The rolling element bearing is among the most frequently encountered component in a rotating machine. Bearing fault can cause machinery breakdown and lead to productivity loss. A bearing fault diagnosis method has been proposed based on multi-scale permutation entropy (MPE) and adaptive neuro fuzzy classifier (ANFC). In this paper, MPE is applied for feature extraction to reduce the complexity of the feature vector. Extracted features are given input to the ANFC for an automated fault diagnosis procedure. Vibration signals are captured for healthy and faulty bearings. Experiment results pointed out that proposed method is a reliable approach for automated fault diagnosis. Thus, this approach has potential in diagnosis of incipient bearing faults.
Aziz W and Arif M (2005) Multiscale permutation entropy of physiological time series. In Proceedings of 9th IEEE International Multitopic Conference, Karachi, Pakistan, Dec. 24–25.
2.
BanditCPompeB (2002) Permutation entropy: A natural complexity measure for time series. Physical Review Letters88: 174102–1–174102–4.
3.
BruzzoAAGesierichBSantiMTassinariCABirnaumerNRubboliG (2008) Permutation entropy to detect vigilance changes and preictal state from scalp EEG in epileptic patients: A preliminary study. Neurological Science29: 3–9.
4.
CetisliB (2010) Development of adaptive neuro-fuzzy classifier using linguistic hedges: Part 1. Expert Systems with Applications37: 6093–6101.
5.
CostaMGoldbergerALPengCK (2002) Multiscale entropy analysis of complex physiological time series. Physical Review Letters89: 068102–1–068102–4.
El-MezyaniTWilsonRSattlerMSrivastavaSKEdringtonCSCartesDA (2012) Quantification of complexity of power electronics based system. IET Electrical Systems in Transportation2(4): 211–222.
8.
KankarPKSharmaSCHarshaSP (2011a) Fault diagnosis of ball bearing using machine learning methods. Expert Systems with Applications38(3): 1876–1886.
9.
KankarPKSharmaSCHarshaSP (2011b) Rolling element bearing fault diagnosis using autocorrelation and continuous wavelet transform. Journal of Vibration and Control17(14): 2081–2094.
10.
Kankar PK, Sharma SC and Harsha SP (2012a) Vibration signature analysis of a high speed rotor supported on ball bearings due to localized defects. Journal of Vibration and Controlhttps://dx-doi-org.web.bisu.edu.cn/10.1177/1077546312448506.
11.
KankarPKSharmaSCHarshaSP (2012b) Vibration–based fault diagnosis of a rotor bearing system using artificial neural network and support vector machine. International Journal of Modelling, Identification and Control15(3): 185–198.
12.
KankarPKSharmaSCHarshaSP (2013) Fault diagnosis of rolling element bearing using cyclic autocorrelation and wavelet transform. Neurocomputing110: 9–17.
13.
LiXOuyangGLiangZ (2008) Complexity measure of motor current signals for tool flute breakage detection in end milling. International Journal of Machine Tools and Manufacture48: 371–379.
MollerMF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks6(4): 525–533.
16.
RichmanJSMoormanJR (2000) Physiological time series analysis using approximate entropy and sample entropy. American Journal of Physiology - Heart and Circulatory Physiology278(6): H2039–H2049.
17.
SamantaBAl-BalushiKR (2003) Artificial neural networks based fault diagnostics of rolling element bearing using time domain features. Mechanical System and Signal Processing17: 317–328.
18.
VyasNSKumarSD (2001) Artificial neural network design for fault identification in a rotor bearing system. Mechanism and Machine Theory36: 157–175.
19.
WuSDWuPHWuCWDingJJWangCC (2012) Bearing fault diagnosis based on multiscale entropy and support vector machine. Entropy14: 1343–1356.
20.
YangJYZhangYYZhuYS (2007a) Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension. Mechanical System and Signal Processing21(5): 2012–2024.
21.
YangYDejieYChangJ (2007b) Fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement40: 943–950.
22.
ZhangLXiongGLiuHZouHGuoW (2010) Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference. Expert Systems with Applications37: 6077–6085.
