A bearing fault diagnosis scheme with statistical-enhanced covariance matrix and Riemannian maximum margin flexible convex hull classifier

Xin Li; Yu Yang; Wang Ping; Wang Jian; Junsheng Cheng

doi:10.1016/j.isatra.2020.11.018

A bearing fault diagnosis scheme with statistical-enhanced covariance matrix and Riemannian maximum margin flexible convex hull classifier

ISA Trans. 2021 May:111:323-336. doi: 10.1016/j.isatra.2020.11.018. Epub 2020 Nov 26.

Authors

Xin Li¹, Yu Yang², Wang Ping³, Wang Jian³, Junsheng Cheng¹

Affiliations

¹ State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, 410082, China.
² State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, 410082, China. Electronic address: yangyu@hnu.edu.cn.
³ AECC Hunan Aviation Powerplant Research Institute, Zhuzhou, 412002, China; AECC Key Laboratory of Aero-engine Vibration Technology, Zhuzhou, 412002, China.

PMID: 33272589
DOI: 10.1016/j.isatra.2020.11.018

Abstract

To achieve more appropriate fault feature representation for bearing, a statistical-enhanced covariance matrix (SECM) is proposed to extract the global-local features and the interaction of them. Besides, three statistical parameters are introduced to SECM to enhance its statistical characteristics. For fully mining the Riemannian geometric information embedded in SECMs, a Riemannian maximum margin flexible convex hull (RMMFCH) classifier with Log-Euclidean metric (LEM) is designed, where a set of Riemannian kernel mapping functions map SECMs to a higher-dimensional Hilbert space. In this space, the RMMFCH can be directly solved, which reduces the extra computation cost. Hence, we design a fault diagnosis scheme of bearing with SECM and RMMFCH. Experiment results prove the promising performance of our method for bearing fault diagnosis.

Keywords: Fault diagnosis of bearing; Riemannian manifold; Riemannian maximum margin flexible convex hull; Statistical-enhanced covariance matrix.