Model-driven deep unrolling: Towards interpretable deep learning against noise attacks for intelligent fault diagnosis
Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the “black box” nature of DL-based methods still seriously hinders wide applications in industry, especially in aero-engine IFD, and how to inter...
Saved in:
Published in | ISA transactions Vol. 129; pp. 644 - 662 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
Elsevier Ltd
01.10.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the “black box” nature of DL-based methods still seriously hinders wide applications in industry, especially in aero-engine IFD, and how to interpret the learned features is still a challenging problem. Furthermore, IFD based on vibration signals is often affected by the heavy noise, leading to a big drop in accuracy. To address these two problems, we develop a model-driven deep unrolling method to achieve ante-hoc interpretability, whose core is to unroll a corresponding optimization algorithm of a predefined model into a neural network, which is naturally interpretable and robust to noise attacks. Motivated by the recent multi-layer sparse coding (ML-SC) model, we herein propose to solve a general sparse coding (GSC) problem across different layers and deduce the corresponding layered GSC (LGSC) algorithm. Based on the ideology of deep unrolling, the proposed algorithm is unfolded into LGSC-Net, whose relationship with the convolutional neural network (CNN) is also discussed in depth. The effectiveness of the proposed model is verified by an aero-engine bevel gear fault experiment and a helical gear fault experiment with three kinds of adversarial noise attacks. The interpretability is also discussed from the perspective of the core of model-driven deep unrolling and its inductive reconstruction property.
•A model-driven deep unrolling method is developed to design interpretable DL models.•GSC is solved gradually and its inducing optimization algorithm is unrolled into the LGSC-Net.•The interpretability is discussed from the perspective of the core of model-driven deep unrolling.•Experiments are performed to verify the diagnosis ability via adding adversarial noise attacks. |
---|---|
AbstractList | Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the “black box” nature of DL-based methods still seriously hinders wide applications in industry, especially in aero-engine IFD, and how to interpret the learned features is still a challenging problem. Furthermore, IFD based on vibration signals is often affected by the heavy noise, leading to a big drop in accuracy. To address these two problems, we develop a model-driven deep unrolling method to achieve ante-hoc interpretability, whose core is to unroll a corresponding optimization algorithm of a predefined model into a neural network, which is naturally interpretable and robust to noise attacks. Motivated by the recent multi-layer sparse coding (ML-SC) model, we herein propose to solve a general sparse coding (GSC) problem across different layers and deduce the corresponding layered GSC (LGSC) algorithm. Based on the ideology of deep unrolling, the proposed algorithm is unfolded into LGSC-Net, whose relationship with the convolutional neural network (CNN) is also discussed in depth. The effectiveness of the proposed model is verified by an aero-engine bevel gear fault experiment and a helical gear fault experiment with three kinds of adversarial noise attacks. The interpretability is also discussed from the perspective of the core of model-driven deep unrolling and its inductive reconstruction property.
•A model-driven deep unrolling method is developed to design interpretable DL models.•GSC is solved gradually and its inducing optimization algorithm is unrolled into the LGSC-Net.•The interpretability is discussed from the perspective of the core of model-driven deep unrolling.•Experiments are performed to verify the diagnosis ability via adding adversarial noise attacks. Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the "black box" nature of DL-based methods still seriously hinders wide applications in industry, especially in aero-engine IFD, and how to interpret the learned features is still a challenging problem. Furthermore, IFD based on vibration signals is often affected by the heavy noise, leading to a big drop in accuracy. To address these two problems, we develop a model-driven deep unrolling method to achieve ante-hoc interpretability, whose core is to unroll a corresponding optimization algorithm of a predefined model into a neural network, which is naturally interpretable and robust to noise attacks. Motivated by the recent multi-layer sparse coding (ML-SC) model, we herein propose to solve a general sparse coding (GSC) problem across different layers and deduce the corresponding layered GSC (LGSC) algorithm. Based on the ideology of deep unrolling, the proposed algorithm is unfolded into LGSC-Net, whose relationship with the convolutional neural network (CNN) is also discussed in depth. The effectiveness of the proposed model is verified by an aero-engine bevel gear fault experiment and a helical gear fault experiment with three kinds of adversarial noise attacks. The interpretability is also discussed from the perspective of the core of model-driven deep unrolling and its inductive reconstruction property. |
