Weighted Kernel Entropy Component Analysis for Fault Diagnosis of Rolling Bearings

Hongdi Zhou; Tielin Shi; Guanglan Liao; Jianping Xuan; Jie Duan; Lei Su; Zhenzhi He; Wuxing Lai

doi:10.3390/s17030625

Weighted Kernel Entropy Component Analysis for Fault Diagnosis of Rolling Bearings

Sensors (Basel). 2017 Mar 18;17(3):625. doi: 10.3390/s17030625.

Authors

Hongdi Zhou¹, Tielin Shi², Guanglan Liao³, Jianping Xuan⁴, Jie Duan⁵, Lei Su⁶, Zhenzhi He⁷, Wuxing Lai⁸

Affiliations

¹ State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. zh_hongdi@hust.edu.cn.
² State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. tlshi@hust.edu.cn.
³ State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. guanglan.liao@hust.edu.cn.
⁴ State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. jpxuan@hust.edu.cn.
⁵ State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. jduan@hust.edu.cn.
⁶ School of Mechanical Engineering, Jiangnan University, Wuxi 214122, China. lei_su2015@jiangnan.edu.cn.
⁷ School of Mechanical & Electrical Engineering, Jiangsu Normal University, Xuzhou 221116, China. hezz82@163.com.
⁸ State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China. wxlai@hust.edu.cn.

Abstract

This paper presents a supervised feature extraction method called weighted kernel entropy component analysis (WKECA) for fault diagnosis of rolling bearings. The method is developed based on kernel entropy component analysis (KECA) which attempts to preserve the Renyi entropy of the data set after dimension reduction. It makes full use of the labeled information and introduces a weight strategy in the feature extraction. The class-related weights are introduced to denote differences among the samples from different patterns, and genetic algorithm (GA) is implemented to seek out appropriate weights for optimizing the classification results. The features based on wavelet packet decomposition are derived from the original signals. Then the intrinsic geometric features extracted by WKECA are fed into the support vector machine (SVM) classifier to recognize different operating conditions of bearings, and we obtain the overall accuracy (97%) for the experimental samples. The experimental results demonstrated the feasibility and effectiveness of the proposed method.

Keywords: Renyi entropy; dimensional reduction; fault diagnosis; feature extraction; weighted kernel entropy component analysis.