• CN：11-2187/TH
• ISSN：0577-6686

• 运载工程 •

### 滚动轴承安全域建模方法及其在高速列车异常检测中的应用

1. 1. 电子科技大学机械电子工程学院 成都 611731；
2. 杭州轴承试验研究中心有限公司 杭州 310022
• 出版日期:2017-05-15 发布日期:2017-05-15
• 作者简介:

刘志亮(通信作者)，男，1984年出生，博士，副教授，格拉斯哥大学(英国)荣誉讲师、阿尔伯塔大学(加拿大)访问学者。主要研究方向为旋转机械预测与健康管理、工业大数据挖掘。

E-mail：Zhiliang_Liu@uestc.edu.cn

• 基金资助:
* 国家重点研发计划(2016YF131200401)、国家自然科学基金(51505066)、中央高校基本科研业务经费(ZYGX2015J081)、中国博士后科学基金(2016T90842)和浙江省博士后科研项目择优(B5H1502002)资助项目; 20160604收到初稿，20170115收到修改稿;

### Safety Domain Modelling of Rolling Bearings and Its Application to Anomaly Detection for High-speed Rail Vehicles

LIU Zhiliang1,2, LIU Shilin1, LI Xinglin2, KANG Jinlong1, PENG Xing1

1. 1. School of Mechatronics Engineering， University of Electronic Science and Technology of China， Chengdu 611731;
2. State Testing Laboratory of Hangzhou Bearing Test and Research Center， Hangzhou 310022
• Online:2017-05-15 Published:2017-05-15

Abstract:

Safety domain can be used to describe bearing health condition from the perspective of the concept of domain. It is used to identify whether a bearing is normal in a feature space established by the operation condition. However, high-speed rail vehicles usually operate in normal condition, that is, the collected data are usually normal samples rather than faulty ones. Actually, it is costly to get faulty samples for high-speed rail vehicles. Therefore, we know very little or even nothing about their fault behaviors. It means that the conventional methods, based on both normal and fault samples, cannot be applied to fault diagnosis of high speed rail vehicles. Support vector data description (SVDD) is a tool to use only normal samples in the feature space to build the so-called safety domain; however, the SVDD based models are easily influenced by the penalty parameter. Particularly in the context of big data, it is crucial to select the penalty parameter in a reasonable and quick way so that it helps to improve accuracy of both the safety domain boundary and the anomaly detection. For this reason, a penalty parameter selection method based on the distance entropy in the kernel space of safety domain is proposed. Based on the position distribution of samples in the kernel space, the method calculates the distance between every sample and the kernel center, computes the distance entropy of the training data, finds the relationship between the optimal penalty parameter and the distance entropy on the basis of a large number of reference data points, and finally provides an empirical formula to determine the optimal penalty parameter. Experimental results show that, comparing with grid search methods and genetic algorithm, the proposed method can be easily interpreted and can also significantly improve efficiency of safety domain modeling without much accuracy loss. The proposed approach is applied to anomaly detection of a wheel set bearing for high-speed rail vehicles.