Joint learning system based on semi–pseudo–label reliability assessment for weak–fault diagnosis with few labels
•Deep learning method for extracting weak–fault–related features when the labels are insufficient.•Pseudo–label selection mechanism based on reliability assessment.•Joint learning workflow combining the advantages of UL, TL, and SSL.•SSL based on multiple views considering prior knowledge of signal...
Saved in:
| Published in | Mechanical systems and signal processing Vol. 189; p. 110089 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
15.04.2023
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •Deep learning method for extracting weak–fault–related features when the labels are insufficient.•Pseudo–label selection mechanism based on reliability assessment.•Joint learning workflow combining the advantages of UL, TL, and SSL.•SSL based on multiple views considering prior knowledge of signal processing.
Deep neural networks exhibit excellent performance in fault feature extraction for considerable amounts of data. However, data labeling is a difficult task in practical engineering, which may lead to problems in fault diagnosis particularly when faults are weak. To resolve the foregoing, a semi–pseudo–labeling diagnosis system is proposed in this paper. The proposed system considers the confidence and reliability of samples to cope with situations where labels are insufficient and faults are weak. By adding pseudo–labels, unlabeled data whose fault information is swamped by a large amount of noise can achieve low–density separation and entropy regularization in the sample space. Consequently, the training of deep learning models for weak–fault diagnosis is supported. Regarding the traditional pseudo–labeling problems in weak–fault–related feature extraction, a series of solutions has been proposed to solve the problems in the field of fault diagnosis. The designed model reduces pseudo–label noise and enhances the capability of weak–fault–related feature extraction. The effectiveness of this method was validated on the datasets collected by simulating faulty bearings and those sustaining actual failure. |
|---|---|
| AbstractList | •Deep learning method for extracting weak–fault–related features when the labels are insufficient.•Pseudo–label selection mechanism based on reliability assessment.•Joint learning workflow combining the advantages of UL, TL, and SSL.•SSL based on multiple views considering prior knowledge of signal processing.
Deep neural networks exhibit excellent performance in fault feature extraction for considerable amounts of data. However, data labeling is a difficult task in practical engineering, which may lead to problems in fault diagnosis particularly when faults are weak. To resolve the foregoing, a semi–pseudo–labeling diagnosis system is proposed in this paper. The proposed system considers the confidence and reliability of samples to cope with situations where labels are insufficient and faults are weak. By adding pseudo–labels, unlabeled data whose fault information is swamped by a large amount of noise can achieve low–density separation and entropy regularization in the sample space. Consequently, the training of deep learning models for weak–fault diagnosis is supported. Regarding the traditional pseudo–labeling problems in weak–fault–related feature extraction, a series of solutions has been proposed to solve the problems in the field of fault diagnosis. The designed model reduces pseudo–label noise and enhances the capability of weak–fault–related feature extraction. The effectiveness of this method was validated on the datasets collected by simulating faulty bearings and those sustaining actual failure. |
| ArticleNumber | 110089 |
| Author | Zhu, Yong-sheng Kang, Wei Fu, Hong Yan, Ke Guedes Soares, C. Gao, Da-wei Ren, Zhi-jun |
| Author_xml | – sequence: 1 givenname: Da-wei surname: Gao fullname: Gao, Da-wei organization: Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China – sequence: 2 givenname: Yong-sheng surname: Zhu fullname: Zhu, Yong-sheng organization: Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China – sequence: 3 givenname: Ke surname: Yan fullname: Yan, Ke organization: Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China – sequence: 4 givenname: Hong surname: Fu fullname: Fu, Hong email: yszhu@mail.xjtu.edu.cn, hfu@eduhk.hk organization: Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Tai Po, New Territories, Hong Kong – sequence: 5 givenname: Zhi-jun surname: Ren fullname: Ren, Zhi-jun organization: Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China – sequence: 6 givenname: Wei surname: Kang fullname: Kang, Wei organization: Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China – sequence: 7 givenname: C. surname: Guedes Soares fullname: Guedes Soares, C. organization: Centre for Marine Technology and Ocean Engineering (CENTEC), Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal |
| BookMark | eNqFkLFOHDEQQK0IpByEL6DxD-xl7N3b2y0oIhRCIqQ0SW3N2mPwsWufPIbTdfxD_jBfwsKloiDVTDHvSfNOxFFMkYQ4V7BUoNrPm-V-Yt4uNWi9VAqg6z-IhYK-rZRW7ZFYQNd1Va3X8FGcMG8AoG-gXYjHHynEIkfCHEO8lbznQpMckMnJFCXTFP4-_dkyPbg0LyMONMpMY8AhjKHsJTIT80Szxacsd4T3853Hh7FIF_A2Jg4sd6HcSU87-SrgT-LY48h09m-eit9XX39dXlc3P799v_xyU9ka6lJ12Crba9W1q8F57LRdd46A1EqDa2rt2vXKoUbdNs42fdN7BK_8QH7wRE1dn4r-4LU5MWfyxoaCJaRYMobRKDAvAc3GvAY0LwHNIeDM1m_YbQ4T5v1_qIsDNX9Jj4GyYRsoWnIhky3GpfAu_wysLZR3 |
