An unsupervised and enhanced deep belief network for bearing performance degradation assessment

被引:35
作者
Xu, Fan [2 ]
Fang, Zhou [3 ]
Tang, Ruoli [1 ]
Li, Xin [1 ]
Tsui, Kwok Leung [2 ]
机构
[1] Wuhan Univ Technol, Sch Energy & Power Engn, Wuhan 730072, Peoples R China
[2] City Univ Hong Kong, Sch Data Sci, Kowloon, Tat Chee Ave, Hong Kong 990777, Peoples R China
[3] City Univ Hong Kong, Dept Syst Engn & Engn Management, Kowloon, Tat Chee Ave, Hong Kong 990777, Peoples R China
基金
中国国家自然科学基金;
关键词
Improved deep belief network; Health indicator; Bearing; Performance degradation assessment; EMPIRICAL MODE DECOMPOSITION; FAULT-DIAGNOSIS; CLUSTERING-ALGORITHM; PROGNOSIS;
D O I
10.1016/j.measurement.2020.107902
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
An improved unsupervised deep belief network (DBN), namely median filtering deep belief network (MFDBN) model is proposed in this paper through median filtering (MF) for bearing performance degradation. MFDBN has the following advantages: (1) MFDBN uses the absolute amplitude of the original vibration signal as direct input to extract HI and reduce dependence on manual experience. (2) Unlike the bearing failure signal, the degradation signal is continuously changing; hence it is difficult to label the data. To solve this problem, MFDBN is used to extract health indicator (HI) without an output layer. (3) Because the noise of the vibration data, the smoothness of the extracted HI is poor, it is easy to misjudge the bearing health status. The multiple hidden layers with the MF model can denoise the HI curve layer by layer. Finally, this is verified by comparing other models and using multiple bearing datasets to demonstrate its superiority. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页数:10
相关论文
共 41 条
[1]   Deep learning for biological image classification [J].
Affonso, Carlos ;
Debiaso Rossi, Andre Luis ;
Antunes Vieira, Fabio Henrique ;
de Leon Ferreira de Carvalho, Andre Carlos Ponce .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 85 :114-122
[2]   A modal disturbance estimator for vibration suppression in nonlinear flexible structures [J].
Bagordo, G. ;
Cazzulani, G. ;
Resta, F. ;
Ripamonti, F. .
JOURNAL OF SOUND AND VIBRATION, 2011, 330 (25) :6061-6069
[3]   Rotating machinery prognostics: State of the art, challenges and opportunities [J].
Heng, Aiwina ;
Zhang, Sheng ;
Tan, Andy C. C. ;
Mathew, Joseph .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (03) :724-739
[4]   Reducing the dimensionality of data with neural networks [J].
Hinton, G. E. ;
Salakhutdinov, R. R. .
SCIENCE, 2006, 313 (5786) :504-507
[5]  
[黄毅 Huang Yi], 2012, [振动与冲击, Journal of Vibration and Shock], V31, P91
[6]   Initial center frequency-guided VMD for fault diagnosis of rotating machines [J].
Jiang, Xingxing ;
Shen, Changqing ;
Shi, Juanjuan ;
Zhu, Zhongkui .
JOURNAL OF SOUND AND VIBRATION, 2018, 435 :36-55
[7]   Fusion of medical images using deep belief networks [J].
Kaur, Manjit ;
Singh, Dilbag .
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2020, 23 (02) :1439-1453
[8]   Robust Beamforming and Jamming for Enhancing the Physical Layer Security of Full Duplex Radios [J].
Kong, Zhengmin ;
Yang, Shaoshi ;
Wang, Die ;
Hanzo, Lajos .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2019, 14 (12) :3151-3159
[9]   Degradation Trend Estimation and Prognosis of Large Low Speed Slewing Bearing Lifetime [J].
Kosasih, Buyung ;
Caesarendra, Wahyu ;
Tieu, Kiet ;
Widodo, Achmad ;
Moodie, Craig A. S. .
ADVANCES IN APPLIED MECHANICS AND MATERIALS, 2014, 493 :343-+
[10]   Stochastic Distributed Pinning Control for Co-Multi-Inverter Networks With a Virtual Leader [J].
Lai, Jingang ;
Lu, Xiaoqing ;
Monti, Antonello ;
Liu, Guo-Ping .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2020, 67 (10) :2094-2098