Affiliations: [a] School of Mechatronic Engineering, Changchun University of Technology, Changchun, Jilin, China
| [b] School of Mechatronic Engineering, Changchun Institute of Technology, Changchun, Jilin, China
| [c] School of Applied Technology, Changchun University of Technology, Changchun, Jilin, China
| [d] Welding and Assembly Development Department, FAW Tooling Die Manufacturing CO., LTD., Changchun, Jilin, China
Correspondence:
[*]
Corresponding author. Bangcheng Zhang, School of Mechatronic Engineering, Changchun Institute of Technology, as well, School of Mechatronic Engineering, Changchun University of Technology, Changchun, Jilin, China. E-mail: zhangbangcheng@ccut.edu.cn.
Abstract: The anomaly detection research of drive end bearings (DEBs) is of great significance to the safe and reliable operation of hoist. This paper proposes an anomaly detection method of DEBs based on the linear weighted sum combines with the belief rule base. First, in order to improve the accuracy of anomaly detection, the time-domain features and frequency-domain features are integrated by linear weighted sum (LWS) respectively. Then, belief rule base (BRB) method is provided for anomaly detection using fused features. Meanwhile, the covariance matrix adaption evolution strategy (CMA-ES) is utilized to optimize the parameters of belief rule base model. Finally, the validity of the proposed method is verified by the vibration data, which are acquired from the condition monitoring system of hoist in body-in-white (BIW) welding production line. The proposed method achieves a high detection accuracy. It is proved that the proposed method is suitable for anomaly detection of DEBs in the actual BIW welding production line.
Keywords: Anomaly detection, linear weighted
sum, belief rule base, drive end bearing