| CitedBy_id | crossref_primary_10_1016_j_aei_2024_103092 crossref_primary_10_1088_1361_6501_ad3668 crossref_primary_10_1002_qre_3314 crossref_primary_10_1007_s13042_024_02199_z crossref_primary_10_1016_j_eswa_2024_126347 crossref_primary_10_3233_IDA_230994 crossref_primary_10_1016_j_inffus_2024_102271 crossref_primary_10_1088_1361_6501_ace644 crossref_primary_10_1016_j_cie_2024_110292 crossref_primary_10_1016_j_aei_2024_102875 crossref_primary_10_1016_j_aei_2024_102897 crossref_primary_10_1016_j_ress_2023_109746 crossref_primary_10_1177_14759217231217936 crossref_primary_10_1088_1361_6501_adbb08 crossref_primary_10_1016_j_ress_2023_109468 crossref_primary_10_1016_j_engappai_2024_107861 crossref_primary_10_1016_j_ress_2024_110393 crossref_primary_10_1177_09544054241266000 crossref_primary_10_1016_j_aei_2025_103140 crossref_primary_10_1016_j_triboint_2023_108497 crossref_primary_10_1016_j_engappai_2024_109845 crossref_primary_10_1109_JSEN_2024_3356605 crossref_primary_10_1016_j_eswa_2023_121817 crossref_primary_10_1109_TETCI_2024_3369999 crossref_primary_10_1016_j_aei_2023_101974 crossref_primary_10_1109_TIM_2024_3453339 crossref_primary_10_1109_TIM_2025_3544384 crossref_primary_10_26599_TST_2024_9010006 crossref_primary_10_1016_j_aei_2023_102040 crossref_primary_10_1016_j_knosys_2024_112216 crossref_primary_10_3390_machines11020187 crossref_primary_10_1016_j_ymssp_2024_112032 |
| Cites_doi | 10.1109/TII.2020.2967822 10.1016/j.measurement.2020.108071 10.1016/j.jsv.2020.115641 10.1016/j.neucom.2018.07.004 10.1109/TIM.2017.2654552 10.1109/CVPR42600.2020.00966 10.1109/TIE.2015.2417501 10.3390/lubricants10010009 10.1016/j.ymssp.2004.09.001 10.1016/j.protcy.2014.08.057 10.1016/j.ymssp.2015.10.025 10.1109/TSMC.2017.2754287 10.1109/TIE.2016.2519325 10.1016/j.ress.2018.02.012 10.1016/j.knosys.2017.10.024 10.1016/j.cirp.2020.04.074 10.1109/CVPR42600.2020.00975 10.1016/S0888-3270(03)00099-2 10.1109/TKDE.2009.191 10.1016/j.neucom.2018.07.034 10.1016/j.compind.2019.05.005 10.1016/j.renene.2019.03.136 10.1016/j.ymssp.2013.03.008 10.1109/ACCESS.2020.2988796 10.1016/j.eswa.2013.01.033 10.1109/TIE.2009.2025288 10.1016/j.patcog.2017.01.035 10.1016/j.ymssp.2019.106608 10.1109/TIE.2017.2762639 10.1016/j.ijhydene.2018.04.163 10.1016/j.neucom.2015.05.076 10.1016/j.inffus.2021.03.008 10.1109/ACCESS.2017.2720965 10.1016/j.ymssp.2010.07.017 10.1016/j.ymssp.2021.108487 10.1109/TIM.2021.3116309 10.1007/s10994-019-05855-6 10.1016/j.knosys.2021.106796 10.1016/j.ymssp.2018.12.051 10.1016/j.ress.2021.107927 10.1016/j.ymssp.2019.05.049 10.1016/j.ress.2018.02.010 10.1201/9781003216582-29 10.1016/j.oceaneng.2021.109261 10.1016/j.knosys.2021.107413 10.1016/j.eswa.2011.02.181 10.1109/ACCESS.2020.2985617 10.1016/j.ymssp.2021.107963 10.1016/j.ress.2018.11.011 10.1109/TII.2020.2991796 10.1016/j.isatra.2019.03.017 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Ltd |
| Copyright_xml | – notice: 2022 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ymssp.2022.110089 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1096-1216 |
| ExternalDocumentID | 10_1016_j_ymssp_2022_110089 S0888327022011578 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABJNI ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DM4 DU5 EBS EFBJH EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG5 LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SPD SST SSV SSZ T5K XPP ZMT ZU3 ~G- 29M AAQXK AATTM AAXKI AAYWO AAYXX ABDPE ABEFU ABFNM ABWVN ABXDB ACNNM ACRPL ACVFH ADCNI ADFGL ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BNPGV CAG CITATION COF EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- RIG SBC SET SSH WUQ |
| ID | FETCH-LOGICAL-c303t-8a61c921865bdfa82c78de0e1520d432d675da2a264dc4949fa0f1fbefbfee433 |
| IEDL.DBID | .~1 |
| ISSN | 0888-3270 |
| IngestDate | Tue Jul 01 04:30:16 EDT 2025 Thu Apr 24 23:01:14 EDT 2025 Fri Feb 23 02:35:32 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Sample reliability Pseudo–label Label noise Weak–fault diagnosis Semi–supervised learning |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c303t-8a61c921865bdfa82c78de0e1520d432d675da2a264dc4949fa0f1fbefbfee433 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_ymssp_2022_110089 crossref_primary_10_1016_j_ymssp_2022_110089 elsevier_sciencedirect_doi_10_1016_j_ymssp_2022_110089 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-04-15 |
| PublicationDateYYYYMMDD | 2023-04-15 |
| PublicationDate_xml | – month: 04 year: 2023 text: 2023-04-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Mechanical systems and signal processing |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Pan, Yang (b0220) 2009; 22 Wang, Gao (b0230) 2020; 69 Lei, Feng, Jing, Xing, Ding (b0200) 2016; 63 Zhao, Zhang, Yu, Sun, Wang, Yan, Chen (b0305) 2021; 70 Pandya, Upadhyay, Harsha (b0210) 2013; 40 Yang, Lei, Jia, Xing (b0240) 2019; 122 Yin, Shu, Liang (b0165) 2017; 67 Yang, Liao, Meng, Lee (b0185) 2011; 38 Li, Zhang, Ding (b0035) 2019; 182 S.R. Saufi, Z.A.B. Ahmad, M.S. Leong, M.H. Lim, Gearbox fault diagnosis using a deep learning model with limited data sample, IEEE Transactions on Industrial Informatics, 16 (2020), 6263-6271. https://doi.org/0.1109/TII.2020.2967822. Qiao, Yan, Tang, Xu (b0090) 2020; 8 Li, Wang, Chyu, Tang (b0050) 2015; 168 Yu, Cheng, Yang (b0190) 2005; 19 Chen, Xu, Wang, Wang (b0115) 2018; 314 Sinaga, Yang (b0125) 2020; 8 K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729–9738. Zhang, Chen, Li, An (b0225) 2020; 165 Gao, Zhu, Ren, Yan, Kang (b0280) 2021; 231 Jia, Lei, Lin, Zhou, Lu (b0110) 2016; 72–73 M. Caron, I. Misra, J. Mairal, P. Goyal, P. Bojanowski, A. Joulin, Unsupervised learning of visual features by contrasting cluster assignments, arXiv preprint arXiv:2006.09882, (2020). Gao, Cecati, Ding (b0195) 2015; 62 Immovilli, Cocconcelli, Bellini, Rubini (b0075) 2009; 56 Liu, Li, Chen, Cao (b0205) 2018; 43 Bhardwaj, U.; Teixeira, A. P., and Guedes Soares, C. Reliability prediction of an offshore wind turbine gearbox. Renewable Energy. 