiJ. Decision tree and PCA-based fault diagnosis of rotating machinery. Mech Syst Signal Process2007; 21: 1300–1317.
11.
Rafiee J, Rafiee M and Tse P. Application of mother wavelet functions for automatic gear and bearing fault diagnosis. Expert Syst Appl 2010; 37(6): 4568–4579.
12.
PanYChenJLiX. Bearing performance degradation assessment based on lifting wavelet packet decomposition and fuzzy c-means. Mech Syst Signal Process2010; 24: 559–566.
13.
CongFChenJPanY. Kolmogorov-Smirnov test for rolling bearing performance degradation assessment and prognosis. J Vib Control2011; 17: 1337–1347.
14.
OcakHLoparoKA. Estimation of the running speed and bearing defect frequencies of an induction motor from vibration data. Mech Syst Signal Process2004; 18: 515–533.
15.
MingYChenJDongG. Weak fault feature extraction of rolling bearing based on cyclic Wiener filter and envelope spectrum. Mech Syst Signal Process2011; 25: 1773–1785.
16.
FeldmanM. Hilbert transform in vibration analysis. Mech Syst Signal Process2011; 25: 735–802.
17.
JiangQJiaMHuJ. Machinery fault diagnosis using supervised manifold learning. Mech Syst Signal Process2009; 23: 2301–2311.
18.
LopezISarigul-KlijnN. Distance similarity matrix using ensemble of dimensional data reduction techniques: vibration and aerocoustic case studies. Mech Syst Signal Process2009; 23: 2287–2300.
19.
LiuHLiuCHuangY. Adaptive feature extraction using sparse coding for machinery fault diagnosis. Mech Syst Signal Process2011; 25: 558–574.
LiBZhangY. Supervised locally linear embedding projection (SLLEP) for machinery fault diagnosis. Mech Syst Signal Process2011; 25: 3125–3134.
22.
BellinoAFasanaAGaribaldiL. PCA-based detection of damage in time-varying systems. Mech Syst Signal Process2010; 24: 2250–2260.
23.
MartinezAMKakAC. PCA versus LDA. IEEE Trans Pattern Anal Mach Intell2001; 23: 228–233.
24.
TangEKSuganthanPNYaoX. Linear dimensionality reduction using relevance weighted LDA. Pattern Recognit2005; 38: 485–493.
25.
PatelSAKamraniAK. Intelligent decision support system for diagnosis and maintenance of automated systems. Comput Ind Eng1996; 30: 297–319.
26.
SamantaBAl-BalushiKRAl-AraimiSA. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Eng Appl Artif Intell2003; 16: 657–665.
27.
SakthivelNRSugumaranVBabudevasenapatiS. Vibration based fault diagnosis of monoblock centrifugal pump using decision tree. Expert Syst Appl2010; 37: 4040–4049.
28.
WidodoAYangB-S. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process2007; 21: 2560–2574.
29.
RabinerLR. A Tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE1989; 77: 257–286.
30.
FlynnRJonesE. Robust distributed speech recognition in noise and packet loss conditions. Digital Signal Process2010; 20: 1559–1571.
31.
BoutrosTLiangM. Detection and diagnosis of bearing and cutting tool faults using hidden Markov models. Mech Syst Signal Process2011; 25: 2102–2124.
32.
MiaoQMakisV. Condition monitoring and classification of rotating machinery using wavelets and hidden Markov models. Mech Syst Signal Process2007; 21: 840–855.
33.
CongFChenJDongG. Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis. J Sound Vib2013; 332: 2081–2097.
34.
McFaddenPDSmithJD. Vibration monitoring of rolling element bearings by the high-frequency resonance technique — a review. Tribol Int1984; 17: 3–10.
35.
YuDChengJYangY. Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings. Mech Syst Signal Process2005; 19: 259–270.
36.
LiuY. Fault diagnosis based on SWPT and Hilbert transform. Procedia Eng2011; 15: 3881–3885.
37.
KimHDrakeBLParkH. Multiclass classifiers based on dimension reduction with generalized LDA. Pattern Recognit2007; 40: 2939–2945.
38.
ZhuKWongYSHongGS. Multi-category micro-milling tool wear monitoring with continuous hidden Markov models. Mech Syst Signal Process2009; 23: 547–560.
39.
LeeJMKimSJHwangY. Diagnosis of mechanical fault signals using continuous hidden Markov model. J Sound Vib2004; 276: 1065–1080.
40.
JardineAKSLinDBanjevicD. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process2006; 20: 1483–1510.
41.
Nam K and Lee S. Diagnosis of rotating machines by utilizing a backpropagation neural network. In: Proceedings of the 1992 International Conference of the IEEE Industrial Electronics Society, San Diego, USA, 1992, pp.1064–1067.
42.
ZouJChenJPuY. Application of wavelet time-frequency analysis to identification of cracked rotor. Chinese J Mech Eng (English Ed)2003; 16: 50–53.
43.
van der Maaten LJP, Postma EO and van den Herik HJ. Dimensionality reduction: a comparative review. Tilburg University Technical Report, TiCC-TR 2009-005. Tilburg Centre for Creative Computing, Tilburg University, 2009.
