1.School of Urban Construction and Safety Engineering, Shanghai Institute of Technology, Shanghai 201418, China;
2. School of Mechanical Engineering, Shanghai Institute of Technology, Shanghai 201418, China;
3. School of Rail Transit, Shanghai Institute of Technology, Shanghai 201418, China;
4. School of Electrical and Electronic Engineering,Shanghai Institute of Technology, Shanghai 201418, Chin
Abstract:The existing degradation index construction of rolling bearing is highly dependent on prior knowledge and the practical application situation is single. Aiming at this, a restricted Boltzmann machine (RBM) based degradation index construction method for rolling bearings was proposed. The vibration signals of rolling bearings in normal state were processed as normalized amplitude spectrum, which was taken as the training samples for establishing RBM model. The structural characteristics of the RBM model was that the number of units in its output layer was set as 1, and the output after model training was taken as the basis for constructing degradation indexes. The validity of the proposed method is verified by the whole life cycle experimental data of rolling bearings under different situations. Compared with the recent literatures, the proposed degradation index avoids the manual selection of degradation features in the construction process, describes the bearing degradation process clearly and has a certain sensitivity to early weak fault detection.
Keywords: degradation index; restricted Boltzmann machine(RBM); rolling bearing
程道来1,魏婷婷2,潘玉娜3,马向华4. 一种基于RBM的滚动轴承退化指标构建方法[J]. 振动与冲击, 2022, 41(16): 210-216.
CHENG Daolai1,WEI Tingting2,PAN Yuna3,MA Xianghua4. A rolling bearing degradation index construction method based on RBM. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(16): 210-216.
[1] DONG S, WEN G, ZHANG Z. Rolling Bearing Incipient Degradation Monitoring and Performance Assessment Based on Signal Component Tracking [C]. IEEE Special section on advances in prognostics and system health management, 2019, 7:45984-45993.
[2] 何正嘉, 陈进, 王太勇, 等. 机械故障诊断理论及应用 [M]. 北京: 高等教育出版社, 2010.
HE Zhengjia, CHEN Jin, WANG Taiyong. Theories and applications of machinery fault diagnostics [M].Beijing: Higher Education Press, 2010.
[3] XU F, FANG Z, TANG R, et al. An unsupervised and enhanced deep belief network for bearing performance degradation assessment [J]. Measurement, 2020, 162 (107902): 1-10.
[4] 张龙, 成俊良, 李兴林, 等.基于自适应频带冲击强度的滚动轴承故障量化评估[J]. 振动与冲击, 2018, 37(19):30-38.
ZHANG Long, CHNEG Junliang, LI Xinglin, et al. Fault quantitative evaluation of rolling bearings based on shock value of selected frequency band [J]. Journal of vibration and shock, 2018, 37 (19): 30-38.
[5] C.H.Hu, B.D.Y, P.W. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life [J]. Reliability engineering and system safety, 2012, 103 (3): 120-135.
[6] LEI Y, LI N, GUO L., et al. Machinery health prognostics: a systematic review from data acquisition to RUL prediction [J], Mechanical system and signal processing. 2018, 104: 799-834.
[7] SHEN Z, CHEN X, HE Z. remaining life predictions of rolling bearing based on relative features and multivariable support vector machine [J]. Mechanical engineering, 2013, 49 (2): 183-189.
[8] TSE P W, WANG D. Enhancing the abilities in assessing slurry pumps’ performance degradation and estimating their remaining useful lives by using captured vibration signals [J]. Journal of vibration and control, 2017, 23 (12): 1925-1937.
[9] LIU Y, ZHAO C, XIONG M, et al. Assessment of bearing performance degradation via extension and EEMD combined approach [J]. Journal of central south university, 2017, 24 (5): 1155-1163.
[10] 潘玉娜, 陈进. 小波包-支持向量数据描述在轴承性能退化评估中的应用研究. 振动与冲击. 2009, 28 (4):164-167.
PAN Yuna, CHEN Jin. Wavelet package-support vector data description applied in bearing performance degradation assessment [J]. Journal of vibration and shock, 2009, 28 (4): 164-167.
[11] ZHANG T, Li K, Ma J, et al. Degradation assessment and trend prediction of rolling bearing based on MD-ESN [J]. Vibroengineering PROCEDIA, 2018, 19: 60-65.
[12] WANG S, CHEN J, WANG H, et al. Degradation evaluation of slewing bearing using HMM and improved GRU [J]. Measurement, 2019, 146: 385-395.
