Rolling Bearing Fault Diagnosis Method based on EEMD and GBDBN
Volume 15, Number 1, January 2019, pp. 230-240 DOI: 10.23940/ijpe.19.01.p23.230240
Zhiwu Shang, Xia Liu, Xiangxiang Liao, Rui Geng, Maosheng Gao, and Jintian Yun
Tianjin Key Laboratory of Modern Mechatronics Equipment Technology, Tianjin Polytechnic University, Tianjin, 300387, China (Submitted on October 13, 2018; Revised on November 14, 2018; Accepted on December 17, 2018)
Abstract:
Aiming at the complexity, nonlinearity, and non-stationarity of the rolling bearing vibration signal, a fault diagnosis method based on Ensemble Empirical Mode Decomposition (EEMD) and Gauss Bernoulli Deep Belief Network (GBDBN) model is proposed. The method first carries out EEMD on the vibration signal; second, the eigenvalues of each intrinsic mode function (IMF) are statistically analyzed; then, the feature vectors are constructed by selecting less change features; finally, the normalized feature vectors are input into the GBDBN to identify the fault types. The experimental results show that the proposed method achieves more than 90% recognition rate of fault types and has better fault diagnosis ability, which can provide convenience for maintenance.
References: 26
- L. Wen, X. Li, and L. Gao, “A New Convolutional Neural Network based Data-Driven Fault Diagnosis Method,” IEEE Transactions on Industrial Electronics, Vol. 65, No. 7, pp. 5990-5998, 2017
- D. Chen, J. Lin, and Y. Li, “Modified Complementary Ensemble Empirical Mode Decomposition and Intrinsic Mode Functions Evaluation Index for High-Speed Train Gearbox Fault Diagnosis,” Journal of Sound & Vibration, Vol. 424, pp. 192-207, 2018
- J. Zhao, H. Li, and J. Liu, “Planetary Gearboxes Fault Diagnosis based on EMD and EDT,” in Proceedings of Prognostics and System Health Management Conference, pp. 1-5, IEEE, 2016
- Y. Wang, S. Kang, and Y. Zhang, “Condition Recognition Method of Rolling Bearing based on Ensemble Empirical Mode Decomposition Sensitive Intrinsic Mode Function Selection Algorithm,” Journal of Electronics & Information Technology, Vol. 36, No. 3, pp. 595-600, 2014
- M. Guo and H. Chen, “Gear Defect Detection based on EEMD and BP Neural Networks,” Journal of Mechanical & Electrical Engineering, Vol. 30, No. 6, pp. 678-682, 2013
- Z. Yuan, N. Wang, and M. Li, “Fault Diagnosis Method of Fan Gearbox based on EEMD and BP Neural Network,” Journal of Northeast Dianli University, Vol. 35, No. 1, pp. 64-72, 2015
- G. Zhang, X. Wang, and H. Wang, “Rolling Bearing Fault Diagnosis based on EEMD and Fuzzy BP Neural Network,” Control & Instruments in Chemical Industry, Vol. 44, No. 1, pp. 34-38+72, 2017
- W. Shan and X. Zeng, “Signal Reconstruction and Bearing Fault Recognition based on Deep Belief Network,” Electronic Design Engineering, Vol. 24, No. 4, pp. 67-71, 2016
- G. Zhao, Q. Ge, X.Liu and X.Peng, “Research on Fault Feature Extraction and Diagnosis Method based on DBN,” Chinese Journal of Scientific Instrument, No. 9, pp. 1946-1953, 2016
- Y. Li, X. Wang, M. Zhang, and H. Zhu, “A Fault Diagnosis Method for Rolling Bearings based on Singular Value Decomposition and Deep Belief Network,” Journal of Shanghai Jiao Tong University, Vol. 49, No. 5, pp. 681-686+694, 2015
- S. Zhang, Y. Hu, and A. Jiang, “Fault Diagnosis of Bearing based on Dual Tree Complex Wavelet and Deep Belief Network,” China Mechanical Engineering, No. 5, pp. 532-536+543, 2017
- Y. Wang, X. Na, S. Kang, J. Xie, and V. Mikulovich , “State Identification Method of Rolling Bearings based on EEMD-Hilbert Envelope Spectrum and DBN Variable Loads,” Proceedings of the Chinese Society of Electrical Engineering, pp. 1-7, 2017
- M. Žvokelj, S. Zupan, and I Prebil, “Non-Linear Multivariate and Multiscale Monitoring and Signal Denoising Strategy using Kernel Principal Component Analysis Combined with Ensemble Empirical Mode Decomposition Method,” Mechanical Systems & Signal Processing, Vol. 25, No. 7, pp. 2631-2653, 2011
- N. Qin, W. Jin, J. Huang, and Z. Li, “The Empirical Modal Decomposition and Fuzzy Entropy Feature Analysis of Fault Signals of High Speed Train Bogies,” Control Theory and Application, Vol. 3, No. 9, pp. 1245-1251, 2014
- X. Zhao, “Vibration Detection Method of Rolling Bearing Fault,” Journal of Chongqing University of Science and Technology, Vol. 9, No. 1, pp. 41-44, 2007
- L. Guo, H. Gao, and Y. Zhang, “Research on Bearing State Recognition based on Deep Learning Theory,” Journal of Vibration and Shock, Vol. 12, pp. 166-170+195, 2016
- W. Li, W. Shan, and X. Zeng, “Classification and Recognition of Bearing Faults based on Deep Belief Network,” Journal of Vibration Engineering, No. 2, pp. 340-347, 2016
- Y. Lei, F. Jia, and X. Zhou, “Method of Health Monitoring of Mechanical Equipment Big Data based on Deep Learning Theory,” Chinese Journal of Mechanical Engineering, Vol. 21, pp. 49-56, 2015
- P. Tamilselvan and P. Wang, “Failure Diagnosis using Deep Belief Learning based Health State Classification,” Reliability Engineering and System Safety, Vol. 115, pp. 124-135, 2013
- G. Wu and A. Xiao, “Gear Box Fault Recognition based on Depth Learning Neural Network,” Network Security Technology and Application, No. 12, pp. 162-164, 2016
- S. Zhang, “Dynamic Monitoring of Bearing States based on Multiple Sparse Self Coding,” Journal of Vibration and Shock, No. 19, pp. 125-131, 2016
- W. Sun, S. Shao, and R. Yan, “Fault Diagnosis of Induction Motor based on Sparse Automatic Coding Deep Neural Network,” Chinese Journal of Mechanical Engineering, No. 9, pp. 65-71, 2016
- G. Wu, J. Ding, and J. Lin, “Research on EEMD-RA-KU Method for Bearing Fault Detection,” Mechanical Strength, No. 6, pp. 1167-1172, 2016
- X. Chen, L. Jiang, and Z. Song, “Nonlinear Process Fault Detection based on Gauss Restricted Boltzmann Machine,” Journal of Shanghai Institute of Technology (Natural Science Edition), Vol. 15, No. 2, pp. 139-143, 2015
- P. Shi, K. Liang, and N. Zhao, “Gear Intelligent Fault Diagnosis based on Deep Learning Feature Extraction and Particle Swarm Support Vector Machine,” Chinese Mechanical Engineering, No. 9, pp. 1056-1061+1068, 2017
- Y. Zhu, S. Huang, and T. Yang, “Fault Diagnosis based on Self Encoding Stack Noise,” Automation of Manufacturing Industry, No. 3, pp. 152-156, 2017
Please note : You will need Adobe Acrobat viewer to view the full articles. |