小波包能量特征法在汽车变速器轴承故障诊断中的应用

归纳和总结了小波神经网络轴承故障诊断法的实施步骤,阐述了小波包的原理,并以变速器轴承故障诊断为例,提取了小波包节点能量作为反映变速器轴承故障类型的振动信号特征参数,并用这些特征参数训练BP神经网络进行故障模式识别。结果表明,如果神经网络设计合理,训练适当,则具有很强的故障识别能力。说明了利用小波包能量法和BP神经网络进行变速器轴承故障诊断是可行而且有效的。

The Application of Wavelet Packet Energy Feature to the Fault Diagnosis of Automotive Transmission Bearing

A fault diagnosis method for rolling bearings in automotive transmission based on wavelet packet energy feature and BP neural network is presented. The wavelet decomposition is conducted on the vibration signals of bearing, and the energy of wavelet node is extracted as the feature parameter of vibration signal of bearing. Then these feature parameters are used to train BP neural network for fault pattern recognition. The results show that the neural network with rational design and proper training has strong capability of fault identification and that applying wavelet packet energy feature and BP neural network to fault diagnosis of transmission bearing is feasible and effective.