Author | An, Botao Li, Tianfu Yan, Ruqiang Ding, Baoqing Zhao, Zhibin Wang, Shibin Chen, Xuefeng |
Author_xml | – sequence: 1 givenname: Zhibin orcidid: 0000-0003-4180-7137 surname: Zhao fullname: Zhao, Zhibin email: zhaozhibin@xjtu.edu.cn – sequence: 2 givenname: Tianfu surname: Li fullname: Li, Tianfu email: litianfu@stu.xjtu.edu.cn – sequence: 3 givenname: Botao surname: An fullname: An, Botao email: albert_an@stu.xjtu.edu.cn – sequence: 4 givenname: Shibin orcidid: 0000-0003-4923-0491 surname: Wang fullname: Wang, Shibin email: wangshibin2008@xjtu.edu.cn – sequence: 5 givenname: Baoqing orcidid: 0000-0001-5256-9061 surname: Ding fullname: Ding, Baoqing email: dingbq@xjtu.edu.cn – sequence: 6 givenname: Ruqiang surname: Yan fullname: Yan, Ruqiang email: yanruqiang@xjtu.edu.cn – sequence: 7 givenname: Xuefeng surname: Chen fullname: Chen, Xuefeng email: chenxf@xjtu.edu.cn |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35249725$$D View this record in MEDLINE/PubMed |
BookMark | eNp9kNFrFDEQxoO02GvrfyCSR1_2TLKXTdYHQYq2QqUv7XOYSyZHzr3kTLJX_O_ddauPwsDA8Pu-mfkuyVlMEQl5y9maM9592K9DgZphLZgQazaXekVWXKu-mUdnZMUY7xsmlb4gl6XsGWNC9vo1uWil2PRKyBU5fU8Oh8blcMJIHeKRjjGnYQhx95E-pmfIrtAQK-ZjxgrbARdqQMhxgijsIMRSaUyhIIVawf4o1Kf8RzUZ7TBW6mEcKnUBdjGVUK7JuYeh4JuXfkWevn55vLlr7h9uv918vm9s24na9FwKK6XTbtO5Xm0BlFV2q9BrJxWXkindgxbeqY0DaRVq3lrmPVPCIfftFXm_-B5z-jliqeYQip2ugohpLEZ0baeVELqf0M2C2pxKyejNMYcD5F-GMzMnbvZmSdzM8Ro2l5pk7142jNsDun-ivxFPwKcFwOnPU8Bsig0YLbqQ0VbjUvj_ht_Yd5ig |
CitedBy_id | crossref_primary_10_1109_TIM_2024_3373098 crossref_primary_10_1109_TIM_2024_3375974 crossref_primary_10_1109_TII_2023_3275704 crossref_primary_10_3390_biomedinformatics2040039 crossref_primary_10_1088_1361_6501_aceff0 crossref_primary_10_1016_j_jmsy_2024_04_003 crossref_primary_10_1016_j_engappai_2023_107214 crossref_primary_10_1177_14759217241249656 crossref_primary_10_1016_j_aei_2023_101883 crossref_primary_10_1016_j_eswa_2023_122806 crossref_primary_10_1016_j_ymssp_2023_110545 crossref_primary_10_1088_1361_6501_ad0939 crossref_primary_10_1007_s10489_023_04753_8 crossref_primary_10_1007_s11431_022_2102_3 crossref_primary_10_1016_j_ymssp_2024_111314 crossref_primary_10_1016_j_compstruct_2023_117299 crossref_primary_10_1016_j_ymssp_2023_110724 crossref_primary_10_1109_TII_2023_3342886 crossref_primary_10_1016_j_aei_2024_102493 crossref_primary_10_1109_TIM_2023_3291742 crossref_primary_10_1016_j_ress_2022_109046 crossref_primary_10_1016_j_eswa_2023_120860 crossref_primary_10_1016_j_isatra_2022_07_020 crossref_primary_10_1109_TSMC_2023_3346398 crossref_primary_10_1016_j_ymssp_2022_110046 crossref_primary_10_3390_electronics12204282 crossref_primary_10_1088_1361_6501_ad24ba crossref_primary_10_1109_TIM_2024_3351257 crossref_primary_10_1109_TIM_2024_3375402 crossref_primary_10_1109_TIM_2024_3373103 crossref_primary_10_3390_machines11040424 crossref_primary_10_1016_j_cose_2023_103578 crossref_primary_10_1088_1361_6501_ad36d9 crossref_primary_10_3390_machines11111012 crossref_primary_10_1109_TIE_2022_3229344 crossref_primary_10_1088_1361_6501_ad3b29 crossref_primary_10_1016_j_aei_2024_102421 crossref_primary_10_1109_TIM_2022_3212547 crossref_primary_10_1016_j_isatra_2023_08_028 crossref_primary_10_1016_j_ymssp_2023_110615 crossref_primary_10_1016_j_aei_2023_102120 crossref_primary_10_1016_j_eswa_2023_121323 crossref_primary_10_1109_ACCESS_2023_3292181 crossref_primary_10_1109_TNNLS_2023_3250664 crossref_primary_10_1016_j_isatra_2023_11_034 crossref_primary_10_1016_j_ymssp_2024_111489 crossref_primary_10_3390_machines10100879 |
Cites_doi | 10.1016/j.engappai.2018.09.010 10.1007/s11263-014-0784-7 10.1038/nature14539 10.1109/CVPR.2018.00745 10.1109/TRPMS.2021.3066428 10.3390/s20061693 10.1016/j.measurement.2019.02.080 10.1177/0142331217708242 10.1109/TAI.2021.3133846 10.1016/j.engappai.2020.103936 10.1016/j.isatra.2019.07.001 10.1016/j.ymssp.2015.11.014 10.1016/j.jsv.2019.01.042 10.1109/TIE.2018.2838070 10.1109/TSP.2020.3014716 10.1016/j.engappai.2020.103996 10.1007/s00041-008-9045-x 10.1016/j.nanoen.2021.106698 10.1007/978-3-030-01234-2_1 10.1109/TIM.2017.2698738 10.1016/j.isatra.2019.06.007 10.1016/j.isatra.2020.08.010 10.1016/j.patcog.2018.12.023 10.1016/j.ymssp.2018.03.025 10.1109/CVPR.2016.90 10.1016/j.ymssp.2017.06.022 10.1109/TIM.2021.3116309 10.1016/j.sigpro.2019.03.019 10.1016/j.engappai.2020.103678 10.1109/TIM.2016.2613359 10.1109/JSEN.2019.2958787 10.1109/TSMC.2017.2754287 10.1021/acsami.0c10714 10.1038/s41591-018-0316-z 10.1016/j.isatra.2018.04.005 10.1109/TII.2019.2943898 10.1016/j.ymssp.2017.08.002 10.1016/j.apacoust.2021.108336 10.1016/j.isatra.2019.08.012 |
ContentType | Journal Article |
Copyright | 2022 ISA Copyright © 2022 ISA. Published by Elsevier Ltd. All rights reserved. |
Copyright_xml | – notice: 2022 ISA – notice: Copyright © 2022 ISA. Published by Elsevier Ltd. All rights reserved. |
DBID | NPM AAYXX CITATION 7X8 |
DOI | 10.1016/j.isatra.2022.02.027 |
DatabaseName | PubMed CrossRef MEDLINE - Academic |
DatabaseTitle | PubMed CrossRef MEDLINE - Academic |
DatabaseTitleList | PubMed |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Sciences (General) |
EISSN | 1879-2022 |
EndPage | 662 |
ExternalDocumentID | 10_1016_j_isatra_2022_02_027 35249725 S0019057822000878 |
Genre | Journal Article |
