Independent component analysis (ICA) is a powerful tool for analyzing non-Gaussian data. Through the use of ICA, invariable features embedded in multi-channel vibration measurements made in different operating modes can be extracted. The hidden Markov model (HMM) is a statistical model of the time series, and has a strong capability in pattern classification, especially for signals with abundant information quantity, non-stationary natures and poor repeatability and reproducibility. A new approach to fault recognition is proposed in this article, in which ICA is used for feature extraction, and the HMM as a classifier. Fault recognition in the speed-up and speed-down processes of rotating machinery has been successfully completed. The proposed approach is compared with another recognition approach, in which principal component analysis (PCA) is used for feature extraction, and HMM as a classifier, and is shown to be very effective.
Cardoso, J.F. and Souloumiac, A., 1993, Blind beamforming for non-Gaussian signals, IEE Proceedings F140(6), 362–370.
2.
Ding, Q.Q., Feng, C.J., Li, Z.N., and Wu, Z.T., 2003, “Study on DHMM fault diagnostic methods for rotating machinery during run-up,”Journal of Vibration Engineering16(1), 41–45.
3.
Dong, H.M., Jun, G., Hu, L.M., and Dong, W.W., 2003, “Research on the shape feature extraction and recognition based on principal component analysis,”Journal of Hefei University of Technology26(2), 176–179, in Chinese.
4.
Feng, C.J., 2002, “HMM dynamical pattern recognition theories, methods and applications in fault diagnosis of rotating machinery,” Ph.D. Thesis, Zhejiang University, China, in Chinese.
5.
Feng, C.J., Ding, Q.Q., Wu, Z.T., and Li, Z.N., 2002, “Study on hidden Markov models for faults diagnosis of rotor machine in the whole run-up process,”Journal of Zhejiang University (Engineering Science)36(6), 642–645, in Chinese.
6.
Guedalia, I.D., London, M., and Werman, M., 1999, “An on-line agglomerative clustering method for non-stationary data,”Neural Computation11(2), 521–540.
7.
He, S.B., Ding, Q.Q., Li, Z.N., and Wu, Z.T., 2003, “Study on fault diagnosis methods of rotating machines based on wavelet transform-hidden Markov models,”Journal of Mechanical Strength25(5), 473–476.
8.
Hyvärinen, A., 1999, “Survey on independent component analysis,”Neural Computing Surveys2, 94–128.
9.
Hyvärinen, A., Hoyer, P.O., and Hurri, J., 2003, “Extensions of ICA as models of natural images and visual processing,” in Proceedings of the International Symposium on Independent Component Analysis and Blind Source Separation (ICA2003), (keynote talk), Nara, Japan, pp.963–974.
10.
Jiao, W.D., 2003, “Research on methods for fault diagnosis of rotating machinery based on independent component analysis,” Ph.D. Thesis, Zhejiang University, China, in Chinese.
11.
Jiao, W.D., Yang, S.X., and Wu, Z.T., 2003, “Extracting invariable fault features of rotating machines with multi-ICA networks,”Journal of Zhejiang University Science4(5), 595–601.
12.
Jiao, W.D., Yang, S.X., and Wu, Z.T., 2003, “Combination of ICA and SVM for mechanical pattern classification,”China Mechanical Engineering15(1), 62–65.
13.
Jiao, W.D. and Yang, S.X., 2003, “ICA based neural networks for pattern recognition of mechanical faults,”Computing Technology and Automation22(2), 63–67.
14.
Kim, K., 2001, “Face recognition using principal component analysis,”http://www.umiacs.umd.edu/~kim/SoftwareDevelopment-KimUMD.htm%23FaceRecog.
15.
Kotani, M., Shirata, Y., Maekawa, S., Ozawa, S., and Akazawa, K., 1999, “Application of independent component analysis to feature extraction of speech,” in Proceedings of the International Joint Conference on Neural Networks, Washington DC, USA, 10–16 July, Vol. 5, pp. 2981–2984.
16.
Lawrence, R., 1989, “A tutorial on hidden Markov models and selected applications in speech recognition,”Proceedings of the IEEE77(2), 257–285.
17.
Lee, J.-H., Jung, H.-Y., Lee, T.-W., and Lee, S.-Y., 2000, “Speech feature extraction using independent component analysis,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing 2000 (ICASSP'00), Istanbul, Turkey, 5–9 June, Vol.3, pp.1631–1634.
18.
Li, L. and Qu, L.S., 2003, “Independent component analysis for feature extraction of machine condition,”Journal of Xi'an Jiaotong University37(1), 44–47, in Chinese.
19.
Moddemeijer, R., 1989, “On estimation of entropy and mutual information of continuous distributions,”Signal Processing16(3), 233–246.
20.
Olshausen, B.A. and Field, D.J., 1996, “Emergence of simple-cell receptive field properties by learning a sparse code for natural image,”Nature381, 607–609.
Xie, J.H., 1995, “Hidden Markov model (HMM) and its application in the speech signal processing,”Huazhong University of Science and Technology, pp.3–25, 1995, Wuhan, Hubei, P.R.China, in Chinese.
23.
Ypma, A., 2001, “Learning methods for machine vibration analysis and health monitoring,” Ph.D. Dissertation, ISBN 90-9015310-1, Pattern Recognition Group, Department of Applied Physics, Delft University of Technology, The Netherlands.
24.
Ypma, A., Tax, D.M.J., and Duin, R.P.W., 1999, “Robust machine fault detection with independent component analysis and support vector data description,” in Proceedings of IEEE International Workshop on Neural Networks for Signal Processing 1999, Madison, Wisconsin (USA), 23–25 August, pp.67–76.
25.
Zhang, Y.N., Zhao, R.C., and Liang, Y., 2002, “An efficient target recognition method for large scale data,”ACTA Electronic Sinica30(10),1–3.
