基于小波神经网络的滚动轴承故障诊断

Fault diagnosis of the ball bearings based on wavelet neural networks

根据滚动轴承振动信号的频域变化特征,利用小波分析对其建立频域特征向量,准确地提取了故障的特征信息,结合RBF神经网络训练速度快的优点,将RBF神经网络应用于轴承故障特征的选择,并利用所确定的特征及RBF分类器进行故障诊断。实验结果表明,该方法可实现滚动轴承故障的可靠诊断。

Based on the frequency domain characteristics of the vibration signals of the ball bearings, the characteristic vector of frequency domain was established using the wavelet analysis,and feature infor- mation of the faults is correctly extracted by using a RBF network ,and the faults of the ball bearings are di- agnosed on the base of the established characteristic vectors and the RBF classifier. The experimental results demonstrate that the method can be applied into reliable diagnosis of typical faults of rotating machinery.