GroupedDBID | --- --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29J 4.4 457 4G. 53G 5GY 5VS 6P2 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABFNM ABFRF ABJNI ABMAC ABNEU ABTAH ABXDB ABYKQ ACDAQ ACFVG ACGFO ACNNM ACRLP ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFDAS AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AIVDX AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SDF SDG SES SET SEW SPC SPCBC SPD SSQ SST SSZ T5K T9H TAE TN5 UHS UNMZH WUQ XPP ZMT ZY4 ~G- AAXKI AKRWK NPM AAYXX AFJKZ CITATION 7X8 |
ID | FETCH-LOGICAL-c362t-9152c55d8d46d97baa7c7cb7ef8d571550789a82fd74da5c7e813c0ff072de1f3 |
IEDL.DBID | .~1 |
ISSN | 0019-0578 |
IngestDate | Sat Aug 17 03:56:59 EDT 2024 Thu Sep 26 16:08:54 EDT 2024 Sat Sep 28 08:20:49 EDT 2024 Fri Feb 23 02:40:31 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Model-driven deep unrolling Intelligent fault diagnosis Interpretable deep learning Noise attacks |
Language | English |
License | Copyright © 2022 ISA. Published by Elsevier Ltd. All rights reserved. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c362t-9152c55d8d46d97baa7c7cb7ef8d571550789a82fd74da5c7e813c0ff072de1f3 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ORCID | 0000-0003-4923-0491 0000-0001-5256-9061 0000-0003-4180-7137 |
PMID | 35249725 |
PQID | 2636872289 |
PQPubID | 23479 |
PageCount | 19 |
ParticipantIDs | proquest_miscellaneous_2636872289 crossref_primary_10_1016_j_isatra_2022_02_027 pubmed_primary_35249725 elsevier_sciencedirect_doi_10_1016_j_isatra_2022_02_027 |
PublicationCentury | 2000 |
PublicationDate | 2022-10-01 |
PublicationDateYYYYMMDD | 2022-10-01 |
PublicationDate_xml | – month: 10 year: 2022 text: 2022-10-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States |
PublicationTitle | ISA transactions |
PublicationTitleAlternate | ISA Trans |
PublicationYear | 2022 |
Publisher | Elsevier Ltd |
Publisher_xml | – name: Elsevier Ltd |
References | Wen, Gao, Li (b48) 2017; 49 Zhao, Wu, Qiao, Wang, Chen (b3) 2018; 66 Maaten, Hinton (b52) 2008; 9 Shen, Qi, Wang, Cai, Zhu (b28) 2018; 76 Zhao, Wang, An, Guo, Chen (b40) 2020; 96 Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 7132–41. Gan, Wang (b25) 2016; 72 Li, Zhang, Ding (b21) 2019; 161 Yu, Wen, Yang, Zhao, Guo, Guo (b10) 2022; 92 Yang, Wang, Zhao, Guo, Chen, Zhang, Guo (b9) 2020; 12 Fan, Xiong, Li, Wang (b17) 2021 He, Zheng, Tan, Sun (b38) 2013; 36 Sulam, Aberdam, Beck, Elad (b36) 2019 Liu, Zhou, Zheng, Jiang, Zhang (b12) 2018; 77 Nascimento, Fricke, Viana (b23) 2020; 96 Zhang, Li, Peng, Chen, Zhang (b30) 2018; 100 Fink, Wang, Svensén, Dersin, Lee, Ducoffe (b1) 2020; 92 Jia, Lei, Lu, Xing (b19) 2018; 110 Han, Liu, Yang, Jiang (b14) 2020; 97 Li, Zhao, Sun, Cheng, Chen, Yan, Gao (b24) 2021 Han, Jiang, Zhao, Wang, Yin (b6) 2018; 40 Romano, Aberdam, Sulam, Elad (b34) 2019 Fawzi, Davies, Frossard (b42) 2015; 114 Goodfellow, Shlens, Szegedy (b53) 2014 Zhao, Li, Wu, Sun, Wang, Yan, Chen (b15) 2020; 107 He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 770–8. Esteva, Robicquet, Ramsundar, Kuleshov, DePristo, Chou, Cui, Corrado, Thrun, Dean (b8) 2019; 25 Rawal, Mccoy, Rawat, Sadler, Amant (b18) 2021; 1 Saeki, Ogata, Murakawa, Ogawa (b20) 2019 Ba (b43) 2020; 68 Zhao, Zhang, Yu, Sun, Wang, Yan, Chen (b16) 2021 Yang, Zhang, Yang, Zhang (b37) 2011 Zhao, Wang, Wong, Wang, Yan, Chen (b5) 2021 Wang, Pan, Yuan, Yang, Gui (b13) 2020; 96 Berghout, Mouss, Kadri, Saïdi, Benbouzid (b7) 2020; 96 Zhu, Li, Wang, Tang, Su, Cao (b51) 2021; 183 Peng, Wang (b31) 2019; 138 Wan, Chen, Li, Li (b50) 2020; 20 Zhao, Jia, Liu (b49) 2020; 70 Jiang, He, Xie, Tang (b27) 2017; 66 LeCun, Bengio, Hinton (b11) 2015; 521 Sulam, Papyan, Romano, Elad (b35) 2018; 66 Mnih, Heess, Graves (b46) 2014 Grezmak, Zhang, Wang, Loparo, Gao (b22) 2019; 20 Papyan, Romano, Elad (b33) 2017; 18 Wang, Chen, Tong, Zhao (b2) 2016; 66 Candes, Wakin, Boyd (b39) 2008; 14 Xu, An, Zhang, Zhang (b44) 2019; 88 Shao, Jiang, Zhang, Duan, Liang, Wu (b26) 2018; 100 Zhang, Li, Gao, Chen, Li (b29) 2020 Woo S, Park J, Lee J-Y, So Kweon I. Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV). 2018, p. 3–19. Zhao, Zhong, Fu, Tang, Pecht (b32) 2019; 16 Zhao, Qiao, Wang, Shen, Chen (b4) 2019; 446 Jia (10.1016/j.isatra.2022.02.027_b19) 2018; 110 Fan (10.1016/j.isatra.2022.02.027_b17) 2021 Rawal (10.1016/j.isatra.2022.02.027_b18) 2021; 1 Nascimento (10.1016/j.isatra.2022.02.027_b23) 2020; 96 Wan (10.1016/j.isatra.2022.02.027_b50) 2020; 20 Zhao (10.1016/j.isatra.2022.02.027_b15) 2020; 107 Sulam (10.1016/j.isatra.2022.02.027_b35) 2018; 66 Zhu (10.1016/j.isatra.2022.02.027_b51) 2021; 183 Zhao (10.1016/j.isatra.2022.02.027_b49) 2020; 70 Fink (10.1016/j.isatra.2022.02.027_b1) 2020; 92 Zhao (10.1016/j.isatra.2022.02.027_b40) 2020; 96 Zhao (10.1016/j.isatra.2022.02.027_b32) 2019; 16 Papyan (10.1016/j.isatra.2022.02.027_b33) 2017; 18 Shen (10.1016/j.isatra.2022.02.027_b28) 2018; 76 Yang (10.1016/j.isatra.2022.02.027_b37) 2011 Berghout (10.1016/j.isatra.2022.02.027_b7) 2020; 96 Xu (10.1016/j.isatra.2022.02.027_b44) 2019; 88 Zhang (10.1016/j.isatra.2022.02.027_b29) 2020 Li (10.1016/j.isatra.2022.02.027_b24) 2021 He (10.1016/j.isatra.2022.02.027_b38) 2013; 36 Zhao (10.1016/j.isatra.2022.02.027_b3) 2018; 66 Zhao (10.1016/j.isatra.2022.02.027_b16) 2021 Wang (10.1016/j.isatra.2022.02.027_b13) 2020; 96 Grezmak (10.1016/j.isatra.2022.02.027_b22) 2019; 20 LeCun (10.1016/j.isatra.2022.02.027_b11) 2015; 521 Gan (10.1016/j.isatra.2022.02.027_b25) 