2019; 141:693-706. https://doi.org/10.1016/j.renene.2019.03.136. Zhang, Tang, Deng, Tan, Yu (b0100) 2021; 161 Shao, Li, Xia, Zhang, Shen, Williams, Kennedy, de Silva (b0070) 2021; 70 Zhang, Tang, Qin, Deng (b0265) 2019; 131 Zhang, Tao, Wu, Guan (b0245) 2017; 5 Zhao, Kang, Tang, Pecht (b0105) 2018; 65 Pham, Dai, Xie, Le (b0175) 2021 Shah, Patel (b0045) 2014; 14 Randall, Antoni (b0055) 2011; 25 Xiang, Qin, Luo, Pu, Tang (b0040) 2021; 216 Wen, Gao, Li (b0250) 2019; 49 R. Li, Q. Jiao, W. Cao, H. Wong, S. Wu, Model adaptation: Unsupervised domain adaptation without source data, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9641–9650. Lee (b0285) 2013 Ren, Zhu, Yan, Chen, Kang, Yue, Gao (b0315) 2020; 138 Case Western Reserve University Bearing Data Center Website (http:// csegroups.case.edu/bearingdatacenter/home). Ge, Chen, Li (b0170) 2020 Shao, Lin, Zhang, Galar, Kumarb (b0005) 2021; 74 Liu, Zhou, Xu, Zheng, Peng, Jiang (b0270) 2018; 315 Cheng, Lin, Wu, Zhu, Shao (b0295) 2021; 216 Li, Huang, Li, Liao, Chen, He, Yan, Gryllias (b0160) 2022; 167 Lee (b0275) 2013; 3 K. Sohn, D. Berthelot, C. Li, Z. Zhang, N. Carlini, E.D. Cubuk, A. Kurakin, H. Zhang, C. Raffel, Fixmatch: Simplifying semi–supervised learning with consistency and confidence, arXiv preprint arXiv:2001.07685, (2020). Zhang, Huang, Chu, Cui (b0010) 2020; 488 He, Zhang, Ren, Sun (b0290) 2016 J. Liang, D. Hu, J. Feng, Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation, International Conference on Machine Learning, PMLR, 2020, pp. 6028–6039. Lin (b0300) 1999; 33 Jiao, Zhao, Lin, Liang (b0065) 2019; 184 Jin, Liu (b0255) 2013; 38 Ma, Zhang, Yan, Zhu, Hong (b0015) 2022; 10 Shao, Jiang, Li, Wu (b0215) 2018; 140 Li, Yang, Pan, Cheng, Cheng (b0120) 2019; 110 Van Engelen, Hoos (b0145) 2020; 109 Yan, Zhou, Pang (b0260) 2017; 66 A. Rege, C. Monteleoni. Evaluating the distribution learning capabilities of GANs. arXiv preprint arXiv:1907.02662, 2019. Han, Liu, Yang, Jiang (b0235) 2019; 93 Li, Díaz, Guedes Soares (b0020) 2021; 234 Sobral, J. and Guedes Soares, C. Reliability analysis of critical systems installed in ships based on degradation mechanisms. Guedes Soares, C. & Santos T. A., (Eds.). Developments in Maritime Technology and Engineering . London, UK: Taylor and Francis; 2021; pp. Vol 1, pp. 261-268. Ma, Mao (b0095) 2020; 17 Manjurul Islam, Kim (b0060) 2019; 184 Antoni (b0080) 2006; 20 10.1016/j.ymssp.2022.110089_b0135 Zhang (10.1016/j.ymssp.2022.110089_b0265) 2019; 131 Liu (10.1016/j.ymssp.2022.110089_b0205) 2018; 43 10.1016/j.ymssp.2022.110089_b0130 Qiao (10.1016/j.ymssp.2022.110089_b0090) 2020; 8 Immovilli (10.1016/j.ymssp.2022.110089_b0075) 2009; 56 Han (10.1016/j.ymssp.2022.110089_b0235) 2019; 93 Shao (10.1016/j.ymssp.2022.110089_b0005) 2021; 74 Lin (10.1016/j.ymssp.2022.110089_b0300) 1999; 33 Pandya (10.1016/j.ymssp.2022.110089_b0210) 2013; 40 He (10.1016/j.ymssp.2022.110089_b0290) 2016 Cheng (10.1016/j.ymssp.2022.110089_b0295) 2021; 216 Ge (10.1016/j.ymssp.2022.110089_b0170) 2020 Ren (10.1016/j.ymssp.2022.110089_b0315) 2020; 138 Zhang (10.1016/j.ymssp.2022.110089_b0245) 2017; 5 Liu (10.1016/j.ymssp.2022.110089_b0270) 2018; 315 Yang (10.1016/j.ymssp.2022.110089_b0185) 2011; 38 10.1016/j.ymssp.2022.110089_b0140 10.1016/j.ymssp.2022.110089_b0180 10.1016/j.ymssp.2022.110089_b0025 Li (10.1016/j.ymssp.2022.110089_b0120) 2019; 110 Randall (10.1016/j.ymssp.2022.110089_b0055) 2011; 25 Van Engelen (10.1016/j.ymssp.2022.110089_b0145) 2020; 109 Li (10.1016/j.ymssp.2022.110089_b0020) 2021; 234 Zhang (10.1016/j.ymssp.2022.110089_b0100) 2021; 161 Gao (10.1016/j.ymssp.2022.110089_b0195) 2015; 62 Yu (10.1016/j.ymssp.2022.110089_b0190) 2005; 19 Zhang (10.1016/j.ymssp.2022.110089_b0225) 2020; 165 10.1016/j.ymssp.2022.110089_b0030 10.1016/j.ymssp.2022.110089_b0150 Lei (10.1016/j.ymssp.2022.110089_b0200) 2016; 63 Shao (10.1016/j.ymssp.2022.110089_b0215) 2018; 140 Yang (10.1016/j.ymssp.2022.110089_b0240) 2019; 122 Wen (10.1016/j.ymssp.2022.110089_b0250) 2019; 49 10.1016/j.ymssp.2022.110089_b0310 Xiang (10.1016/j.ymssp.2022.110089_b0040) 2021; 216 Manjurul Islam (10.1016/j.ymssp.2022.110089_b0060) 2019; 184 10.1016/j.ymssp.2022.110089_b0155 Shah (10.1016/j.ymssp.2022.110089_b0045) 2014; 14 Ma (10.1016/j.ymssp.2022.110089_b0095) 2020; 17 Jin (10.1016/j.ymssp.2022.110089_b0255) 2013; 38 Chen (10.1016/j.ymssp.2022.110089_b0115) 2018; 314 Li (10.1016/j.ymssp.2022.110089_b0160) 2022; 167 Jiao (10.1016/j.ymssp.2022.110089_b0065) 2019; 184 Yan (10.1016/j.ymssp.2022.110089_b0260) 2017; 66 Yin (10.1016/j.ymssp.2022.110089_b0165) 2017; 67 Ma (10.1016/j.ymssp.2022.110089_b0015) 2022; 10 Wang (10.1016/j.ymssp.2022.110089_b0230) 2020; 69 Li (10.1016/j.ymssp.2022.110089_b0050) 2015; 168 10.1016/j.ymssp.2022.110089_b0085 Gao (10.1016/j.ymssp.2022.110089_b0280) 2021; 231 Jia (10.1016/j.ymssp.2022.110089_b0110) 2016; 72–73 Shao (10.1016/j.ymssp.2022.110089_b0070) 2021; 70 Pan (10.1016/j.ymssp.2022.110089_b0220) 2009; 22 Li (10.1016/j.ymssp.2022.110089_b0035) 2019; 182 Zhang (10.1016/j.ymssp.2022.110089_b0010) 2020; 488 Sinaga (10.1016/j.ymssp.2022.110089_b0125) 2020; 8 Zhao (10.1016/j.ymssp.2022.110089_b0305) 2021; 70 Zhao (10.1016/j.ymssp.2022.110089_b0105) 2018; 65 Lee (10.1016/j.ymssp.2022.110089_b0275) 2013; 3 Pham (10.1016/j.ymssp.2022.110089_b0175) 2021 Antoni (10.1016/j.ymssp.2022.110089_b0080) 2006; 20 Lee (10.1016/j.ymssp.2022.110089_b0285) 2013 |
