Kernel Independent Component Analysis and its Application in Blind Separation of Mechanical Faults

Abstract:

A nonlinear blind separation method of mechanical fault sources is proposed. In the proposed method, the signal is transformed from the low-dimensional nonlinear original space into a high-dimensional linear feature space by the kernel function, so that nonlinear mixture mechanical fault sources can be separated by the linear ICA method in a new feature space. The simulation result shows that the proposed method is superior to the traditional ICA method in processing nonlinear blind separation problem. Finally the proposed method is applied to the nonlinear blind separation of bearing faults. The experiment result further verifies the validity of the proposed method.

• Periodical: Applied Mechanics and Materials (Volume 703)
• Pages: 394-399
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.703.394
• Online since: December 2014
• Authors: Meng Di Ye, Zhi Nong Li*, Yao Xian Xiao, Xu Ping He, Jing Wen Yan
• Keywords: Blind Source Separation (BSS), Fault Diagnosis, Kernel Independent Component Analysis, Nonlinear Mixture

References

[1] T. FAN, Z.N. Li, Y.X. XIAO, Blind separation of mechanical source signals based on the estimation of source numbers. Journal of Mechanical Strength, 2011, 33(1): 15-19(In Chinese).

[2] Y. Li, Y.Y. He, Z.N. Li, et al. Study on application of blind source separation and wavelet denoising in rubbing fault acoustic signal analysis. Journal of Mechanical Strength, 2005, 27 ( 6) : 719-724(In Chinese).

[3] Z.N. Li, J. Han, J.J. Sun, et al. Fault Recognition Method Based on Independent Component Analysis and Hidden Markov Model. Journal of Vibration and Control, 2007, 13(2): 125-137.

DOI: 10.1177/1077546307066964

[4] Z.N. Li, Y.D. Zeng, T. Fan, et al.  Source Separation method of Machine Faults Based on Post-Nonlinear Blind Source Separation. Proceedings of the 7th World Congress on Intelligent Control and Automation, June 25 - 27, 2008, Chongqing, China, pp.1786-1789.

DOI: 10.1109/wcica.2008.4594464

[5] A Table, C Jutten. Sources separation in Post-nonlinear mixtures. IEEE Trans. Signal processing, 1999, 47: 2807-2820.

DOI: 10.1109/78.790661

[6] H. Lappalainen, A. Honkela. Bayesian nonlinear independent component analysis by multi-layer perceptions. In advances in independent component analysis (M Girolami, ed), Berlin: Springer-Verlag, 2000: 93-121.

DOI: 10.1007/978-1-4471-0443-8_6

[7] Francis R. Bach, Michael I. Jordan, kernel independent component analysis. Journal of Machine Learning Research, 2002, Vol. 3: 1-48.

[8] Francis R Bach, Michael I Jordan. Kernel Independent Component Aanlysis. Journal of Machine Learing Research, 1998, 10(5): 1299- 1319.

[9] Francis R B, M ichael I J Kernel independent component analysis [J]. Journal of Machine Learning Research, 2002, 2(3): 1246-1248.

[10] A. Hyvärinen and E. A Oja. fast fixed-point algorithm for independent component analysis. Neural Computation, 1997, 9(7): 1483-1492.

DOI: 10.1162/neco.1997.9.7.1483

[11] A. Hyvärinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks 1999, 10(3): 626-634.

DOI: 10.1109/72.761722

[12] J -F. Cardoso and Souloumiac A. Blind beamforming for non-Gaussian signals. Radar and Signal Processing, IEE Proceedings F, 1993, 140(6): 362 -370.

DOI: 10.1049/ip-f-2.1993.0054

[13] A. J. Bell and T. J. Sejnowski, An information maximization approach to blind separation and blind deconvolution, Neural Computation, 1995, 7(6): 1129-1159.

DOI: 10.1162/neco.1995.7.6.1129

[14] J. F, Cardoso and B. Laheld, Equivariant adaptive source separation. IEEE Transaction on Signal Processing, 1996, 44(12): 3017-3029.

DOI: 10.1109/78.553476