Pattern Recognition on Diesel Engine Working Conditions by Wavelet Kullback-Leibler Distance Method

Abstract This article introduces a novel pattern recognition and fault diagnosis method for diesel engines. The method is developed from engine vibration signal analysis in combination with wavelet and Kullback-Leibler distance (KLD) approaches. The new approach is termed wavelet Kullback-Leibler distance (WKLD). Experimental data relating to piston and cylinder liner wear obtained from a production diesel engine are used to evaluate the newly developed method. A good agreement between the experimental data and the WKLD estimation is found. The results of this article suggest that WKLD is an advancement on the methods which have been currently developed for pattern recognition and fault diagnosis of diesel engines.

[1]  Desire L. Massart,et al.  Wavelet packet transform applied to a set of signals: A new approach to the best-basis selection , 1997 .

[2]  C. Pattichis,et al.  Autoregressive and cepstral analyses of motor unit action potentials. , 1999, Medical engineering & physics.

[3]  Sam D. Haddad,et al.  An analytical study of offset piston and crankshaft designs and the effect of oil film on piston slap excitation in a diesel engine , 1995 .

[4]  Pascal Chesse,et al.  REAL-TIME MARINE DIESEL ENGINE SIMULATION FOR FAULT DIAGNOSIS , 2002 .

[5]  Loon Ching Tang,et al.  Application of neural networks in forecasting engine systems reliability , 2003, Appl. Soft Comput..

[6]  Raymond N. J. Veldhuis,et al.  On the computation of the Kullback-Leibler measure for spectral distances , 2003, IEEE Trans. Speech Audio Process..

[7]  Jérôme Antoni,et al.  EFFECTIVE VIBRATION ANALYSIS OF IC ENGINES USING CYCLOSTATIONARITY. PART I-A METHODOLOGY FOR CONDITION MONITORING , 2002 .

[8]  Robert B. Randall,et al.  EFFECTIVE VIBRATION ANALYSIS OF IC ENGINES USING CYCLOSTATIONARITY. PART II—NEW RESULTS ON THE RECONSTRUCTION OF THE CYLINDER PRESSURES , 2002 .

[9]  C.James Li,et al.  Model-based condition index for tracking gear wear and fatigue damage , 2000 .

[10]  A. F. Stronach,et al.  Third-order spectral techniques for the diagnosis of motor bearing condition using artificial neural networks , 2002 .

[11]  Hoon Sohn,et al.  VIBRATION-BASED DAMAGE DETECTION USING STATISTICAL PROCESS CONTROL , 2001 .

[12]  Yang-Hann Kim,et al.  A SIMPLE MODEL TO ESTIMATE THE IMPACT FORCE INDUCED BY PISTON SLAP , 2002 .

[13]  Jinsong Zhao,et al.  Multidimensional non-orthogonal wavelet-sigmoid basis function neural network for dynamic process fault diagnosis , 1998 .

[14]  Howard A. Gaberson,et al.  The Use of Wavelets for Analyzing Transient Machinery Vibration , 2002 .

[15]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[16]  Minh N. Do,et al.  Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance , 2002, IEEE Trans. Image Process..