| References_xml | – volume: 216 year: 2021 ident: b0040 article-title: Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction publication-title: Reliab. Eng. Syst. Saf. – reference: M. Caron, I. Misra, J. Mairal, P. Goyal, P. Bojanowski, A. Joulin, Unsupervised learning of visual features by contrasting cluster assignments, arXiv preprint arXiv:2006.09882, (2020). – reference: K. Sohn, D. Berthelot, C. Li, Z. Zhang, N. Carlini, E.D. Cubuk, A. Kurakin, H. Zhang, C. Raffel, Fixmatch: Simplifying semi–supervised learning with consistency and confidence, arXiv preprint arXiv:2001.07685, (2020). – volume: 109 start-page: 373 year: 2020 end-page: 440 ident: b0145 article-title: A survey on semi–supervised learning publication-title: Mach. Learn. – reference: Sobral, J. and Guedes Soares, C. Reliability analysis of critical systems installed in ships based on degradation mechanisms. Guedes Soares, C. & Santos T. A., (Eds.). Developments in Maritime Technology and Engineering . London, UK: Taylor and Francis; 2021; pp. Vol 1, pp. 261-268. – volume: 43 start-page: 12428 year: 2018 end-page: 12441 ident: b0205 article-title: A discrete hidden Markov model fault diagnosis strategy based on K-means clustering dedicated to PEM fuel cell systems of tramways publication-title: Int. J. Hydrogen Energy – volume: 8 start-page: 66257 year: 2020 end-page: 66269 ident: b0090 article-title: Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads publication-title: IEEE Access – reference: R. Li, Q. Jiao, W. Cao, H. Wong, S. Wu, Model adaptation: Unsupervised domain adaptation without source data, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9641–9650. – reference: Bhardwaj, U.; Teixeira, A. P., and Guedes Soares, C. Reliability prediction of an offshore wind turbine gearbox. Renewable Energy. 2019; 141:693-706. https://doi.org/10.1016/j.renene.2019.03.136. – volume: 38 start-page: 615 year: 2013 end-page: 627 ident: b0255 article-title: Semi–supervised learning and condition fusion for fault diagnosis publication-title: Mech. Syst. Sig. Process. – year: 2021 ident: b0175 article-title: Meta pseudo labels publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 167 start-page: 108487 year: 2022 ident: b0160 article-title: A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges publication-title: Mech. Syst. Sig. Process. – volume: 66 start-page: 723 year: 2017 end-page: 733 ident: b0260 article-title: Gaussian mixture model using semisupervised learning for probabilistic fault diagnosis under new data categories publication-title: IEEE Trans. Instrum. Meas. – volume: 110 start-page: 36 year: 2019 end-page: 47 ident: b0120 article-title: A novel deep stacking least squares support vector machine for rolling bearing fault diagnosis publication-title: Comput. Ind. – volume: 67 start-page: 313 year: 2017 end-page: 327 ident: b0165 article-title: Unified subspace learning for incomplete and unlabelled multi–view data publication-title: Pattern Recogn. – volume: 72–73 start-page: 303 year: 2016 end-page: 315 ident: b0110 article-title: Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data publication-title: Mech. Syst. Sig. Process. – reference: A. Rege, C. Monteleoni. Evaluating the distribution learning capabilities of GANs. arXiv preprint arXiv:1907.02662, 2019. – volume: 56 start-page: 4710 year: 2009 end-page: 4717 ident: b0075 article-title: Detection of generalized-roughness bearing fault by spectral-kurtosis energy of vibration or current signals publication-title: IEEE Trans. Ind. Electron. – volume: 161 year: 2021 ident: b0100 article-title: A fault diagnosis method for wind turbines gearbox based on adaptive loss weighted meta-ResNet under noisy labels publication-title: Mech. Syst. Sig. Process. – volume: 5 start-page: 14347 year: 2017 end-page: 14357 ident: b0245 article-title: Transfer learning with neural networks for bearing fault diagnosis in changing working conditions publication-title: IEEE Access – volume: 140 start-page: 1 year: 2018 end-page: 14 ident: b0215 article-title: Intelligent fault diagnosis of rolling bearing using deep wavelet auto–encoder with extreme learning machine publication-title: Knowl.