Automotive signal diagnostics using wavelets and machine learning

In this paper, we describe an intelligent signal analysis system employing the wavelet transformation in the solution of vehicle engine diagnosis prob lems. Vehicle engine diagnosis often involves multiple signal analysis, The developed system first partitions a leading signal into small segments rep resenting physical events or stateds based on wavelet multi-resolution anal ysis. Second, by applying the segmentation result of the leading signal to the other signals, the detailed properties of each segment, including inter -signal relationships, are extracted to form a feature vector, Finally, a f uzzy intelligent system is used to learn diagnostic features from a trainin g set containing feature vectors extracted from signal segments at various vehicle states, The fuzzy system applies its diagnostic knowledge to classi fy signals as abnormal or normal. The implementation of the system is descr ibed and experiment results are presented.