小波包熵与多核学习在列车转向架轴承故障诊断中的应用

摘要

A new method based on the wavelet packet entropy and multiple kernel learning is proposed in order to improve the accuracy and efficiency of the fault diagnosis of train bogie bearing. First, the method of wavelet packet is used to decompose the rolling bearing vibration signals into three-layer, characteristic entropy is extracted, and then the eigenvector of wavelet packet of the vibrating signals is constructed.Second, a multi kernel learning is employed to learn a kernel function and the classifier from the training samples.Finally, the trained classifier is used to identify the fault type of the train bogie bearing.The results show that the method proposed can be used to accurately and effectively realize the fault diagnosis of train bearing, provid a good reference for the actual train bogie rolling fault diagnosis.%为提高列车转向架轴承故障诊断的准确性和效率,提出一种基于小波包熵和多核学习的列车轴承故障智能诊断方法.该方法通过对轴承振动信号进行小波包分解,提取小波包特征分量,通过广义信息熵的概念定义了小波包特征熵函数,最后基于多核学习训练出的分类器对轴承故障类型进行分类,判断轴承的工作状态.实验结果表明,该方法可以准确、有效地实现列车轴承的故障判别,为列车转向架轴承早期故障诊断的研究提供一定的新的思路.