-Based Syst. – year: 2020 ident: b0170 article-title: Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 122 start-page: 692 year: 2019 end-page: 706 ident: b0240 article-title: An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings publication-title: Mech. Syst. Sig. Process. – volume: 49 start-page: 136 year: 2019 end-page: 144 ident: b0250 article-title: A new deep transfer learning based on sparse auto-encoder for fault diagnosis publication-title: IEEE Trans. Syst. Man Cyber. Syst. – year: 2013 ident: b0285 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks publication-title: ICML 2013 Workshop : Challenges in Representation Learning (WREPL) – volume: 234 year: 2021 ident: b0020 article-title: A failure analysis of floating offshore wind turbines using AHP-FMEA methodology publication-title: Ocean Eng. – volume: 14 start-page: 447 year: 2014 end-page: 456 ident: b0045 article-title: A review of dynamic modeling and fault identifications methods for rolling element bearing publication-title: Proc. Technol. – volume: 74 start-page: 65 year: 2021 end-page: 76 ident: b0005 article-title: A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance publication-title: Inform. Fusion – reference: S.R. Saufi, Z.A.B. Ahmad, M.S. Leong, M.H. Lim, Gearbox fault diagnosis using a deep learning model with limited data sample, IEEE Transactions on Industrial Informatics, 16 (2020), 6263-6271. https://doi.org/0.1109/TII.2020.2967822. – volume: 184 start-page: 55 year: 2019 end-page: 66 ident: b0060 article-title: Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector machines publication-title: Reliab. Eng. Syst. Saf. – volume: 70 start-page: 1 year: 2021 end-page: 11 ident: b0070 article-title: Fault diagnosis of a rotor-bearing system under variable rotating speeds using two-stage parameter transfer and infrared thermal images publication-title: IEEE Trans. Instrum. Meas. – volume: 131 start-page: 243 year: 2019 end-page: 260 ident: b0265 article-title: Fault diagnosis of planetary gearbox using a novel semi–supervised method of multiple association layers networks publication-title: Mech. Syst. Sig. Process. – volume: 40 start-page: 4137 year: 2013 end-page: 4145 ident: b0210 article-title: Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN publication-title: Expert Syst. Appl. – volume: 25 start-page: 485 year: 2011 end-page: 520 ident: b0055 article-title: Rolling element bearing diagnostics—a tutorial publication-title: Mech. Syst. Sig. Process. – volume: 165 year: 2020 ident: b0225 article-title: Unsupervised domain adaptation via enhanced transfer joint matching for bearing fault diagnosis publication-title: Measurement – reference: Case Western Reserve University Bearing Data Center Website (http:// csegroups.case.edu/bearingdatacenter/home). – volume: 17 start-page: 1658 year: 2020 end-page: 1667 ident: b0095 article-title: Deep-convolution-based LSTM network for remaining useful life prediction publication-title: IEEE Trans. Ind. Inf. – volume: 20 start-page: 282 year: 2006 end-page: 307 ident: b0080 article-title: The spectral kurtosis: a useful tool for characterising non-stationary signals publication-title: Mech. Syst. Sig. Process. – volume: 182 start-page: 208 year: 2019 end-page: 218 ident: b0035 article-title: Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction publication-title: Reliab. Eng. Syst. Saf. – volume: 314 start-page: 445 year: 2018 end-page: 457 ident: b0115 article-title: Detection of weak transient signals based on unsupervised learning for bearing fault diagnosis publication-title: Neurocomputing – volume: 22 start-page: 1345 year: 2009 end-page: 1359 ident: b0220 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. – volume: 231 year: 2021 ident: b0280 article-title: A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity publication-title: Knowl.-Based Syst. – volume: 93 start-page: 341 year: 2019 end-page: 353 ident: b0235 article-title: Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions publication-title: ISA Trans. – volume: 216 year: 2021 ident: b0295 article-title: Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network publication-title: Knowl.-Based Syst. – reference: K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729–9738. – volume: 70 start-page: 3525828 year: 2021 ident: b0305 article-title: Applications of unsupervised deep transfer learning to intelligent fault diagnosis: a survey and comparative study publication-title: IEEE Trans. Instrum. Meas. – volume: 488 year: 2020 ident: b0010 article-title: Mechanism and method for the full-scale quantitative diagnosis of ball bearings with an inner race Fault publication-title: J. Sound Vib. – volume: 65 start-page: 4290 year: 2018 end-page: 4300 ident: b0105 article-title: Deep residual networks with dynamically weighted wavelet coefficients for fault diagnosis of planetary gearboxes publication-title: IEEE Trans. Ind. Electron. – volume: 8 start-page: 80716 year: 2020 end-page: 80727 ident: b0125 article-title: Unsupervised K–means clustering algorithm publication-title: IEEE Access – volume: 19 start-page: 259 year: 2005 end-page: 270 ident: b0190 article-title: Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings publication-title: Mech. Syst. Sig. Process. – volume: 62 start-page: 3757 year: 2015 end-page: 3767 ident: b0195 article-title: A survey of fault diagnosis and fault-tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches publication-title: IEEE Trans. Ind. Electron. – volume: 315 start-page: 412 year: 2018 end-page: 424 ident: b0270 article-title: Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks publication-title: Neurocomputing – volume: 138 year: 2020 ident: b0315 article-title: A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis publication-title: Mech. Syst. Sig. Process. – volume: 33 start-page: 108 year: 1999 end-page: 110 ident: b0300 article-title: Coutinuous wavelet transform and its application for bearing diagnosis