Coordinated method fusing improved bubble entropy and artificial Gorilla Troops Optimizer optimized KELM for rolling bearing fault diagnosis. (30th June 2022)

• Record Type: Journal Article
• Authors: Gong, Jiancheng; Yang, Xiaoqiang; Wang, Haitao; Shen, Jinxing; Liu, Wuqiang; Zhou, Fuming
• Is Part Of: Applied acoustics. Volume 195(2022)
• Publication Date: 2022-06-30
• Subjects: Bearing fault diagnosis -- Bubble entropy -- Variational mode decomposition -- Machine learning -- MCFS -- GTO-KELM; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2022.108844
• Languages: English
• ISSNs: 0003-682X

Abstract

Highlights: An idea of automatically bearing fault detection without parameter setting discussion is proposed. The accuracy of the fault diagnosis method based on bubble entropy have been significantly improved to a practical level for the first time, and experiments have verified that it is a very effective improvement of bubble entropy. The newly proposed artificial Gorilla Troops Optimization algorithm (GTO) is applied to optimize the parameter process of machine learning classifier for the first time. The proposed GTO-KELM improves the performance of Kernel Extreme Learning Machine (KELM). Abstract: In order to improve the fault identification accuracy of bearing and simultaneously, reduce or even eliminate the influence of parameter discussion, a rolling bearing fault diagnosis method without parameter discussion based on bubble entropy is proposed in this paper. In this method, Variational Mode Decomposition based Refined Composite Multiscale Bubble Entropy (VMD-RCMBE) are combined together to extract fault features, MCFS is used to realize feature screening and dimensionality reduction, and Gorilla Troops Optimizer Optimized Kernel Extreme Learning Machine (GTO-KELM) is used to complete model training and pattern recognition. The effectiveness of the method proposed in this paper is proved by two bearing fault data sets. Through the comparative experiment with the existing methods, it is proved that this method can achieve higher classification accuracy though without the parameter discussion process, and the average detection accuracy for different data sets can reach more than 99.8%.