期刊
NEUROCOMPUTING
卷 445, 期 -, 页码 26-34出版社
ELSEVIER
DOI: 10.1016/j.neucom.2021.02.078
关键词
Rolling bearing; Fault diagnosis; Principle component analysis; Adaptive deep belief networks; Particle swarm optimization
资金
- NEEC project under University of South Carolina [N00174-17-1-0006]
"The paper proposes a deep learning-based approach for rolling element bearing fault diagnosis to address challenges in existing methods including difficulty in structure decision-making, low accuracy, and learning efficiency. The proposed method integrates principal component analysis, adaptive deep belief network, and particle swarm optimization, achieving high accuracy and convergence rate. Experimental results demonstrate the effectiveness and accuracy of the proposed approach."
Rolling element bearings are critical components in industrial rotating machines. Faults and failures of bearings can cause degradation of machine performance or even a catastrophe. Therefore, it is significant to perform bearing fault diagnosis accurately and effectively. Deep Learning based approaches are promising for bearing diagnosis. They can extract fault information efficiently and conduct accurate diagnosis. However, the structure of deep learning networks is often determined by trial and error, which is time consuming and lacks theoretical guidance. Besides, the traditional deep learning approaches have low diagnosis accuracy and learning efficiency. To address these problems, this paper proposes a rolling element bearing fault diagnosis approach based on principal component analysis and adaptive deep belief network with Parametric Rectified Linear Unit activation layers. In the proposed approach, particle swarm optimization is integrated to obtain an optimal DBN structure with high accuracy and convergence rate. Experiments on tapered roller bearings and comparison studies with state-of-the-art methods are conducted to demonstrate the effectiveness and accuracy of the proposed approach. (c) 2021 Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据