2016; 72 Jiang (10.1016/j.isatra.2022.02.027_b27) 2017; 66 Goodfellow (10.1016/j.isatra.2022.02.027_b53) 2014 Maaten (10.1016/j.isatra.2022.02.027_b52) 2008; 9 Zhao (10.1016/j.isatra.2022.02.027_b4) 2019; 446 Zhang (10.1016/j.isatra.2022.02.027_b30) 2018; 100 Romano (10.1016/j.isatra.2022.02.027_b34) 2019 Yang (10.1016/j.isatra.2022.02.027_b9) 2020; 12 Liu (10.1016/j.isatra.2022.02.027_b12) 2018; 77 Shao (10.1016/j.isatra.2022.02.027_b26) 2018; 100 Fawzi (10.1016/j.isatra.2022.02.027_b42) 2015; 114 Saeki (10.1016/j.isatra.2022.02.027_b20) 2019 Yu (10.1016/j.isatra.2022.02.027_b10) 2022; 92 Ba (10.1016/j.isatra.2022.02.027_b43) 2020; 68 Li (10.1016/j.isatra.2022.02.027_b21) 2019; 161 Han (10.1016/j.isatra.2022.02.027_b14) 2020; 97 Sulam (10.1016/j.isatra.2022.02.027_b36) 2019 Zhao (10.1016/j.isatra.2022.02.027_b5) 2021 Candes (10.1016/j.isatra.2022.02.027_b39) 2008; 14 10.1016/j.isatra.2022.02.027_b45 10.1016/j.isatra.2022.02.027_b47 Wang (10.1016/j.isatra.2022.02.027_b2) 2016; 66 Wen (10.1016/j.isatra.2022.02.027_b48) 2017; 49 Peng (10.1016/j.isatra.2022.02.027_b31) 2019; 138 Han (10.1016/j.isatra.2022.02.027_b6) 2018; 40 Mnih (10.1016/j.isatra.2022.02.027_b46) 2014 10.1016/j.isatra.2022.02.027_b41 Esteva (10.1016/j.isatra.2022.02.027_b8) 2019; 25 |
References_xml | – volume: 70 start-page: 1 year: 2020 end-page: 13 ident: b49 article-title: Semisupervised deep sparse auto-encoder with local and nonlocal information for intelligent fault diagnosis of rotating machinery publication-title: IEEE Trans Instrum Meas contributor: fullname: Liu – volume: 183 year: 2021 ident: b51 article-title: Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization publication-title: Appl Acoust contributor: fullname: Cao – year: 2019 ident: b36 article-title: On multi-layer basis pursuit, efficient algorithms and convolutional neural networks publication-title: IEEE Trans Pattern Anal Mach Intell contributor: fullname: Elad – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b11 article-title: Deep learning publication-title: Nature contributor: fullname: Hinton – year: 2014 ident: b53 article-title: Explaining and harnessing adversarial examples contributor: fullname: Szegedy – volume: 114 start-page: 306 year: 2015 end-page: 321 ident: b42 article-title: Dictionary learning for fast classification based on soft-thresholding publication-title: Int J Comput Vis contributor: fullname: Frossard – volume: 66 start-page: 2143 year: 2018 end-page: 2153 ident: b3 article-title: Enhanced sparse period-group lasso for bearing fault diagnosis publication-title: IEEE Trans Ind Electron contributor: fullname: Chen – volume: 88 start-page: 679 year: 2019 end-page: 688 ident: b44 article-title: Sparse, collaborative, or nonnegative representation: which helps pattern classification? publication-title: Pattern Recognit contributor: fullname: Zhang – volume: 97 start-page: 269 year: 2020 end-page: 281 ident: b14 article-title: Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application publication-title: ISA Trans contributor: fullname: Jiang – start-page: 1 year: 2019 end-page: 4 ident: b20 article-title: Visual explanation of neural network based rotation machinery anomaly detection system publication-title: 2019 IEEE international conference on prognostics and health management (ICPHM) contributor: fullname: Ogawa – volume: 96 year: 2020 ident: b7 article-title: Aircraft engines remaining useful life prediction with an adaptive denoising online sequential extreme learning machine publication-title: Eng Appl Artif Intell contributor: fullname: Benbouzid – start-page: 1 year: 2019 end-page: 15 ident: b34 article-title: Adversarial noise attacks of deep learning architectures: Stability analysis via sparse-modeled signals publication-title: J Math Imaging Vision contributor: fullname: Elad – volume: 66 start-page: 4090 year: 2018 end-page: 4104 ident: b35 article-title: Multilayer convolutional sparse modeling: Pursuit and dictionary learning publication-title: IEEE Trans Signal Process contributor: fullname: Elad – volume: 72 start-page: 92 year: 2016 end-page: 104 ident: b25 article-title: Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings publication-title: Mech Syst Signal Process contributor: fullname: Wang – volume: 14 start-page: 877 year: 2008 end-page: 905 ident: b39 article-title: Enhancing sparsity by reweighted publication-title: J Fourier Anal Appl contributor: fullname: Boyd – start-page: 625 year: 2011 end-page: 632 ident: b37 article-title: Robust sparse coding for face recognition publication-title: CVPR 2011 contributor: fullname: Zhang – volume: 446 start-page: 429 year: 2019 end-page: 452 ident: b4 article-title: A weighted multi-scale dictionary learning model and its applications on bearing fault diagnosis publication-title: J Sound Vib contributor: fullname: Chen – volume: 100 start-page: 743 year: 2018 end-page: 765 ident: b26 article-title: Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing publication-title: Mech Syst Signal Process contributor: fullname: Wu – volume: 100 start-page: 439 year: 2018 end-page: 453 ident: b30 article-title: A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load publication-title: Mech Syst Signal Process contributor: fullname: Zhang – volume: 96 start-page: 457 year: 2020 end-page: 467 ident: b13 article-title: