摘要
对齿轮振动信号应用小波包分解提取故障特征向量,并以此作为改进BP神经网络的输入,对神经网络进行训练,建立齿轮运行状态分类器,用以诊断齿轮的运行状态。结果表明,该方法对齿轮故障诊断十分有效。
The wavelet package is applied to decompose vibration signal of gear to get fault eigenvector.Then,the eigenvector is employed as the input samples to train the improved BP neural network,so as to set up the classifier of operational state to identity gearbox fault.The experimental results testify that the proposed method is a useful tool to diagnose gear fault.
出处
《机械研究与应用》
2011年第1期82-84,87,共4页
Mechanical Research & Application
关键词
小波包
BP神经网络
齿轮
故障诊断
wavelet packet
BP neural network
gear
fault diagnosis