publication-title: J. Xi'an Jiaotong Univ. – volume: 38 start-page: 11311 year: 2011 end-page: 11320 ident: b0185 article-title: A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis publication-title: Expert Syst. Appl. – volume: 3 start-page: 896 year: 2013 ident: b0275 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks publication-title: Workshop on challenges in representation learning, ICML – volume: 63 start-page: 3137 year: 2016 end-page: 3147 ident: b0200 article-title: An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data publication-title: IEEE Trans. Ind. Electron. – volume: 184 start-page: 41 year: 2019 end-page: 54 ident: b0065 article-title: Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings publication-title: Reliab. Eng. Syst. Saf. – volume: 10 start-page: 9 year: 2022 ident: b0015 article-title: A study on bearing dynamic features under the condition of multiball-cage collision publication-title: Lubricants – start-page: 770 year: 2016 end-page: 778 ident: b0290 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 168 start-page: 505 year: 2015 end-page: 519 ident: b0050 article-title: Weak fault diagnosis of rotating machinery based on feature reduction with Supervised Orthogonal Local Fisher Discriminant Analysis publication-title: Neurocomputing – reference: J. Liang, D. Hu, J. Feng, Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation, International Conference on Machine Learning, PMLR, 2020, pp. 6028–6039. – volume: 69 start-page: 413 year: 2020 end-page: 416 ident: b0230 article-title: Transfer learning for enhanced machine fault diagnosis in manufacturing publication-title: CIRP Ann. – ident: 10.1016/j.ymssp.2022.110089_b0085 doi: 10.1109/TII.2020.2967822 – volume: 165 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0225 article-title: Unsupervised domain adaptation via enhanced transfer joint matching for bearing fault diagnosis publication-title: Measurement doi: 10.1016/j.measurement.2020.108071 – volume: 488 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0010 article-title: Mechanism and method for the full-scale quantitative diagnosis of ball bearings with an inner race Fault publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2020.115641 – volume: 314 start-page: 445 year: 2018 ident: 10.1016/j.ymssp.2022.110089_b0115 article-title: Detection of weak transient signals based on unsupervised learning for bearing fault diagnosis publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.07.004 – volume: 66 start-page: 723 year: 2017 ident: 10.1016/j.ymssp.2022.110089_b0260 article-title: Gaussian mixture model using semisupervised learning for probabilistic fault diagnosis under new data categories publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2654552 – ident: 10.1016/j.ymssp.2022.110089_b0140 doi: 10.1109/CVPR42600.2020.00966 – volume: 62 start-page: 3757 year: 2015 ident: 10.1016/j.ymssp.2022.110089_b0195 article-title: A survey of fault diagnosis and fault-tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2015.2417501 – volume: 10 start-page: 9 year: 2022 ident: 10.1016/j.ymssp.2022.110089_b0015 article-title: A study on bearing dynamic features under the condition of multiball-cage collision publication-title: Lubricants doi: 10.3390/lubricants10010009 – volume: 20 start-page: 282 year: 2006 ident: 10.1016/j.ymssp.2022.110089_b0080 article-title: The spectral kurtosis: a useful tool for characterising non-stationary signals publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2004.09.001 – volume: 14 start-page: 447 year: 2014 ident: 10.1016/j.ymssp.2022.110089_b0045 article-title: A review of dynamic modeling and fault identifications methods for rolling element bearing publication-title: Proc. Technol. doi: 10.1016/j.protcy.2014.08.057 – volume: 72–73 start-page: 303 year: 2016 ident: 10.1016/j.ymssp.2022.110089_b0110 article-title: Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2015.10.025 – volume: 49 start-page: 136 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0250 article-title: A new deep transfer learning based on sparse auto-encoder for fault diagnosis publication-title: IEEE Trans. Syst. Man Cyber. Syst. doi: 10.1109/TSMC.2017.2754287 – volume: 63 start-page: 3137 year: 2016 ident: 10.1016/j.ymssp.2022.110089_b0200 article-title: An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2016.2519325 – volume: 184 start-page: 55 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0060 article-title: Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector machines publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2018.02.012 – ident: 10.1016/j.ymssp.2022.110089_b0180 – volume: 140 start-page: 1 year: 2018 ident: 10.1016/j.ymssp.2022.110089_b0215 article-title: Intelligent fault diagnosis of rolling bearing using deep wavelet auto–encoder with extreme learning machine publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2017.10.024 – volume: 69 start-page: 413 issue: 1 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0230 article-title: Transfer learning for enhanced machine fault diagnosis in manufacturing publication-title: CIRP Ann. doi: 10.1016/j.cirp.2020.04.074 – start-page: 770 year: 2016 ident: 10.1016/j.ymssp.2022.110089_b0290 article-title: Deep residual learning for image recognition – ident: 10.1016/j.ymssp.2022.110089_b0130 doi: 10.1109/CVPR42600.2020.00975 – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0070 article-title: Fault diagnosis of a rotor-bearing system under variable rotating speeds using two-stage parameter transfer and infrared thermal images publication-title: IEEE Trans. Instrum. Meas. – volume: 19 start-page: 259 year: 2005 ident: 10.1016/j.ymssp.2022.110089_b0190 article-title: Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings publication-title: Mech. Syst. Sig. Process. doi: 10.1016/S0888-3270(03)00099-2 – volume: 22 start-page: 1345 year: 2009 ident: 10.1016/j.ymssp.2022.110089_b0220 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2009.191 – volume: 315 start-page: 412 year: 2018 ident: 10.1016/j.ymssp.2022.110089_b0270 article-title: Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.07.034 – volume: 110 start-page: 36 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0120 article-title: A novel deep stacking least squares support vector machine for rolling bearing fault diagnosis publication-title: Comput. Ind. doi: 10.1016/j.compind.2019.05.005 – ident: 10.1016/j.ymssp.2022.110089_b0025 doi: 10.1016/j.renene.2019.03.136 – volume: 38 start-page: 615 year: 2013 ident: 10.1016/j.ymssp.2022.110089_b0255 article-title: Semi–supervised learning and condition fusion for fault diagnosis publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2013.03.008 – volume: 8 start-page: 80716 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0125 article-title: Unsupervised K–means clustering algorithm publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2988796 – volume: 3 start-page: 896 year: 2013 ident: 10.1016/j.ymssp.2022.110089_b0275 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks publication-title: Workshop on challenges in representation learning, ICML – volume: 40 start-page: 4137 year: 2013 ident: 10.1016/j.ymssp.2022.110089_b0210 article-title: Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2013.01.033 – volume: 56 start-page: 4710 year: 2009 ident: 10.1016/j.ymssp.2022.110089_b0075 article-title: Detection of generalized-roughness bearing fault by spectral-kurtosis energy of vibration or current signals publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2009.2025288 – year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0170 article-title: Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification – volume: 67 start-page: 313 year: 2017 ident: 10.1016/j.ymssp.2022.110089_b0165 article-title: Unified subspace learning for incomplete and unlabelled multi–view data publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2017.01.035 – volume: 138 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0315 article-title: A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2019.106608 – volume: 65 start-page: 4290 year: 2018 ident: 10.1016/j.ymssp.2022.110089_b0105 article-title: Deep residual networks with dynamically weighted wavelet coefficients for fault diagnosis of planetary gearboxes publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2762639 – volume: 43 start-page: 12428 year: 2018 ident: 10.1016/j.ymssp.2022.110089_b0205 article-title: A discrete hidden Markov model fault diagnosis strategy based on K-means clustering dedicated to PEM fuel cell systems of tramways publication-title: Int. J. Hydrogen Energy doi: 10.1016/j.ijhydene.2018.04.163 – volume: 168 start-page: 505 year: 2015 ident: 10.1016/j.ymssp.2022.110089_b0050 article-title: Weak fault diagnosis of rotating machinery based on feature reduction with Supervised Orthogonal Local Fisher Discriminant Analysis publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.05.076 – volume: 74 start-page: 65 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0005 article-title: A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance publication-title: Inform. Fusion doi: 10.1016/j.inffus.2021.03.008 – volume: 5 start-page: 14347 year: 2017 ident: 10.1016/j.ymssp.2022.110089_b0245 article-title: Transfer learning with neural networks for bearing fault diagnosis in changing working conditions publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2720965 – volume: 25 start-page: 485 year: 2011 ident: 10.1016/j.ymssp.2022.110089_b0055 article-title: Rolling element bearing diagnostics—a tutorial publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2010.07.017 – ident: 10.1016/j.ymssp.2022.110089_b0150 – volume: 167 start-page: 108487 year: 2022 ident: 10.1016/j.ymssp.2022.110089_b0160 article-title: A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2021.108487 – volume: 70 start-page: 3525828 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0305 article-title: Applications of unsupervised deep transfer learning to intelligent fault diagnosis: a survey and comparative study publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2021.3116309 – volume: 109 start-page: 373 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0145 article-title: A survey on semi–supervised learning publication-title: Mach. Learn. doi: 10.1007/s10994-019-05855-6 – volume: 216 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0295 article-title: Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2021.106796 – volume: 122 start-page: 692 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0240 article-title: An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2018.12.051 – volume: 216 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0040 