A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network publication-title: ISA Trans contributor: fullname: Gui – volume: 16 start-page: 4681 year: 2019 end-page: 4690 ident: b32 article-title: Deep residual shrinkage networks for fault diagnosis publication-title: IEEE Trans Ind Inf contributor: fullname: Pecht – volume: 1 start-page: 1 year: 2021 ident: b18 article-title: Recent advances in trustworthy explainable artificial intelligence: Status, challenges and perspectives publication-title: IEEE Trans Artif Intell contributor: fullname: Amant – volume: 66 start-page: 2391 year: 2017 end-page: 2402 ident: b27 article-title: Stacked multilevel-denoising autoencoders: A new representation learning approach for wind turbine gearbox fault diagnosis publication-title: IEEE Trans Instrum Meas contributor: fullname: Tang – volume: 36 start-page: 261 year: 2013 end-page: 275 ident: b38 article-title: Half-quadratic-based iterative minimization for robust sparse representation publication-title: IEEE Trans Pattern Anal Mach Intell contributor: fullname: Sun – volume: 92 year: 2022 ident: b10 article-title: Monitoring on triboelectric nanogenerator and deep learning method publication-title: Nano Energy contributor: fullname: Guo – volume: 138 start-page: 652 year: 2019 end-page: 658 ident: b31 article-title: NOSCNN: A robust method for fault diagnosis of RV reducer publication-title: Measurement contributor: fullname: Wang – volume: 20 start-page: 1693 year: 2020 ident: b50 article-title: Rolling-element bearing fault diagnosis using improved LeNet-5 network publication-title: Sensors contributor: fullname: Li – volume: 66 start-page: 360 year: 2016 end-page: 372 ident: b2 article-title: Matching synchrosqueezing wavelet transform and application to aeroengine vibration monitoring publication-title: IEEE Trans Instrum Meas contributor: fullname: Zhao – volume: 96 year: 2020 ident: b23 article-title: A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural network publication-title: Eng Appl Artif Intell contributor: fullname: Viana – volume: 18 start-page: 2887 year: 2017 end-page: 2938 ident: b33 article-title: Convolutional neural networks analyzed via convolutional sparse coding publication-title: J Mach Learn Res contributor: fullname: Elad – year: 2021 ident: b16 article-title: Applications of unsupervised deep transfer learning to intelligent fault diagnosis: A survey and comparative study publication-title: IEEE Trans Instrum Meas contributor: fullname: Chen – volume: 76 start-page: 170 year: 2018 end-page: 184 ident: b28 article-title: An automatic and robust features learning method for rotating machinery fault diagnosis based on contractive autoencoder publication-title: Eng Appl Artif Intell contributor: fullname: Zhu – volume: 161 start-page: 136 year: 2019 end-page: 154 ident: b21 article-title: Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism publication-title: Signal Process contributor: fullname: Ding – volume: 20 start-page: 3172 year: 2019 end-page: 3181 ident: b22 article-title: Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis publication-title: IEEE Sens J contributor: fullname: Gao – volume: 96 start-page: 429 year: 2020 end-page: 443 ident: b40 article-title: Hierarchical hyper-Laplacian prior for weak fault feature enhancement publication-title: ISA Trans contributor: fullname: Chen – start-page: 2204 year: 2014 end-page: 2212 ident: b46 article-title: Recurrent models of visual attention publication-title: Advances in neural information processing systems contributor: fullname: Graves – volume: 77 start-page: 167 year: 2018 end-page: 178 ident: b12 article-title: Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders publication-title: ISA Trans contributor: fullname: Zhang – volume: 68 start-page: 4727 year: 2020 end-page: 4742 ident: b43 article-title: Deeply-sparse signal representations (DS publication-title: IEEE Trans Signal Process contributor: fullname: Ba – volume: 40 start-page: 2681 year: 2018 end-page: 2693 ident: b6 article-title: Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery publication-title: Trans Inst Meas Control contributor: fullname: Yin – volume: 9 start-page: 2579 year: 2008 end-page: 2605 ident: b52 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res contributor: fullname: Hinton – year: 2021 ident: b17 article-title: On interpretability of artificial neural networks: A survey publication-title: IEEE Trans Radiat Plasma Med Sci contributor: fullname: Wang – volume: 25 start-page: 24 year: 2019 end-page: 29 ident: b8 article-title: A guide to deep learning in healthcare publication-title: Nat Med contributor: fullname: Dean – year: 2021 ident: b5 article-title: Fast sparsity-assisted signal decomposition with non-convex enhancement for bearing fault diagnosis publication-title: IEEE/ASME Trans Mechatronics contributor: fullname: Chen – year: 2021 ident: b24 article-title: Waveletkernelnet: An interpretable deep neural network for industrial intelligent diagnosis contributor: fullname: Gao – volume: 92 year: 2020 ident: b1 article-title: Potential, challenges and future directions for deep learning in prognostics and health management applications publication-title: Eng Appl Artif Intell contributor: fullname: Ducoffe – volume: 12 start-page: 38192 year: 2020 end-page: 38201 ident: b9 article-title: Particle-laden