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