Affiliations: [a] School of Applied Mathematics, Xiamen University of Technology, Xiamen, Fujian, P.R. China | [b] School of Computer Science and Technology, Huaqiao University, Xiamen, Fujian, P.R. China
Correspondence:
[*]
Corresponding author. Huixin He, School of Computer Science and Technology, Huaqiao University, Xiamen 361024,
Fujian, P.R. China. E-mail: [email protected].
Abstract: Fault level identification is a new challenge and a special task in the field of fault diagnosis. There are ordinal structures between different fault levels, so how to utilize the potential ordinal information is especially important for fault level diagnosis. Fault level identification can be regarded as ordinal classification in the fields of machine learning and pattern recognition. This paper first proposes an ordinal rough set model by introducing ordinal rough approximation operators based on fuzzy covering, and then designs a feature selection algorithm for ordinal classification. Finally, the proposed method is applied to the gear crack level identification. Experimental results demonstrate the effectiveness of the proposed approach for fault level identification.
