Diesel Engine Fault Diagnosis and Classification

Vibration signal of diesel engine fault is nonstationary and nonlinear. It is very difficult to analyze. Distinguishing diesel faults and classifying them is more difficult. In this paper, we use a new method 'Wigner Trispectrum (WT)' to describe the characteristics of vibration signals got from diesel engine. WT of signals can characterize each fault. Then WT of signals as fault features are input into least squares support vector machines (LS-SVM) to classify faults. Finally different faults can be distinguished correctly. Application indicates that the method described in the paper is a good way in analysis and classification of diesel engine faults

[1]  Johan A. K. Suykens,et al.  Bankruptcy prediction with least squares support vector machine classifiers , 2003, 2003 IEEE International Conference on Computational Intelligence for Financial Engineering, 2003. Proceedings..

[2]  Chrysostomos L. Nikias,et al.  Wigner Higher Order Moment Spectra: Definition, Properties, Computation and Application to Transient Signal Analysis , 1993, IEEE Trans. Signal Process..

[3]  J. Suykens,et al.  Bayesian inference for LS-SVMs on large data sets using the Nystrom method , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[4]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[5]  Jason Weston,et al.  Multi-Class Support Vector Machines , 1998 .