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  

Application of wavelet packet entropy and multi kernel learning in fault diagnosis of train bogie bearing

作　　者：周彭滔 单奇[1] 叶运广 

机构地区：[1]西南交通大学机械工程学院,四川成都610031

出　　处：《燕山大学学报》2017年第5期401-406,共6页Journal of Yanshan University

基　　金：国家自然科学基金资助项目(51475387);中央高校基本业务费专项基金项目(2682014CX033);四川省科技创新苗子工程项目(2015102)

摘　　要：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。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.

关 键 词：列车转向架轴承 故障诊断 小波包熵 多核学习 

分 类 号：TH18[机械工程—机械制造及自动化]