Independent component analysis (ICA) is one of the robust methods to extract the features. Many researchers have indicated a great potential for this approach to analyze the signals using ICA to detect the similarity or non-similarity between two signals. We have proposed a novel method which is extension of ICA to detect the faults associated with any machine by collecting vibration signals of machine. This paper presents the details of this method. The classification of the faults, if detected, is carried out using suitable classification technique.

1. M. F. Abdel-Magied, K. A. Loparo, Wei Lin, "Fault detection and diagnosis for rotating machinery: A model-based approach", Proceedings of the American Control Conference, pp. 3291-3296, June 1998.
2. Liu Tingting, Ren Xingmin "A Blind De-convolution Technique for Machine Fault Diagnosis" (ISBN 978-0-7695-3634-7/09), 2009 IEEE. Pp. 232 – 235.
3. Aapo Hyvärinen and Erkki Oja "Independent Component Analysis: Algorithms and Applications" Neural Networks Research Centre, Helsinki University of Technology, P. O. Box 5400, FIN-02015 HUT, Finland, Neural Networks, 13(4-5):411-430, 2000.
4. "Fast and Robust Fixed-Point Algorithms for Independent Component Analysis" Aapo Hyvarinen IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 10, NO. 3, MAY 1999.
5. Yu Zhu, Ruina Wu, Aiguo Li "The Recognition of Vibration Sensor's Signals Based on ICA", IEEE 2010.
6. "Research on Robust Kernel Independent Component analysis based on Kurtosis in Fault Detection" Zhao Jin et al. IEEE 2013.
7. "Sound and Vibration in Rolling Bearings" T. momono, B. noda, Basic Technology and Research Center, Japan.
8. "Evolving Artificial Neural Networks" Xin yao, IEEE 2000.
9. "Detecting Faulty Rolling Element Bearing" Bruel and Kjar, Denmark.
10. "Vibration Monitoring" D. Howieson, SKF Reliability Systems, San Diego, US.

Independent Component Analysis (ica) Fast Fourier Transform (fft) Classifier.