Fault detection based on robust independent component analysis and support vector machines

This study aims to develop an intelligent algorithm by integrating robust independent component analysis (RobustICA) and support vector machines (SVMs). According to different characteristics of source signals including real or complex, super-Gaussian or sub-Gaussian and pollution of signal noise, a new method for fault detection that uses RobustICA based on kurtosis is put forward in this paper. The basic idea of the approach is to use RobustICA optimized by iterative technique to separate independent components which drive a process after wavelet de-noising of the original data. On this basis, statistics are established for fault detection and the kernel density estimation is used in calculating the confidence limit of statistics. After that, support vector machines (SVMs) is utilized to classify the faults. The simulation results of signal experiment and TE model clearly show the effectiveness and advantages of the proposed method in comparison to FastICA method.

[1]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[2]  Richard D. Deveaux,et al.  Applied Smoothing Techniques for Data Analysis , 1999, Technometrics.

[3]  Pierre Comon,et al.  Robust Independent Component Analysis by Iterative Maximization of the Kurtosis Contrast With Algebraic Optimal Step Size , 2010, IEEE Transactions on Neural Networks.

[4]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[5]  Bo-Suk Yang,et al.  Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors , 2007, Expert Syst. Appl..

[6]  H. Krim,et al.  Robust independent component analysis , 2005, IEEE/SP 13th Workshop on Statistical Signal Processing, 2005.

[7]  Pierre Comon,et al.  ROBUST INDEPENDENT COMPONENT ANALYSIS , 2009 .

[8]  Vicente Zarzoso,et al.  Independent component analysis based on first-order statistics , 2012, Signal Process..

[9]  Aapo Hyvärinen,et al.  Survey on Independent Component Analysis , 1999 .

[10]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[11]  ChangKyoo Yoo,et al.  Statistical process monitoring with independent component analysis , 2004 .

[12]  Pierre Comon,et al.  Robust independent component analysis for blind source separation and extraction with application in electrocardiography , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Yingwei Zhang,et al.  Enhanced statistical analysis of nonlinear processes using KPCA, KICA and SVM , 2009 .

[14]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[15]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[16]  Manabu Kano,et al.  Monitoring independent components for fault detection , 2003 .