Study On Wavelet Neural Network Fault Diagnosis For Diesel Engine Based On The Vibration Signal

Condition monitoring and fault diagnosis of diesel engine is crucial to improve the reliability of diesel engine power plant, and to meet the requirements of modern predictive maintenance and automatization. However, diesel engine is a typical reciprocating machine, its monitoring and diagnosis are very difficult because of its complex structure. This paper gave the diagnosis method of diesel engine fault based on vibration signal.Wavelet packet analysis is a way of handing signals based on multi-resolution analysis, capable of distinguishing each wave frequency to the desired level of detail. It can not only resolve low-frequency signals , further, it can also do the same to high-frequency signals, and so has broad application in the diagnosis of machine fault.Artificial Neural Networks, a kind of large-scale parallel distributing system, is charactersized by self-organizing, self-learning, self-adapting and non-linearity. Those characteristics make it have bright prospect in settling complex non-linearity questions.This paper give a fault diagnosis method of diesel engine based on wavelet neural network analysis of vibration signals considering the current research on it home and aboard and then executes empiricial test analysis on it . First of all , making analysis on time domain and frequency domain of Vibration signal of diesel engine in order to extract parameters of time domain; Then having the process of noise reduction on signal collected using the method of improved wavelet packets noise reduction, the consequence of Experiments tell us that the method presented in this paper is prior to traditional noise reduction method, extracting feature parameters based on wavelet packet analysis and putting the samples into BP neural network for training and testing to achieve the desired effect. The method presented in this paper is tested through experiment, the result is that The combining of wavelet analysis and neural networks is a correct method about diesel engine fault diagnosis, the method presented in the paper is easier and has broader prospects comparing with that based on neural network characteristic by time domain parameters.