Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review

IEEE Access - Tập 8 - Trang 29857-29881 - 2020
Shen Zhang1,2, Shibo Zhang3, Bingnan Wang1, T.G. Habetler2
1Mitsubishi Electric Research Laboratories, Cambridge, USA
2[school of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA]
3Department of Computer Science, Northwestern University, Evanston, USA

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1109/ACCESS.2019.2934233

10.1016/j.microrel.2017.03.006

10.1109/TIA.2017.2661250

10.1109/TIE.2017.2762639

10.1016/j.ymssp.2017.08.002

10.1109/TII.2018.2819674

10.1109/TIE.2018.2866050

10.1016/j.neucom.2018.09.027

10.1016/j.isatra.2018.04.005

10.1142/9789812797926_0003

koch, 2015, Siamese neural networks for one-shot image recognition, 2, 1

10.1109/TIM.2004.834070

10.1109/M2VIP.2016.7827265

10.1007/978-3-030-01424-7_27

10.1109/TKDE.2009.191

10.1016/j.aei.2004.08.001

lee, 2007, Bearing data set

10.1109/TII.2012.2231084

10.1109/41.873214

10.1109/28.475698

10.1109/41.107100

2018, IEEE PHM 2012 Data Challenge Bearing Dataset

2018, Bearing data

10.1016/j.aca.2012.11.007

nectoux, 2012, PRONOSTIA: An experimental platform for bearings accelerated life test, Proc IEEE Int Conf Prognostics Health Manag, 1

10.1016/j.eswa.2013.06.033

10.1016/j.ymssp.2017.11.024

10.1016/j.ymssp.2018.02.016

10.1016/j.ymssp.2018.05.050

10.1016/j.ymssp.2017.06.012

raghu, 2016, On the expressive power of deep neural networks, arXiv 1606 05336

2018, Case Western Reserve University Bearing Data Center Website

2018, Tesla the worlds most advanced data center GPUs

10.1109/DEMPED.2019.8864915

10.1016/j.asoc.2011.03.014

10.1109/ICPHM.2012.6299511

10.1109/ACCESS.2018.2890693

zhang, 2018, Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition, arXiv 1805 00778

tzeng, 2014, Deep domain confusion: Maximizing for domain invariance, arXiv 1412 3474

10.3390/app9040746

10.23919/ChiCC.2018.8483334

10.1016/j.neucom.2018.07.034

radford, 2015, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv 1511 06434

10.1088/1361-6501/aab945

goodfellow, 2014, Generative adversarial nets, Proc Annu Conf Neural Inf Process Syst (NIPS), 2672

fragkiadaki, 2017, CMU 10703 Course Notes Deep Reinforcement Learning and Control Lecture 14

10.1109/BigData.2017.8258307

10.1109/SDPC.2017.118

10.1109/TIE.2017.2767551

10.1109/JSEN.2017.2727638

10.1109/PHM.2017.8079180

10.1109/TIE.2017.2688963

10.1109/IECON.2016.7793237

10.1109/TIA.2016.2639453

10.1109/TPEL.2014.2358494

zhang, 2005, An integrated approach to bearing fault diagnostics and prognostics, Proc Amer Control Conf, 4, 2750

10.1155/2019/6943234

10.1016/j.measurement.2019.106857

10.1016/j.neucom.2018.09.050

sabour, 2017, Dynamic routing between capsules, Proc Adv Neural Inf Process Syst, 3859

10.1177/1475921718788299

kingma, 2013, Auto-encoding variational Bayes, arXiv 1312 6114

10.1109/TIE.2018.2868023

zhang, 2017, A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, SENSORS, 17, 425, 10.3390/s17020425

10.1109/TIA.1985.349532

10.1109/TIA.2010.2090839

10.1109/TIA.1987.4504880

1985, Report of large motor reliability survey of industrial and commercial installations, Part II, IEEE Trans Ind Appl, ia 22, 865

10.1109/TIE.2018.2877090

harris, 1991, Rolling Bearing Analysis

10.1109/IMTC.2008.4547208

2000, On Recommended Interval of Updating Induction Motors JEMA (in Japanese)

ganin, 2016, Domain-adversarial training of neural networks, J Mach Learn Res, 17, 1

