Novel early fault detection and diagnosis for rolling element bearings in graph spectrum domain

被引：0
|
作者：
Chen Z. [1 ,2 ,3 ]
Zhu Z. [1 ,2 ,3 ]
Lu G. [1 ,2 ,3 ]
机构：
[1] School of Mechanical Engineering, Shandong University, Jinan
[2] Key Laboratory of High-efficiency and Clean Mechanical Manufacture of MOE, Shandong University, Jinan
[3] National Demonstration Center for Experimental Mechanical Engineering Education, Shandong University, Jinan
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2022年 / 41卷 / 06期
关键词：
Early fault detection; Fault diagnosis; Graph modeling; Local mean decomposition (LMD); Rolling element bearings;
D O I：
10.13465/j.cnki.jvs.2022.06.008
中图分类号：
学科分类号：
摘要：
Health status online diagnosis is an important way to ensure the reliable operation of rolling element bearings (REBs). As a self-adaptive decomposition method, local mean decomposition (LMD) can make a multi-scale description for the non-stationary signal. However, the decomposed component signals always have an excessive large scale and are hard to extract weak fault features. To solve these problems, a novel early fault detection and diagnosis method for rolling element bearings in graph spectrum domain was proposed. First, the vibration signal was decomposed into multi-scale signals by LMD. Based on the generated component signals, the graph theory was used for dynamically modeling of rolling element bearings. Then, a quantitative index of dynamic characteristics was established by calculating the similarity between adjacent models, and the Pauta criterion was employed to make early fault detection. Finally, the pattern recognition method was used to make fault diagnosis. The experiments on XJTU-SY and Case Western Reserve University (CWRU) data sets demonstrate the effectiveness of the method. © 2022, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：51 / 59
页数：8
相关论文
共 29 条
  • [1] LEI Yaguo, JIA Feng, KONG Detong, Et al., Opportunities and challenges of machinery intelligent fault diagnosis in big data era, Journal of Mechanical Engineering, 54, 5, pp. 94-104, (2018)
  • [2] GUO Liang, GAO Hongli, ZHANG Yiwen, Et al., Research on bearing condition monitoring based on deep learning, Journal of Vibration and Shock, 35, 12, pp. 166-170, (2016)
  • [3] HUANG H, BADDOUR N, LIANG M., Bearing fault diagnosis under unknown time-varying rotational speed conditions via multiple time-frequency curve extraction, Journal of Sound & Vibration, 414, pp. 43-60, (2018)
  • [4] ZAN Tao, WANG Hui, LIU Zhihao, Et al., A fault diagnosis model for rolling bearings based on a multi-input layer convolutional neural network, Journal of Vibration and Shock, 39, 12, pp. 142-149, (2020)
  • [5] ZHANG Kang, SHI Yangchun, TANG Mingzhu, Et al., Local oscillatory-characteristic decomposition and its application in roller bearing fault diagnosis, Journal of Vibration and Shock, 35, 1, pp. 89-95, (2016)
  • [6] HUANG N E, SHEN Z, LONG S R, Et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceedings Mathematical Physical & Engineering Sciences, 454, 1971, pp. 903-995, (1998)
  • [7] SMITH J S., The local mean decomposition and its application to eeg perception data, Journal of the Royal Society Interface, 2, 5, pp. 443-454, (2005)
  • [8] TIAN Y, MA J, LU C, Et al., Rolling bearing fault diagnosis under variable conditions using LMD-SVD and extreme learning machine, Mechanism & Machine Theory, 90, pp. 175-186, (2015)
  • [9] WANG Hongming, HAO Wangshen, HAN Jie, Et al., Full vector LMD energy entropy in gear fault feature extraction, China Mechanical Engineering, 26, 16, pp. 2160-2164, (2015)
  • [10] WANG Chaoge, PANG Zhen, REN Xueping, Et al., Early fault diagnosis of roller bearing based on ensemble local mean decomposition and maximum correlated kurtosis deconvolution, Mechanical Science and Technology for Aerospace Engineering, 36, 11, pp. 1764-1770, (2017)
123