Fault Diagnosis of Railway Axlebox Bearing Based on Wavelet Packet and Neural Network


Article Preview

A real time and effective axlebox bearing fault diagnostic method is significant in the condition-based maintenance. In the axlebox bearing fault diagnostic system, fault features extraction and fault patterns classification are two important aspects to identify whether a axlebox bearing is failure or not. This paper presents a method of axlebox bearing fault diagnosis based on wavelet packet decomposition and BP neural network. First decompose the vibration signal into a finite number of coefficients by wavelet packet decomposition. Then calculate energy moment of each coefficient and take the energy moment as an eigenvector to effectively express the failure feature. Finally BP neural network is used for fault classification. The experimental results show that combining wavelet packet decomposition with BP neural network could identify the axlebox bearing fault effectively. The average diagnosis accuracy rate is 96.67%.



Edited by:

Chunliang Zhang and Paul P. Lin




X. F. Li et al., "Fault Diagnosis of Railway Axlebox Bearing Based on Wavelet Packet and Neural Network", Applied Mechanics and Materials, Vols. 226-228, pp. 749-755, 2012

Online since:

November 2012




[1] K.C. Gryllias, I.A. Antoniadis: Engineering Applications of Artificial Intelligence, Vol. 25 (2012) No. 2, p.326.

[2] S. Abbasion, A. Rafsanjani, A. Farshidianfar and N. Irani: Mechanical Systems and Signal Processing, Vol. 21 (2007) No. 7, p.2933.

[3] Qiang Miao, Dong Wang and Michael Pecht: IEEE Conference on Prognostics and Health Management (Denver, U.S. A, June 20-23, 2011), p.1.

[4] FarshidTavakkoli, Mohammad Teshnehlab: International Conference on Intelligent and Advanced Systems (Kuala Lumpur Malaysia November 25-28, 2007), p.1210.

[5] Z.K. Peng, Peter W. Tse and F.L. Chu: Mechanical Systems and Signal Processing, Vol. 19(2005) No. 5, p.974.

[6] Wei Liao, Pu Han and Xu Liu: Third International Symposium on Intelligent Information Technology Application (Washington, USA 2009). Vol. 1, p.672.

[7] G.F. Bin, J.J. Gao, X.J. Li and B.S. Dhillon: Mechanical Systems and Signal Processing, Vol. 27 (2012), p.696.

[8] Zhengbo Qin: Rolling Bearing Fault Identification Method Based on Wavelet Package and Support Vector Machine (MS., Taiyuan University of Technology, China 2010), p.1. (In Chinese).

[9] Wenxing Ma: the 27th Chinese Control Conference (Kunming, China, July 16-18, 2008).

[10] Hao Chen, Yanying Liu and Yanjie Wang: IEEE International Symposium on Knowledge Acquisition and Modeling Workshop (Wuhan, China, December 21-22, 2008), p.462.

[11] Defeng Zhang: matlab Wavelet Analysis (China Machine Press, China 2010), p.158. (In Chinese).

[12] HuiGao: Goal Mine Machinery, Vol. 29 (2008) No. 11, p.198. (In Chinese).

[13] Shiqi Ding, LihuaGuo: RengongShenjingWangluoJichu (Harbin Engineering University Press, China 2008), p.54. (In Chinese).

[14] Jing Hu, Shunian Yang: Mechanical and Electronic, (2006) No. 4, p.9. (In Chinese).