Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6883337 | Computers & Electrical Engineering | 2018 | 10 Pages |
Abstract
The failure of rolling bearing is the foremost cause to the failure and breakdown of rotating machines. As the bearing vibration signal is full of periodic and nonlinear characteristics, using common time domain or frequency domain approaches cannot easily make an accurate estimation for the bearing healthy condition. In the paper, an efficient and effective fault diagnostic approach was proposed to accommodate the requirements for both real-time monitoring and accurate estimation of different fault types and their severities. Firstly, a four-dimensional feature extraction algorithm using entropy and Holder coefficient theories was proposed for extracting health status feature vectors from the vibration signals, and secondly a gray relation algorithm was employed for achieving bearing fault pattern recognition intelligently using the extracted feature vectors. The experimental study has illustrated the effectiveness of the proposed approach in comparison with the existing artificial intelligent methods, and can be suitable for on-line health status monitoring.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Networks and Communications
Authors
Ying Yulong, Li Jingchao, Chen Zhimin, Guo Jian,