10.1109/TIE.2016.2627020

10.1109/TEC.2014.2341620

10.1109/TIE.2015.2509913

10.1109/INISTA.2014.6873601

10.1109/MLSP.2005.1532891

10.1109/TIE.2014.2327589

10.1109/IECON.2013.6700356

10.1109/ITAIC.2011.6030215

10.1109/TNN.2011.2169087

10.1016/j.isatra.2016.10.014

10.1016/j.ymssp.2017.09.026

10.1109/I2MTC.2018.8409574

10.3390/app7010041

10.1016/j.sigpro.2016.07.028

10.1109/ACCESS.2017.2720965

shen, 2015, Bearing fault diagnosis based on SVD feature extraction and transfer learning classification, Proc Prognostics Syst Health Manage Conf (PHM), 1

10.1109/TIM.2017.2759418

10.1109/JSEN.2018.2866708

10.1016/j.knosys.2017.10.024

10.1109/ACCESS.2017.2675940

10.1109/TIE.2013.2273471

10.1016/j.neucom.2017.07.032

10.1109/JSEN.2017.2726011

10.1109/ACCESS.2018.2880770

10.1016/j.neucom.2018.07.038

10.1109/ACCESS.2017.2717492

10.1561/2200000006

10.1109/ICPHM.2018.8448775

10.1109/TIM.2015.2498978

10.1016/j.asoc.2018.09.037

10.1109/TIE.2016.2519325

10.1109/PHM.2017.8079169

10.1109/TIM.2017.2669947

10.1109/ISIE.2018.8433778

10.1016/j.isatra.2017.03.017

10.1109/TIE.2018.2833025

10.1088/1742-6596/1074/1/012154

10.1109/TIM.2011.2169182

10.1109/TEC.2018.2839083

10.1109/ICIT.2018.8352514

10.1109/TIE.2012.2188259

10.1109/TIE.2017.2745473

10.1109/TIE.2018.2811366

10.1109/TIE.2017.2752151

10.1109/TR.2014.2315956

10.1109/TSMC.2017.2697842

10.1016/j.neucom.2015.07.020

10.1007/s40313-015-0173-7

10.1109/TIM.2013.2245180

10.1016/j.neucom.2017.02.045

10.1109/41.873206

zhou, 2016, Multi-domain description method for bearing fault recognition in varying speed condition, Proc IEEE Ind Electron Soc Annu Conf (IECON), 423

pan, 2018, An improved bearing fault diagnosis method using one-dimensional CNN and LSTM, J Mech Eng, 64, 443

10.1109/63.737588

10.1109/MCSE.2018.110113254

10.1016/j.knosys.2016.10.022

10.1109/TIE.2017.2774777

10.1088/1742-6596/842/1/012045

10.1109/TMECH.2017.2728371

10.1109/JSEN.2018.2830109

10.1016/j.aei.2017.02.005

10.1109/ACCESS.2017.2773460

10.1109/TII.2016.2645238

10.1016/j.apacoust.2014.08.016

10.1016/j.measurement.2016.07.054

10.1049/iet-smt.2014.0228

10.1016/j.jsv.2016.05.027

10.1007/BF00344251

10.1016/j.ymssp.2017.06.022

10.3390/s17081729

zhuang, 2018, Intelligent fault diagnosis of rolling bearing using one-dimensional multi-scale deep convolutional neural network based health state classification, Proc IEEE 15th Int Conf Netw Sens Control (ICNSC), 1

2018, Amazon Mechanical Turk

ng, 2018, CS229 course notes: Deep learning

10.1007/s00170-018-2902-0

10.1016/j.eswa.2018.05.012

10.1109/TIA.2010.2049623

10.1109/TIE.2014.2361317

10.1109/TIE.2015.2463767

10.1109/28.475697

10.1109/TIE.2008.917108

10.1109/TIA.2017.2655008

10.1109/TIM.2017.2674738

10.1109/TMECH.2013.2260865

10.1177/1077546317721844

10.1109/PHM.2017.8079167

yazici, 1995, Adaptive, on line, statistical method and apparatus for motor bearing fault detection by passive motor current monitoring

10.1109/ACCESS.2017.2693379

10.1109/TEC.2003.811739

10.1109/TIE.2011.2167893

10.1016/j.neunet.2014.09.003

10.1109/41.873207

10.1109/TIE.2010.2058072

10.3390/s18113857

10.1109/TIE.2017.2767540

10.1016/j.neucom.2018.03.014

10.1109/TIE.2012.2219838

10.1088/1361-6501/aad101

ballard, 1987, Modular learning in neural networks, Proc AAAI 2nd Nat Conf AI, 279

10.1109/TIE.2012.2192894

10.1016/j.ymssp.2017.03.034

10.1016/j.ymssp.2015.10.025

10.1177/0954406216675896

10.1109/PHM.2017.8079189

10.1109/TII.2017.2755064

10.1109/PHM.2017.8079125

10.20855/ijav.2015.20.4387