基于小波神经网络的滚动轴承故障诊断

研究了基于BP神经网络、基于径向基神经网络等的故障诊断方法和原理,并利用小波包分解获得了滚动轴承振动信号的特征向量,进行了详细的故障诊断实验研究,通过实验,比较了基于松散型小波神经网络与紧致型小波神经网络的诊断结果。仿真结果表明,紧致型小波神经网络用于滚动轴承的故障诊断更为有效。

Wavelet Neural Network Based Diagnosis of the Rolling Bearing

In this paper,the feature vectors of the roller bearing signals are extracted on the basis of wavelet analysis and a fault diagnosis experiment is carried through wavelet neural network in detail.The method and the theory of fault diagnosis based on BP neural network and the radial basis function neural network are studied and the results of diagnosis based on relax-type neural-networks and close-type neural-networks are compared.Simulation results indicate that diagnosis based on close-type networks more effective.