Application of Blind Source Separation in Ultrasonic NDE

Blind source separation (BSS) allows the recovery of unknown signals from observed signals mixed by an unknown propagation medium, and is a promising technique for signal processing and data analysis. In ultrasonic nondestructive evaluation (NDE), BSS can serve at least three purposes: defect classification, system modeling and noise reduction. This paper discusses the application of BSS in ultrasonic NDE, and explores the implementation of independent component analysis (ICA) in separation of ultrasonic signals. Simulation results were given, which showed that different source signals can be separated using ICA, and the conclusion is that BSS can play a very important role in ultrasonic NDE.

[1]  G. Delaunay,et al.  BLIND SOURCES SEPARATION APPLIED TO ROTATING MACHINES MONITORING BY ACOUSTICAL AND VIBRATIONS ANALYSIS , 2000 .

[2]  JOURNAL OF SOUND AND VIBRATION , 1998 .

[3]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[4]  Stefan Schaal,et al.  Graph matching vs mutual information maximization for object detection , 2001, Neural Networks.

[5]  Jin,et al.  The Research of Blind Source Separation (BSS)in Machinery Fault Diagnosis , 2001 .

[6]  Y. Sato,et al.  A Method of Self-Recovering Equalization for Multilevel Amplitude-Modulation Systems , 1975, IEEE Trans. Commun..

[7]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[8]  Dong-Jo Park,et al.  Blind separation of sources using higher-order cumulants , 1999, Signal Process..

[9]  Joseph Mathew,et al.  A COMPARISON OF AUTOREGRESSIVE MODELING TECHNIQUES FOR FAULT DIAGNOSIS OF ROLLING ELEMENT BEARINGS , 1996 .

[10]  P. Comon,et al.  Contrasts for multichannel blind deconvolution , 1996, IEEE Signal Processing Letters.

[11]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[12]  Jean-François Cardoso,et al.  Equivariant adaptive source separation , 1996, IEEE Trans. Signal Process..

[13]  Ahmed Yamani,et al.  A novel defect identification scheme in ultrasonic nondestructive evaluation , 1997 .

[14]  Joseph Mathew,et al.  Multiple Band-Pass Autoregressive Demodulation for Rolling-Element Bearing Fault Diagnosis , 2001 .

[15]  Christian Jutten,et al.  Blind source separation for convolutive mixtures , 1995, Signal Process..

[16]  Tian-Tai Guo,et al.  Introduction of BSS into VR-based test and simulation-with application in NDE , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[17]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[18]  ScienceDirect.  Mechanical systems and signal processing , 1987 .

[19]  Michael J. Roan,et al.  A NEW, NON-LINEAR, ADAPTIVE, BLIND SOURCE SEPARATION APPROACH TO GEAR TOOTH FAILURE DETECTION AND ANALYSIS , 2002 .

[20]  E. Oja,et al.  Independent Component Analysis , 2001 .

[21]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[22]  Dirk Van Compernolle,et al.  Signal separation by symmetric adaptive decorrelation: stability, convergence, and uniqueness , 1995, IEEE Trans. Signal Process..

[23]  Esfandiar Sorouchyari,et al.  Blind separation of sources, part III: Stability analysis , 1991, Signal Process..

[24]  B D.C.,et al.  A COMPARISON OF AUTOREGRESSIVE MODELING TECHNIQUES FOR FAULT DIAGNOSIS OF ROLLING ELEMENT BEARINGS , 1996 .

[25]  Guillaume Gelle,et al.  BLIND SOURCE SEPARATION: A TOOL FOR ROTATING MACHINE MONITORING BY VIBRATIONS ANALYSIS? , 2001 .

[26]  Pierre Comon,et al.  Separation Of Sources Using Higher-Order Cumulants , 1989, Optics & Photonics.

[27]  Robert P. W. Duin,et al.  Blind separation of rotating machine sources: bilinear forms and convolutive mixtures , 2002, Neurocomputing.