A Fault Diagnosis Method of Rolling Bearing Based on Attention Entropy and Adaptive Deep Kernel Extreme Learning Machine

Weiyu Wang; Xunxin Zhao; Lijun Luo; Pei Zhang; Fan Mo; Fei Chen; Diyi Chen; Fengjiao Wu; Bin Wang

LAPSE:2023.7789

Published Article

LAPSE:2023.7789

A Fault Diagnosis Method of Rolling Bearing Based on Attention Entropy and Adaptive Deep Kernel Extreme Learning Machine

Weiyu Wang, Xunxin Zhao, Lijun Luo, Pei Zhang, Fan Mo, Fei Chen, Diyi Chen, Fengjiao Wu, Bin Wang

February 24, 2023

Abstract
To address the difficulty of early fault diagnosis of rolling bearings, this paper proposes a rolling bearing diagnosis method by combining the attention entropy and adaptive deep kernel extreme learning machine (ADKELM). Firstly, the wavelet threshold denoising method is employed to eliminate the noise in the vibration signal. Then, the empirical wavelet transform (EWT) is utilized to decompose the denoised signal, and extract the attention entropy of the intrinsic mode function (IMF) as the feature vector. Next, the hyperparameters of the deep kernel extreme learning machine (DKELM) are optimized using the marine predators algorithm (MPA), so as to achieve the adaptive changes in the DKELM parameters. By analyzing the fault diagnosis performances of the ADKELM model with different kernel functions and hidden layers, the optimal ADKELM model is determined. Compared with conventional machine learning models such as extreme learning machine (ELM), back propagation neural network (BPNN) and probabilistic neural network (PNN), the high efficiency of the method proposed in this paper is verified.

Record ID

LAPSE:2023.7789

Keywords

attention entropy, deep kernel extreme learning machine, empirical wavelet transform, fault diagnosis, marine predators algorithm, rolling bearing

Subject

Process Control

Suggested Citation

Wang W, Zhao X, Luo L, Zhang P, Mo F, Chen F, Chen D, Wu F, Wang B. A Fault Diagnosis Method of Rolling Bearing Based on Attention Entropy and Adaptive Deep Kernel Extreme Learning Machine. (2023). LAPSE:2023.7789

Author Affiliations

Wang W: Wuling Power Corporation Ltd., Changsha 410004, China; Hydropower Industry Innovation Center of State Power Investment Corporation Limited, Changsha 410004, China [ORCID]
Zhao X: Wuling Power Corporation Ltd., Changsha 410004, China; Hydropower Industry Innovation Center of State Power Investment Corporation Limited, Changsha 410004, China
Luo L: Wuling Power Corporation Ltd., Changsha 410004, China; Hydropower Industry Innovation Center of State Power Investment Corporation Limited, Changsha 410004, China
Zhang P: Wuling Power Corporation Ltd., Changsha 410004, China; Hydropower Industry Innovation Center of State Power Investment Corporation Limited, Changsha 410004, China
Mo F: Wuling Power Corporation Ltd., Changsha 410004, China; Hydropower Industry Innovation Center of State Power Investment Corporation Limited, Changsha 410004, China
Chen F: Department of Power and Electrical Engineering, Northwest A&F University, Xianyang 712100, China
Chen D: Department of Power and Electrical Engineering, Northwest A&F University, Xianyang 712100, China
Wu F: Department of Power and Electrical Engineering, Northwest A&F University, Xianyang 712100, China
Wang B: Department of Power and Electrical Engineering, Northwest A&F University, Xianyang 712100, China [ORCID]

Journal Name

Energies

Volume

15

Issue

22

First Page

8423

Year

2022

Publication Date

2022-11-10