基于小波变换预处理的一种神经网络故障诊断方法的研究

Research on NN Based Diagnosis Method Using Wavelet as its Pretreatment

针对无法区分干扰信号与有用信号一类系统提出了一种先用小波变换让信号在不同频段上进行分解，提取各分量故障信号的特征，然后应用ＢＰ神经网络进行故障诊断的一种方法。并将这种方法应用于液压系统的泄漏故障诊断。

A fault diagnosis method based on multiresolution and neural network(NN) is proposed in this paper. In this method, the wavelet transform is used to divide the signal into different frequency bands in order to extract the properties of the signal. And then inputing these feature parameters to a BP neural network the fault diagnosis is realized. As an application of this method, experiments on hydraulic system leakage are made and the results are satisfactory.