droplet-driven triboelectric nanogenerator for real-time sediment monitoring using a deep learning method publication-title: ACS Appl Mater Interfaces contributor: fullname: Guo – year: 2020 ident: b29 article-title: Ensemble deep contractive auto-encoders for intelligent fault diagnosis of machines under noisy environment publication-title: Knowl-Based Syst contributor: fullname: Li – volume: 110 start-page: 349 year: 2018 end-page: 367 ident: b19 article-title: Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization publication-title: Mech Syst Signal Process contributor: fullname: Xing – volume: 49 start-page: 136 year: 2017 end-page: 144 ident: b48 article-title: A new deep transfer learning based on sparse auto-encoder for fault diagnosis publication-title: IEEE Trans Syst Man Cybern: Syst contributor: fullname: Li – volume: 107 start-page: 224 year: 2020 end-page: 255 ident: b15 article-title: Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study publication-title: ISA Trans contributor: fullname: Chen – volume: 76 start-page: 170 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b28 article-title: An automatic and robust features learning method for rotating machinery fault diagnosis based on contractive autoencoder publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2018.09.010 contributor: fullname: Shen – volume: 114 start-page: 306 issue: 2–3 year: 2015 ident: 10.1016/j.isatra.2022.02.027_b42 article-title: Dictionary learning for fast classification based on soft-thresholding publication-title: Int J Comput Vis doi: 10.1007/s11263-014-0784-7 contributor: fullname: Fawzi – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.isatra.2022.02.027_b11 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 contributor: fullname: LeCun – ident: 10.1016/j.isatra.2022.02.027_b45 doi: 10.1109/CVPR.2018.00745 – year: 2021 ident: 10.1016/j.isatra.2022.02.027_b17 article-title: On interpretability of artificial neural networks: A survey publication-title: IEEE Trans Radiat Plasma Med Sci doi: 10.1109/TRPMS.2021.3066428 contributor: fullname: Fan – start-page: 625 year: 2011 ident: 10.1016/j.isatra.2022.02.027_b37 article-title: Robust sparse coding for face recognition contributor: fullname: Yang – volume: 20 start-page: 1693 issue: 6 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b50 article-title: Rolling-element bearing fault diagnosis using improved LeNet-5 network publication-title: Sensors doi: 10.3390/s20061693 contributor: fullname: Wan – volume: 138 start-page: 652 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b31 article-title: NOSCNN: A robust method for fault diagnosis of RV reducer publication-title: Measurement doi: 10.1016/j.measurement.2019.02.080 contributor: fullname: Peng – volume: 40 start-page: 2681 issue: 8 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b6 article-title: Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery publication-title: Trans Inst Meas Control doi: 10.1177/0142331217708242 contributor: fullname: Han – volume: 1 start-page: 1 issue: 01 year: 2021 ident: 10.1016/j.isatra.2022.02.027_b18 article-title: Recent advances in trustworthy explainable artificial intelligence: Status, challenges and perspectives publication-title: IEEE Trans Artif Intell doi: 10.1109/TAI.2021.3133846 contributor: fullname: Rawal – year: 2019 ident: 10.1016/j.isatra.2022.02.027_b36 article-title: On multi-layer basis pursuit, efficient algorithms and convolutional neural networks publication-title: IEEE Trans Pattern Anal Mach Intell contributor: fullname: Sulam – volume: 18 start-page: 2887 issue: 1 year: 2017 ident: 10.1016/j.isatra.2022.02.027_b33 article-title: Convolutional neural networks analyzed via convolutional sparse coding publication-title: J Mach Learn Res contributor: fullname: Papyan – start-page: 2204 year: 2014 ident: 10.1016/j.isatra.2022.02.027_b46 article-title: Recurrent models of visual attention contributor: fullname: Mnih – volume: 96 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b7 article-title: Aircraft engines remaining useful life prediction with an adaptive denoising online sequential extreme learning machine publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2020.103936 contributor: fullname: Berghout – volume: 96 start-page: 457 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b13 article-title: A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network publication-title: ISA Trans doi: 10.1016/j.isatra.2019.07.001 contributor: fullname: Wang – volume: 72 start-page: 92 year: 2016 ident: 10.1016/j.isatra.2022.02.027_b25 article-title: Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2015.11.014 contributor: fullname: Gan – volume: 446 start-page: 429 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b4 article-title: A weighted multi-scale dictionary learning model and its applications on bearing fault diagnosis publication-title: J Sound Vib doi: 10.1016/j.jsv.2019.01.042 contributor: fullname: Zhao – volume: 66 start-page: 2143 issue: 3 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b3 article-title: Enhanced sparse period-group lasso for bearing fault diagnosis publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2018.2838070 contributor: fullname: Zhao – volume: 68 start-page: 4727 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b43 article-title: