HOS-based nonparametric and parametric methodologies for machine fault detection

A framework for the detection and identification of machine faults through vibration measurements and higher order statistics (HOS) analysis is presented. As traditional signal processing techniques are based on the nonparametric magnitude analysis of vibration signals, in this paper, two different state-of-the-art HOS-based methods, namely, a nonparametric phase-analysis approach and a parametric linear or nonlinear modeling approach are used for machine fault diagnostic analysis. The focus of this paper is on the application of the techniques, not on the underlying theories. Each technique is described briefly and is accompanied by an experimental discussion on how it can be applied to classify the synthetic mechanical and electrical faults of induction machines compared with their normality. Promising results were obtained which show that the presented methodologies are possible approaches to perform effective preventive maintenance in rotating machinery.

[1]  Paul R. White,et al.  The interpretation of the bispectra of vibration signals—: I. Theory , 1995 .

[2]  Tommy W. S. Chow,et al.  Semiblind identification of nonminimum-phase ARMA models via order recursion with higher order cumulants , 1998, IEEE Trans. Ind. Electron..

[3]  J. Juang.  Applied system identification , 1994 .

[4]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems: theory and application , 1989 .

[5]  Asoke K. Nandi,et al.  Neural network autoregressive modeling of vibrations for condition monitoring of rotating shafts , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[6]  Tommy W. S. Chow,et al.  Blind identification of quadratic nonlinear models using neural networks with higher order cumulants , 2000, IEEE Trans. Ind. Electron..

[7]  Karim Abed-Meraim,et al.  Blind system identification , 1997, Proc. IEEE.

[8]  Chris F. Beards,et al.  Engineering Vibration Analysis with Application to Control Systems , 1995 .

[9]  J. Penman,et al.  Induction machine condition monitoring with higher order spectra. II. Variable frequency operation and automated diagnosis , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).

[10]  Kenneth J. Hunt,et al.  Neural Adaptive Control Technology , 1996 .

[11]  Han-Fu Chen,et al.  Identification and Stochastic Adaptive Control , 1991 .

[12]  Anuradha M. Annaswamy,et al.  Adaptive control of nonlinear dynamic systems using θ-adaptive neural networks , 1997, Autom..

[13]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[14]  J. Penman,et al.  Induction machine condition monitoring with higher order spectra. I. Fundamentals and fixed frequency operation , 1998, IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200).

[15]  Rolf Isermann,et al.  Trends in the Application of Model Based Fault Detection and Diagnosis of Technical Processes , 1996 .

[16]  Tommy W. S. Chow,et al.  Extended least squares based algorithm for training feedforward networks , 1997, IEEE Trans. Neural Networks.

[17]  Melvin J. Hinich,et al.  Monitoring Rotating Tool Wear Using Higher-Order Spectral Features , 1993 .

[18]  Ananthram Swami,et al.  Bibliography on higher-order statistics , 1997, Signal Process..

[19]  J. Penman,et al.  Condition monitoring of electrical drives , 1986 .

[20]  J. L. Maryak,et al.  Automated system monitoring and diagnosis via singular value decomposition , 1997, Autom..

[21]  Steffen Leonhardt,et al.  Methods of fault diagnosis , 1997 .

[22]  J. Penman,et al.  Supply invariant induction machine condition monitoring , 1997 .

[23]  Robert E. Uhrig,et al.  Monitoring and diagnosis of rolling element bearings using artificial neural networks , 1993, IEEE Trans. Ind. Electron..

[24]  Mo-Yuen Chow,et al.  A neural network approach to real-time condition monitoring of induction motors , 1991 .

[25]  George W. Irwin,et al.  Neural network applications in control , 1995 .

[26]  Paul R. White,et al.  The interpretation of the bispectra of vibration signals—: II. Experimental results and applications , 1995 .

[27]  Tommy W. S. Chow,et al.  Third-order cumulant RLS algorithm for nonminimum ARMA systems identification , 1997, Signal Process..

[28]  Tommy W. S. Chow,et al.  Three phase induction machines asymmetrical faults identification using bispectrum , 1995 .

[29]  T.W.S. Chow,et al.  Blind and total identification of ARMA mode in higher order cumulants domain , 1999, IEEE Trans. Ind. Electron..

[30]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[31]  Tommy W. S. Chow,et al.  An accelerated recurrent network training algorithm using IIR filter model and recursive least squares method , 1997 .