论文部分内容阅读
应用小波包分解技术提取齿轮箱振动信号中的故障特征向量,并以此作为改进BP神经网络的输入,对神经网络进行训练,建立了齿轮箱运行状态分类器,用以识别齿轮箱的运行状态。试验结果表明,小波包分解与神经网络相结合的齿轮箱齿轮故障识别方法是可靠的,可以准确识别齿轮箱的故障。
The wavelet packet decomposition technique is used to extract the fault eigenvectors in the gearbox vibration signal and use it as input to improve the BP neural network to train the neural network. The gearbox operating state classifier is established to identify the operating status of the gearbox . The experimental results show that the method of gear box fault identification based on wavelet packet decomposition and neural network is reliable and can accurately identify the fault of gear box.