Deeply-sparse signal representations (DS2P) publication-title: IEEE Trans Signal Process doi: 10.1109/TSP.2020.3014716 contributor: fullname: Ba – volume: 96 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b23 article-title: A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural network publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2020.103996 contributor: fullname: Nascimento – start-page: 1 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b20 article-title: Visual explanation of neural network based rotation machinery anomaly detection system contributor: fullname: Saeki – volume: 14 start-page: 877 issue: 5–6 year: 2008 ident: 10.1016/j.isatra.2022.02.027_b39 article-title: Enhancing sparsity by reweighted l1 minimization publication-title: J Fourier Anal Appl doi: 10.1007/s00041-008-9045-x contributor: fullname: Candes – volume: 9 start-page: 2579 issue: Nov year: 2008 ident: 10.1016/j.isatra.2022.02.027_b52 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res contributor: fullname: Maaten – year: 2021 ident: 10.1016/j.isatra.2022.02.027_b24 contributor: fullname: Li – volume: 92 year: 2022 ident: 10.1016/j.isatra.2022.02.027_b10 article-title: Monitoring on triboelectric nanogenerator and deep learning method publication-title: Nano Energy doi: 10.1016/j.nanoen.2021.106698 contributor: fullname: Yu – ident: 10.1016/j.isatra.2022.02.027_b47 doi: 10.1007/978-3-030-01234-2_1 – volume: 66 start-page: 2391 issue: 9 year: 2017 ident: 10.1016/j.isatra.2022.02.027_b27 article-title: Stacked multilevel-denoising autoencoders: A new representation learning approach for wind turbine gearbox fault diagnosis publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2017.2698738 contributor: fullname: Jiang – volume: 96 start-page: 429 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b40 article-title: Hierarchical hyper-Laplacian prior for weak fault feature enhancement publication-title: ISA Trans doi: 10.1016/j.isatra.2019.06.007 contributor: fullname: Zhao – volume: 107 start-page: 224 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b15 article-title: Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study publication-title: ISA Trans doi: 10.1016/j.isatra.2020.08.010 contributor: fullname: Zhao – volume: 88 start-page: 679 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b44 article-title: Sparse, collaborative, or nonnegative representation: which helps pattern classification? publication-title: Pattern Recognit doi: 10.1016/j.patcog.2018.12.023 contributor: fullname: Xu – volume: 70 start-page: 1 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b49 article-title: Semisupervised deep sparse auto-encoder with local and nonlocal information for intelligent fault diagnosis of rotating machinery publication-title: IEEE Trans Instrum Meas contributor: fullname: Zhao – volume: 110 start-page: 349 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b19 article-title: Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2018.03.025 contributor: fullname: Jia – ident: 10.1016/j.isatra.2022.02.027_b41 doi: 10.1109/CVPR.2016.90 – volume: 66 start-page: 4090 issue: 15 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b35 article-title: Multilayer convolutional sparse modeling: Pursuit and dictionary learning publication-title: IEEE Trans Signal Process contributor: fullname: Sulam – volume: 100 start-page: 439 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b30 article-title: A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2017.06.022 contributor: fullname: Zhang – year: 2021 ident: 10.1016/j.isatra.2022.02.027_b5 article-title: Fast sparsity-assisted signal decomposition with non-convex enhancement for bearing fault diagnosis publication-title: IEEE/ASME Trans Mechatronics contributor: fullname: Zhao – year: 2021 ident: 10.1016/j.isatra.2022.02.027_b16 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 contributor: fullname: Zhao – volume: 161 start-page: 136 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b21 article-title: Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism publication-title: Signal Process doi: 10.1016/j.sigpro.2019.03.019 contributor: fullname: Li – volume: 92 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b1 article-title: Potential, challenges and future directions for deep learning in prognostics and health management applications publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2020.103678 contributor: fullname: Fink – volume: 66 start-page: 360 issue: 2 year: 2016 ident: 10.1016/j.isatra.2022.02.027_b2 article-title: Matching synchrosqueezing wavelet transform and application to aeroengine vibration monitoring publication-title: IEEE Trans Instrum Meas doi: 10.1109/TIM.2016.2613359 contributor: fullname: Wang – year: 2020 ident: 10.1016/j.isatra.2022.02.027_b29 article-title: Ensemble deep contractive auto-encoders for intelligent fault diagnosis of machines under noisy environment publication-title: Knowl-Based Syst contributor: fullname: Zhang – volume: 20 start-page: 3172 issue: 6 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b22 article-title: Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis publication-title: IEEE Sens J doi: 10.1109/JSEN.2019.2958787 contributor: fullname: Grezmak – volume: 49 start-page: 136 issue: 1 year: 2017 ident: 10.1016/j.isatra.2022.02.027_b48 