Fault Diagnosis of Rolling Bearing Based on the PSO-SVM of the Mixed-Feature

Abstract:

The rolling bearing is one of the most important and widely used parts in the rotating machinery. It is necessary to establish a reliable condition monitoring program which can avoid serious fault in the runtime and diagnose failure timely and accurately when it happens. This paper puts forward to a fault diagnosis method of rolling bearing based on the PSO-SVM of the mixed-feature. Firstly, we extract features in time domain, frequency domain, and order quenfrency domain. Secondly, select both Support Vector Machine (SVM) parameters by Particle Swarm Optimization (PSO) algorithm and kernel function of SVM classification model. Finally, classification model of SVM is designed by using the extracted salient features, kernel function and optimal parameter of PSO. The result verifies the effectiveness of the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 895-901
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.895
• Online since: August 2013
• Authors: Jun Ma, Jian De Wu, Yu Gang Fan, Xiao Dong Wang, Zong Kai Shao
• Keywords: Fault Diagnosis, Mixed-Feature Extraction, Particle Swarm Optimization (PSO), Rolling Bearing, Support Vector Machine (SVM)

References

[1] P.K. Kanlar, Satish C. Sharma and S.P. Harsha, Rolling Element Bearing Fault Diagnosis Using Wavelet Transform, , Neurocomputing, vol. 74, pp.638-1645, May (2011).

DOI: 10.1016/j.neucom.2011.01.021

[2] P. Tao, H.B. Yang, J.B. Li and H. Jiang , Mixed-domain feature extraction approach to rolling bearings faults based on kernel principle component analysis, Journal of Central South University(Science and Technology) , vol. 42，pp.3384-3391, November (2011).

[3] N.G. Nikolaou and I.A. Antoniadis, Rolling element fault diagnosis using wavelet packets, NDT&E International , vol. 38, pp.197-205, April (2002).

DOI: 10.1016/s0963-8695(01)00044-5

[4] Y. R Hwang, K. K Jen and Y. T Shen, Application of cepstrum and neural network to bearing fault detection, Journal of Mechanical Science and Technology, vol. 23, pp.2730-2737, October (2009).

DOI: 10.1007/s12206-009-0802-9

[5] P.K. Kankar, Satish C. Sharma, S.P. Harsha, Fault diagnosis of ball bearings using machine learing methods, Expert Systems with Applications, vol. 38, pp.1876-1886, March (2011).

DOI: 10.1016/j.eswa.2010.07.119

[6] Z.W. Liu, H.R. Cao and X.F. Chen, Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings, Neurocomputing, vol. 99, p.399–410, January (2012).

DOI: 10.1016/j.neucom.2012.07.019

[7] ZH. Chen, J.H. Zhu and Y. Ling, An improved PSO algorithm for structure damage identification, JOURNAL OF VIBRATION AND SHOCK, vol. 31, pp.17-20. May (2012).

[8] X.S. Wen, Pattern Recognition and Condition monitoring, Beijing: Science Press, pp.147-165, October, (2007).

[9] H. Li, H.Q. Zheng and L.W. Tang, Bearing Fault Diagnosis Based on Order Tracking and Teager-Huang Transform, Journal of Vibration, Measurement & Diagnosis, pp.138-142, April (2010).

[10] W.Y. Zhang and G. ZH. Liu, The Cepstrum Analysis of Rolling Bearing Fault, Journal of Vibration, Measurement & Diagnosis, pp.31-36, June, (2000).

[11] SH.F. Ai and H. Li, Application of order cepstrum and neural network to gear fault detection, "IMACS Multi conference on "Computational Engineering in Systems Applications, (CESA), Beijing, China, p.1822 –1827, October (2006).

DOI: 10.1109/cesa.2006.4281934

[12] LOPARO K A. Bearings vibration data set [EB/OL]. Case Western Reserve University. http/www. eecs. cwru. edu/laboratory/bearing/ download. htm.