Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized Fisher’s criterion
- 594 Downloads
Condition monitoring of rotating machinery has attracted more and more attention in recent years in order to reduce the unnecessary breakdowns of components such as bearings and gears which suffer frequently from failures. Vibration based approaches are the most commonly used techniques to the condition monitoring tasks. In this paper, we propose a bearing fault detection scheme based on support vector machine as a classification method and binary particle swarm optimization algorithm (BPSO) based on maximal class separability as a feature selection method. In order to maximize the class separability, regularized Fisher’s criterion is used as a fitness function in the proposed BPSO algorithm. This approach was evaluated using vibration data of bearing in healthy and faulty conditions. The experimental results demonstrate the effectiveness of the proposed method.
KeywordsSupport vector machines (SVMs) Particle swarm optimization (PSO) Regularized linear discriminant analysis (RLDA) Features selection Condition monitoring
This work was completed in the laboratory of applied precision mechanics LAPM (University of Setif1, Algeria). The authors would like to thank the Algerian Ministry of Higher Education and Scientific Research (MESRS) and the Delegated Ministry for Scientific Research (MDRS) for granting financial support for CNEPRU Research Project No. J0301220120001. The authors would like to thank Professor K. A. Loparo of Case Western Reserve University for his kind permission to use their bearing data.
- Duda, R., Hart, P., & Stork, D. (2000). Pattern classification (2nd ed.). New York: Wiley.Google Scholar
- Kennedy, J., & Eberhart, R. C. (1995). Particle swarm optimization. In Proceedings of IEEE international conference on neural networks, Vol. 4, pp. 1942–1948.Google Scholar
- Kennedy.J, & Eberhart, R. C., (1997). A discrete binary version of the particle swarm optimisation algorithm. In Proceedings of the IEEE International Conference on Neural Networks (pp. 4104–4108). Australia: Perth.Google Scholar
- Kurek, J., & Osowski, S. (2010). Support vector machine for fault diagnosis of the broken rotor bars of squirrel-cage induction motor. Neural Computing & Application, 19, 557–564.Google Scholar
- Li, Y., Tong, Y., Bai, B., & Zhang, Y. (2007). An improved particle swarm optimization for SVM training. Proceedings of the third international conference on natural computation (pp. 611–615). Los Alamitos: IEEE Computer Society.Google Scholar
- Li, H., Lian, X., Guo, C., & Zhao, P. (2013a). Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination. Journal of Intelligent Manufacturing. doi: 10.1007/s10845-013-0772-8.
- Li, Z., Yan, X., Tian, Z., Yuan, C., Peng, Z., & Li, L. (2013b). Blind vibration component separation and nonlinear feature extraction applied to the nonstationary vibration signals for the gearbox multi-fault diagnosis. Measurement, 46, 259–271.Google Scholar
- Loparo, K. A. (2012). Bearings Vibration Data Sets, Case Western Reserve University: http://csegroups.case.edu/bearingdatacenter/home.
- Mallat, S. G. (2003). A wavelet tour of signal processing. The sparse way (3rd ed.). New York: Academic Press.Google Scholar
- Randall, R. B., Antoni, J., & Chobsaard, S. (2001). The relationship between spectral correlation and envelope analysis in the diagnosis of bearing faults and other cyclostationary machine signals. Mechanical Systems and Signal Processing, 15(945–962), 2001.Google Scholar
- Samanta, B., Al-Balushi, K. R., & Al-Araimi, S. A. (2001). Use of genetic algorithm and artificial neural network for gear condition diagnostics. Proceedings of COMADEM, (pp. 449–456). University of Manchester, UK.Google Scholar
- Scholkopf, B. (1998). SVMs-a practical consequence of learning theory. IEEE Intelligent Systems, 13, 18–19.Google Scholar
- Soong, T. T. (2004). Fundamentals of probability and statistics for engineers. New York: Wiley.Google Scholar
- Yang, Y., Yu, D., & Cheng, J. (2007). A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement, 40, 943–950.Google Scholar
- Ye, J., Janardan, R., Li, Q., & Park, H. (2004). Feature extraction via generalized uncorrelated linear discriminant analysis, In The Proceedings of the international conference on machine learning, pp. 895–902.Google Scholar
- Ye, J., & Xiong, T. (2006). Computational and theoretical analysis of null space and orthogonal linear discriminant analysis. Journal of Machine Learning Research, 7, 1183–1204.Google Scholar