article-title: Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2021.107927 – volume: 131 start-page: 243 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0265 article-title: Fault diagnosis of planetary gearbox using a novel semi–supervised method of multiple association layers networks publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2019.05.049 – volume: 184 start-page: 41 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0065 article-title: Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2018.02.010 – year: 2013 ident: 10.1016/j.ymssp.2022.110089_b0285 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks – ident: 10.1016/j.ymssp.2022.110089_b0030 doi: 10.1201/9781003216582-29 – year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0175 article-title: Meta pseudo labels – ident: 10.1016/j.ymssp.2022.110089_b0310 – volume: 33 start-page: 108 issue: 11 year: 1999 ident: 10.1016/j.ymssp.2022.110089_b0300 article-title: Coutinuous wavelet transform and its application for bearing diagnosis publication-title: J. Xi'an Jiaotong Univ. – volume: 234 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0020 article-title: A failure analysis of floating offshore wind turbines using AHP-FMEA methodology publication-title: Ocean Eng. doi: 10.1016/j.oceaneng.2021.109261 – volume: 231 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0280 article-title: A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2021.107413 – volume: 38 start-page: 11311 year: 2011 ident: 10.1016/j.ymssp.2022.110089_b0185 article-title: A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2011.02.181 – volume: 8 start-page: 66257 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0090 article-title: Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2985617 – volume: 161 year: 2021 ident: 10.1016/j.ymssp.2022.110089_b0100 article-title: A fault diagnosis method for wind turbines gearbox based on adaptive loss weighted meta-ResNet under noisy labels publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2021.107963 – ident: 10.1016/j.ymssp.2022.110089_b0155 – volume: 182 start-page: 208 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0035 article-title: Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2018.11.011 – ident: 10.1016/j.ymssp.2022.110089_b0135 – volume: 17 start-page: 1658 year: 2020 ident: 10.1016/j.ymssp.2022.110089_b0095 article-title: Deep-convolution-based LSTM network for remaining useful life prediction publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2020.2991796 – volume: 93 start-page: 341 year: 2019 ident: 10.1016/j.ymssp.2022.110089_b0235 article-title: Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions publication-title: ISA Trans. doi: 10.1016/j.isatra.2019.03.017 |
| SSID | ssj0009406 |
| Score | 2.542398 |
| Snippet | •Deep learning method for extracting weak–fault–related features when the labels are insufficient.•Pseudo–label selection mechanism based on reliability... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 110089 |
| SubjectTerms | Label noise Pseudo–label Sample reliability Semi–supervised learning Weak–fault diagnosis |
| Title | Joint learning system based on semi–pseudo–label reliability assessment for weak–fault diagnosis with few labels |
| URI | https://dx.doi.org/10.1016/j.ymssp.2022.110089 |
| Volume | 189 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF6KXvQgPvFZ9uDR2CS7TbLHUiy1ohcVvIV9SrQmpUkVL-J_8B_6S9zJoypID95CmAlhZjIzSWa-D6FjGzM6dD3pCCFChwaB7zAlqcOIJIGgkqkSu_PyKhje0tFd966F-s0uDIxV1rm_yulltq7PdGprdiZJ0rm2z4cNxxBWRQExBhZ-KQ0hyk_fvsc8GC35NUHYAekGeaic8Xp9ynMArfR9GId3gev9r-r0o-IM1tFa3SriXnU3G6il0020-gNAcAs9j7IkLXBN_XCPK1xmDKVJ4SzFuX5KPt8_JrmeqcweWJfrMZ7qcVLBc79iPkfmxLZ9xS-aP1o5w2fjAqtqDC_JMXytxUa_4PIC-Ta6HZzd9IdOzaTgSFuiCifigScZ0E91hTI88mUYKe1qW7xdRYmv7GuD4j633ZF1FKPMcNd4RmgjjNaUkB20lGap3kVYMJdJYOfwte0MPMJJFDKXEBOZIJAh2UN-Y8FY1jDjwHYxjpt5soe4NHsMZo8rs--hk7nSpELZWCweNK6JfwVLbOvAIsX9_yoeoBXgmYffSF73EC0V05k-st1IIdpluLXRcu_8Ynj1BS-m5Ac |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NbtQwELaqcigcEBQQpUB9gBthE8ebxAcOFbTa_l5opd6Cf8ZVYJtdNdmu9oJ4hz4Kb8STMJOftkhVD0i9RZEdOePJzMT-_H2MvUOfgTSMbGCMSQOZJCJQzspAxTZOjLTKNdydB4fJ6FjungxPltjv_iwMwSq72N_G9CZad3cGnTUH06IYfMXvA90xpaOixBiTdcjKPVjM8b-t-rTzBSf5vRDbW0efR0EnLRBYjNl1kOkksor0mIbGeZ0Jm2YOQsBsFjoZC4d1tNNCY7mAI1dSeR36yBvwxgNIWgXFuP9AYrgg2YSPP69xJUo2gp40uoCG11MdNaCyxVlVEUumEIS_D0lc_rZ0eCPFbT9hj7valG-2r_-ULUG5yh7dYCx8xi52J0VZ805r4pS3RNCccqHjk5JXcFb8-XU5rWDmJniBPgZjfg7jouUDX3B9RQXKsV7mc9A_sJ3Xs3HNXYv7KypOy8Pcw5w3D6ies-N7se8LtlxOSnjJuFGhsiQHIgBLkSjWcZaqMI595pPEpvEaE70Fc9vxmpO8xjjvAWzf88bsOZk9b82-xj5cdZq2tB53N0_6qcn_8c4cE89dHV_9b8cNtjI6OtjP93cO99bZQxK5pz2saPiaLdfnM3iDpVBt3jaux9m3-_b1v-RvIOw |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Joint+learning+system+based+on+semi%E2%80%93pseudo%E2%80%93label+reliability+assessment+for+weak%E2%80%93fault+diagnosis+with+few+labels&rft.jtitle=Mechanical+systems+and+signal+processing&rft.au=Gao%2C+Da-wei&rft.au=Zhu%2C+Yong-sheng&rft.au=Yan%2C+Ke&rft.au=Fu%2C+Hong&rft.date=2023-04-15&rft.pub=Elsevier+Ltd&rft.issn=0888-3270&rft.eissn=1096-1216&rft.volume=189&rft_id=info:doi/10.1016%2Fj.ymssp.2022.110089&rft.externalDocID=S0888327022011578 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0888-3270&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0888-3270&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0888-3270&client=summon |