基于小波包能量特征向量神经网络的旋转机械故障诊断

为精确诊断旋转机械的故障,提出一种基于小波包特征向量的神经网络故障诊断方法。用转子台信号模拟旋转机械故障,并对采集到的信号进行3层小波包分解,构造小波包特征向量,并以此为故障样本对3层BP网络进行训练,实现智能化故障诊断。实验结果表明训练好的神经网络能够很好地诊断出转子台故障类型,为旋转机械的故障诊断提供了新方向。

Fault Diagnosis of Rotation Machine Based on Wavelet Packet Energy Eigenvector Neural Network

To diagnose accurately the rotation machine fault,this paper presents a new method of fault diagnosis based on wavelet packet energy eigenvector and neural network.It adopts three-layer wavelet packet to decompose the signal of rotation machine,and constructs the wavelet packet energy eigenvector,then takes those wavelet packet energy eigenvectors as fault samples to train three-layer BP(Back Propagation)neural network,finally realizes intelligent fault diagnosis.The practical example shows that the trained BP neural network can diagnose the kind of rotation machine faults.This method develops a new direction of the fault diagnosis of rotation machine.