[13] RAI A, UPADHYAY S H. Intelligent bearing performance degradation assessment and remaining useful life prediction based on self-organizing map and support vector regression [J]. Journal of mechanical engineering science, 2018, 232 (6): 1-15.
[14] 周建民, 王发令, 张臣臣, 等. 基于特征优选和GA-SVM的滚动轴承智能评估方法 [J]. 振动与冲击, 2021, 40 (04): 227-234.
ZHOU Jianmin, WANG Falin, ZHANG Chenchen, et al. An intelligent method for rolling bearing evaluation using feature optimization and GA-SVM[J]. Journal of vibration and shock, 2021, 40 (04): 227-234.
[15] WANG F, JIANG H, SHAO H, et al. An adaptive deep convolutional neural network for rolling bearing fault diagnosis [J]. Measurement science and technology, 2017, 28 (9):095-104.
[16] JIA F, LEI Y, GUO L, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines [J]. Neurocomputing, 2018, 272: 619-628.
[17] GUO L, LEI Y, LI N , et al. Deep convolution feature learning for health indicator construction of bearings[C]. 2017 Prognostics and System Health Management Conference (PHM-Harbin) . Harbin :IEEE,2017.
[18] YIN J, ZHAO W. Fault diagnosis network design for vehicle on-board equipment of high-speed railway: a deep learning approach [J]. Engineering applications of artificial intelligence, 2016, 56: 250–259.
[19] PAN Y, HONG R, CHEN J, et al. Performance degradation assessment of slewing bearings based on deep auto-encoder and optimized particle filtering[J]. Journal of vibration and control, 2019, 25 (17): 1-15.
[20] SALAKHUTDINOV R, MNIH A, HINTON G. Restricted Boltzmann machines for collaborative filtering [C]. Proceedings of the 24th international conference on machine learning, 2007, 791-798.
[21] 李鸿寅, 陈长文, 董诠键, 等. 热力学及统计物理 [M]. 河南: 河南大学出版社, 1988.
LI Hongyin, CHEN Changwen, DONG Quanjian, et al. Thermodynamics and statistical physics [M].Henan: Henan University Press, 1988.
[22] 张春霞, 姬楠楠, 王冠伟. 受限波尔兹曼机 [J].工程数学学报, 2003, 32 (2): 159-173.
ZHANG Chunxia, Ji Nannan, WANG Guanwei. Restricted Boltzmann machines [J], Chinese journal of engineering mathematics, 2003, 32 (2):159-173.
[23] GEOFFREY H. Training Products of Experts by Minimizing Contrastive Divergence [J]. Neural computation, 2002, 14(8):1771-1800.
[24] 潘玉娜.滚动轴承的性能退化特征提取及评估方法研究[D].上海:上海交通大学,2011.
PAN Yuna. Study on feature extraction and assessment method of rolling element bearing performance degradation [D]. Shanghai: Shanghai Jiao Tong University, 2011.
[25] HAI Q, JAY L, JING L, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics [J]. Journal of sound and vibration, 2005, 289 (2006): 1066-1090.
[26] 程道来, 贾玉琛, 潘玉娜. 基于S时频熵的球轴承性能退化特征指标提取方法 [J]. 轴承, 2019,04 (15): 59-62.
CHENG Daolai, JIA Yuchen, PAN Yuna.Extraction Method for Performance Degradation Characteristic Indexes of Ball Bearings Based on S-Time-Frequency Entropy [J].Bearing, 2019, 04(15): 59-62.
[27] 张龙, 吴荣真. 滚动轴承性能退化评估的自适应频带熵能比指标 [J]. 振动与冲击, 2021, 40(02): 63-71+110.
ZHANG Long, WU Rongzhen. Performance degradation assessment of rolling bearings based on the entropy energy ratio of adaptive frequency band [J]. Journal of vibration and shock, 2021, 40 (02): 63-71+110.
[28] 王斐, 房立清, 赵玉龙, 等. 基于VMD和SVDD的滚动轴承早期微弱故障监测和性能退化评估研究 [J]. 振动与冲击, 2019, 38 (22): 224-230.
WANG Fei, FANG Liqing, ZHAO Yulong, et al. Rolling bearing early weak fault detection and performance degradation assessment based on VMD and SVDD [J]. Journal of vibration and shock, 2019, 38 (22): 224-230.