article-title: A new deep transfer learning based on sparse auto-encoder for fault diagnosis publication-title: IEEE Trans Syst Man Cybern: Syst doi: 10.1109/TSMC.2017.2754287 contributor: fullname: Wen – volume: 12 start-page: 38192 issue: 34 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b9 article-title: Particle-laden droplet-driven triboelectric nanogenerator for real-time sediment monitoring using a deep learning method publication-title: ACS Appl Mater Interfaces doi: 10.1021/acsami.0c10714 contributor: fullname: Yang – volume: 25 start-page: 24 issue: 1 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b8 article-title: A guide to deep learning in healthcare publication-title: Nat Med doi: 10.1038/s41591-018-0316-z contributor: fullname: Esteva – volume: 77 start-page: 167 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b12 article-title: Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders publication-title: ISA Trans doi: 10.1016/j.isatra.2018.04.005 contributor: fullname: Liu – year: 2014 ident: 10.1016/j.isatra.2022.02.027_b53 contributor: fullname: Goodfellow – start-page: 1 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b34 article-title: Adversarial noise attacks of deep learning architectures: Stability analysis via sparse-modeled signals publication-title: J Math Imaging Vision contributor: fullname: Romano – volume: 16 start-page: 4681 issue: 7 year: 2019 ident: 10.1016/j.isatra.2022.02.027_b32 article-title: Deep residual shrinkage networks for fault diagnosis publication-title: IEEE Trans Ind Inf doi: 10.1109/TII.2019.2943898 contributor: fullname: Zhao – volume: 36 start-page: 261 issue: 2 year: 2013 ident: 10.1016/j.isatra.2022.02.027_b38 article-title: Half-quadratic-based iterative minimization for robust sparse representation publication-title: IEEE Trans Pattern Anal Mach Intell contributor: fullname: He – volume: 100 start-page: 743 year: 2018 ident: 10.1016/j.isatra.2022.02.027_b26 article-title: Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2017.08.002 contributor: fullname: Shao – volume: 183 year: 2021 ident: 10.1016/j.isatra.2022.02.027_b51 article-title: Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization publication-title: Appl Acoust doi: 10.1016/j.apacoust.2021.108336 contributor: fullname: Zhu – volume: 97 start-page: 269 year: 2020 ident: 10.1016/j.isatra.2022.02.027_b14 article-title: Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application publication-title: ISA Trans doi: 10.1016/j.isatra.2019.08.012 contributor: fullname: Han |
SSID | ssj0002598 |
Score | 2.5418384 |
Snippet | Intelligent fault diagnosis (IFD) has experienced tremendous progress owing to a great deal to deep learning (DL)-based methods over the decades. However, the... |
SourceID | proquest crossref pubmed elsevier |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 644 |
SubjectTerms | Intelligent fault diagnosis Interpretable deep learning Model-driven deep unrolling Noise attacks |
Title | Model-driven deep unrolling: Towards interpretable deep learning against noise attacks for intelligent fault diagnosis |
URI | https://dx.doi.org/10.1016/j.isatra.2022.02.027 https://www.ncbi.nlm.nih.gov/pubmed/35249725 https://search.proquest.com/docview/2636872289 |
Volume | 129 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS-QwEB9EX-4e5PQ-3PODHPhwPvTcjWnT-iaLsvehiCj4FtIklcrSXbZdH_3bnUlS7wSPg4NCaUlpyCQzv5Df_AZgv6RClNyZRBRoBmEyk2iX6YRT9DajTJa-Dtn5RTa5ET9u09sVGPe5MESrjL4_-HTvreObwziah_O6phxfDGakxk7ZJrmkhF-BwQjn9LfH3zQPhPfRGxcJte7T5zzHixgzC1If4twrd1JtmdfD09_gpw9DZ-9gPeJHdhK6uAErrtmEt3-oCm7CRlyvLfsaRaUP3sMDFT2bJnZB3o1Z5-aMeIBekfuYXXvybMvqZwpiOXWhVSwrccf0na4RS7JmVreO6a6j7HyGmNd_FWQ9O1bp5bRjNhD46vYD3JydXo8nSay5kBgMZR36vpSbNLW5FZktZKm1NNKU0lW5TSXtZ2Re6JxXVgqrUyNdPjoyw6oaSm7dqDr6CKvNrHFbwEjnhs5teZkWYiRs6Spc7kNeVGgUrrMBJP1Qq3mQ1lA95-xeBdMoMo0a0iUHIHt7qBdTRKH3_8eXX3rzKVw9dCSiGzdbtgq7mOWS465zAJ-CXZ_7gtBUFJKnn__7v9vwhp4C928HVrvF0u0ihunKPT9J92DtZHz165Lu339OLp4A51TzBQ |
link.rule.ids | 315,786,790,4521,24144,27957,27958,45620,45714 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Ba9swFH50yWHroSxpu6VdNw162A6msSJbdm-lNCRrm1MKvQlZkoNLcELs9PdXz5JDCyuDgU-2hcV70nuf0fe-B3CeYSNKalTAUusGpmIVSBPLgGL2VmHMs6YP2f0snjywP4_R4x5ct7UwSKv0sd_F9CZa-zsX3poX66LAGl-bzFCNHatNEp58gC6LeMg60L2a3k5mu4BsEb4PyGmAA9oKuobmhaSZDQoQUdqId2J7mb9nqPcQaJOJxp_hwENIcuVm2YM9U_Zh_5WwYB96fstW5JfXlf59CM_Y92wZ6A0GOKKNWROkAjai3Jdk3vBnK1LsWIjZ0ri3fGeJBZELWVg4ScpVURki6xoL9ImFvc0op-xZk1xulzXRjsNXVEfwML6ZX08C33YhUDab1Tb8RVRFkU40i3XKMym54irjJk-0tS8KoCWpTGiuOdMyUtwk4UgN83zIqTZhPjqGTrkqzVcgKHWDR7c0i1IWMp2Z3O74IU1z6xQq4wEEranF2qlriJZ29iScawS6Rgzx4gPgrT_Em1UibAL4x8ifrfuE3UB4KiJLs9pWwk4xTji1P54D-OL8upuLRacs5TQ6-e_v_oCPk_n9nbibzm5P4RM-cVTAb9CpN1tzZiFNnX33S_YFqM30Jg |
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=Model-driven+deep+unrolling%3A+Towards+interpretable+deep+learning+against+noise+attacks+for+intelligent+fault+diagnosis&rft.jtitle=ISA+transactions&rft.au=Zhao%2C+Zhibin&rft.au=Li%2C+Tianfu&rft.au=An%2C+Botao&rft.au=Wang%2C+Shibin&rft.date=2022-10-01&rft.eissn=1879-2022&rft.volume=129&rft.spage=644&rft.epage=662&rft_id=info:doi/10.1016%2Fj.isatra.2022.02.027&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0019-0578&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0019-0578&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0019-0578&client=summon |