Blind separation of rotating machine sources: bilinear forms and convolutive mixtures

Abstract We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi–Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.

[1]  Amir Leshem,et al.  Blind Separation Of Machine Vibration With Bilinear Forms , 2000 .

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

[3]  Arogyaswami Paulraj,et al.  An analytical constant modulus algorithm , 1996, IEEE Trans. Signal Process..

[4]  I. Epps.  An investigation into vibrations excited by discrete faults in rolling element bearings , 1991 .

[5]  Alexander Ypma,et al.  Learning methods for machine vibration analysis and health monitoring , 2001 .

[6]  William A. Kuperman,et al.  Matched Field Acoustics , 1997 .

[7]  Patrick J. Loughlin,et al.  COHEN–POSCH (POSITIVE) TIME–FREQUENCY DISTRIBUTIONS AND THEIR APPLICATION TO MACHINE VIBRATION ANALYSIS☆ , 1997 .

[8]  Amir Leshem.  Source separation using bilinear forms , 1999, Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics. SPW-HOS '99.

[9]  Czesław Cempel.  Vibroacoustic condition monitoring : Ellis Horwood, 212pp. (1991) , 1991 .

[10]  Moeness G. Amin,et al.  Blind source separation using time-frequency distributions: algorithm and asymptotic performance , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  J. M. Danthez,et al.  SEPARATION OF BROADBAND SOURCES PROCESSING CONCEPT OF THE LABRADOR SOFTWARE , 1997 .

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

[13]  Petteri Pajunen,et al.  Blind source separation using algorithmic information theory , 1998, Neurocomputing.

[14]  Robert J. Bernhard,et al.  A technique to determine the number of incoherent sources contributing to the response of a system , 1994 .

[15]  Jean-Franois Cardoso.  High-Order Contrasts for Independent Component Analysis , 1999, Neural Computation.

[16]  Lucas C. Parra,et al.  Convolutive blind separation of non-stationary sources , 2000, IEEE Trans. Speech Audio Process..

[17]  Cécile Capdessus,et al.  CYCLOSTATIONARY PROCESSES: APPLICATION IN GEAR FAULTS EARLY DIAGNOSIS , 2000 .

[18]  H. Saunders,et al.  Machinery Noise and Diagnostics , 1987 .

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

[20]  Guillaume Gellé.  Les statistiques d'ordre superieur appliquees a la detection et a la separation de sources utilisation en analyse vibratoire et acoustique , 1998 .

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

[22]  C. Serviere,et al.  Blind separation of noisy harmonic signals using only second order statistics , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[23]  C. Serviere,et al.  Blind source separation of convolutive mixtures , 1996, Proceedings of 8th Workshop on Statistical Signal and Array Processing.

[24]  A. V. D. Veen.  Algebraic methods for deterministic blind beamforming , 1998, Proc. IEEE.

[25]  William A. Gardner,et al.  Spectral self-coherence restoral: a new approach to blind adaptive signal extraction using antenna arrays , 1990, Proc. IEEE.

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

[27]  DelftThe Netherlandsypma,et al.  Rotating Machine Vibration Analysis with Second-order Independent Component Analysis , 1999 .

[28]  Jean-Louis Lacoume,et al.  Blind separation of wide-band sources: Application to rotating machine signals , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[29]  John S. Mitchell,et al.  An introduction to machinery analysis and monitoring , 1981 .