Application of Wavelet Packet Transform for Detection of Ball Bearing Race Fault

Abstract:

In this study, a fault diagnosis system is proposed for rolling ball bearing race using wavelet packet transform(WPT) and artificial neural network(ANN)technique. Vibration signal from ball bearings having defects on inner race and outer race is considered and the extraction method of feature vector based on wavelet packet transform with frequency band energy is used. The vibration signal is decomposed into the individual frequency bands. The variations of the signal energy in these bands reflect the different fault locations. Further, the artificial neural network is proposed to develop the diagnostic rules of the data base in the present fault identification system. The experimental work is performed to evaluate the effect of fault diagnosis in a rolling ball bearing platform under different fault conditions. The experimental results indicate the effectiveness of the proposed method in fault bearing identification.

• Periodical: Materials Science Forum (Volumes 626-627)
• Pages: 511-516
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.626-627.511
• Online since: August 2009
• Authors: Dong Yun Wang, Wen Zhi Zhang, Wei Ping Lu, J.W. Du
• Keywords: Frequency Band Energy, Neural Network (NN), Vibration Signal, Wavelet Packet Transform

References

[1] N. Tandon and A. Choudhury. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribology International Vol. 32(8) (1999), pp.469-480.

DOI: 10.1016/s0301-679x(99)00077-8

[2] D.W. Jian and C.H. Liu. An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Systems with Applications Vol. 36(3) (2009), pp.4278-4286.

DOI: 10.1016/j.eswa.2008.03.008

[3] X.H. Wang, C.M. Zhu, H.L. Mao and Z.F. Huang. Wavelet packet analysis for the propagation of acoustic emission signals across turbine runners. NDT and E International Vol. 42(1) (2009), pp.42-46.

DOI: 10.1016/j.ndteint.2008.07.005

[4] G. G. Yen. Wavelet packet feature extraction for vibration monitoring. IEEE Transactions on Industrial Electronics Vol. 47(3) (2000), pp.650-667.

DOI: 10.1109/41.847906

[5] X. Hu, Z.Z. Wang and X. Ren. Classification of surface EMG signal using relative wavelet packet energy. Computer Methods and Programs in Biomedicine Vol. 79(3) (2005), pp.189-195.

DOI: 10.1016/j.cmpb.2005.04.001

[6] S. Choi. Detection of valvular heart disorders using wavelet packet decomposition and support vector machine. Expert Systems with Applications, Vol. 35(4)(2008), pp.1679-1687.

DOI: 10.1016/j.eswa.2007.08.078

[7] Y.H. Feng, Schlindwein and S. Fernando. Normalized wavelet packets quantifiers for condition monitoring. Mechanical Systems and Signal Processing Vol. 23(3)(2009), pp.712-723.

DOI: 10.1016/j.ymssp.2008.07.002

[8] W.K. Wong, C.W.M. Yuen, D.D. Fan, L.K. Chan and E.H.K. Fung. Stitching defect detection and classification using wavelet transform and BP neural network. Expert Systems with Applications Vol. 36(2)(2009), pp.3845-3856.

DOI: 10.1016/j.eswa.2008.02.066

[9] J.D. Wu and J.J. Chan. Faulted gear identification of a rotating machinery based on wavelet transform and artificial neural network. Expert Systems with Applications Vol. 36(5) (2009), pp.8862-8875.

DOI: 10.1016/j.eswa.2008.11.020

[10] J.D. Wu and S.H. Ye. Driver identification based on voice signal using continuous wavelet transform and artificial neural network techniques. Expert Systems with Applications Vol. 36(2) (2009), pp.1061-1069.

DOI: 10.1016/j.eswa.2007.11.003