CEEMDAN-MFE method for fault extraction of rolling bearing. Issue 5 (June 2019)

• Record Type: Journal Article
• Authors: An, Dong; Xu, Bo; Shao, Meng; Li, Hao-Dong; Wang, Li-Yan
• Is Part Of: Journal of physics. Volume 1213:Issue 5(2019)
• Publication Date: 2019-06
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1213/5/052092
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Due to the harsh environment, the feature extraction of rolling bearings is not convenient. In this paper, a method for the CEEMDAN (Complementary Ensemble Empirical Mode Decomposition With Adaption Noise) and MFE (Multi-scale Fuzzy Entropy) is put forward, Firstly, we use CEEMDAN to analyse the original signal decomposition and its advantages, and then get the weight of MFE feature extracting, put the weight into the SVM (Support Vector Machine) and realize fault detection of rolling bearing. The experimental results show that the accuracy of the algorithm is 98.8%.