Interpreting network knowledge with attention mechanism for bearing fault diagnosis
Condition monitoring and fault diagnosis of bearings play important roles in production safety and limiting the cost of maintenance on a reasonable level. Nowadays, artificial intelligence and machine learning make fault diagnosis gradually become intelligent, and data-driven intelligent algorithms...
Saved in:
| Published in | Applied soft computing Vol. 97; p. 106829 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.12.2020
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Condition monitoring and fault diagnosis of bearings play important roles in production safety and limiting the cost of maintenance on a reasonable level. Nowadays, artificial intelligence and machine learning make fault diagnosis gradually become intelligent, and data-driven intelligent algorithms are receiving more and more attention. However, many methods use the existing deep learning models directly for the analysis of mechanical vibration signals, which is still lack of interpretability to researchers. In this paper, a method based on multilayer bidirectional gated recurrent units with attention mechanism is proposed to access the interpretability of neural networks in fault diagnosis, which combines the convolution neural network, gated recurrent unit, and the attention mechanism. Based on the attention mechanism, the attention distribution of input segments is visualized and thus the interpretability of neural networks can be further presented. Experimental validations and comparisons are conducted on bearings. The results present that the proposed model is effective for localizing the discriminative information from the input data, which provides a tool for better understanding the feature extraction process in neural networks, especially for mechanical vibration signals.
•The attention mechanism is introduced in bearing fault diagnosis.•A deep learning-based bearing fault diagnosis model via attention is proposed.•The results of the model have clearer interpretability compared with other models.•Experiments on bearing datasets verified the effectiveness of the model. |
|---|---|
| AbstractList | Condition monitoring and fault diagnosis of bearings play important roles in production safety and limiting the cost of maintenance on a reasonable level. Nowadays, artificial intelligence and machine learning make fault diagnosis gradually become intelligent, and data-driven intelligent algorithms are receiving more and more attention. However, many methods use the existing deep learning models directly for the analysis of mechanical vibration signals, which is still lack of interpretability to researchers. In this paper, a method based on multilayer bidirectional gated recurrent units with attention mechanism is proposed to access the interpretability of neural networks in fault diagnosis, which combines the convolution neural network, gated recurrent unit, and the attention mechanism. Based on the attention mechanism, the attention distribution of input segments is visualized and thus the interpretability of neural networks can be further presented. Experimental validations and comparisons are conducted on bearings. The results present that the proposed model is effective for localizing the discriminative information from the input data, which provides a tool for better understanding the feature extraction process in neural networks, especially for mechanical vibration signals.
•The attention mechanism is introduced in bearing fault diagnosis.•A deep learning-based bearing fault diagnosis model via attention is proposed.•The results of the model have clearer interpretability compared with other models.•Experiments on bearing datasets verified the effectiveness of the model. |
| ArticleNumber | 106829 |
| Author | Zhang, Jun-peng Chen, Xue-feng Yang, Zhi-bo Zhao, Zhi-bin Zhai, Zhi |
| Author_xml | – sequence: 1 givenname: Zhi-bo surname: Yang fullname: Yang, Zhi-bo email: phdapple@mail.xjtu.edu.cn – sequence: 2 givenname: Jun-peng surname: Zhang fullname: Zhang, Jun-peng – sequence: 3 givenname: Zhi-bin surname: Zhao fullname: Zhao, Zhi-bin – sequence: 4 givenname: Zhi surname: Zhai fullname: Zhai, Zhi – sequence: 5 givenname: Xue-feng surname: Chen fullname: Chen, Xue-feng |
| BookMark | eNp9kM1KAzEURoNUsK2-gKu8wIxJ5i8BN1LUFgou1HXIJHfatNOkJNHi2ztDXbno6l4unI_7nRmaOO8AoXtKckpo_bDLVfQ6Z4SNh5ozcYWmlDcsEzWnk2Gvap6Voqxv0CzGHRkgwfgUva9cgnAMkKzbYAfp5MMe750_9WA2gE82bbFKCVyy3uED6K1yNh5w5wNuQYUR69RXn7CxauN8tPEWXXeqj3D3N-fo8-X5Y7HM1m-vq8XTOtMFISlTFEhbMNFUQ4UWGqZ425iSMyoaYwQQ1lVdW1ei4ESwomWUVoqV3IimEGUpijni51wdfIwBOqltUuOfKSjbS0rkKEfu5ChHjnLkWc6Asn_oMdiDCj-XocczBEOpbwtBRm3BaTA2gE7SeHsJ_wVgpYCa |
| CitedBy_id | crossref_primary_10_1016_j_measurement_2022_111594 crossref_primary_10_1016_j_engappai_2024_107975 crossref_primary_10_1177_14759217211018281 crossref_primary_10_1016_j_ymssp_2022_109611 crossref_primary_10_1109_TIM_2021_3134999 crossref_primary_10_1109_JSEN_2024_3427125 crossref_primary_10_1016_j_ymssp_2025_112624 crossref_primary_10_1109_ACCESS_2022_3164077 crossref_primary_10_3390_app12168388 crossref_primary_10_1093_tse_tdac050 crossref_primary_10_1109_JSEN_2022_3200691 crossref_primary_10_1016_j_asoc_2022_109959 crossref_primary_10_1177_16878132241245894 crossref_primary_10_1016_j_aei_2024_103048 crossref_primary_10_1016_j_compind_2024_104229 crossref_primary_10_1016_j_cose_2022_102663 crossref_primary_10_1007_s12559_023_10218_4 crossref_primary_10_1016_j_ymssp_2021_108653 crossref_primary_10_1109_JSEN_2021_3131166 crossref_primary_10_1109_ACCESS_2023_3255891 crossref_primary_10_1088_1361_6501_ad3a08 crossref_primary_10_1109_TNNLS_2022_3232394 crossref_primary_10_1016_j_measurement_2021_110242 crossref_primary_10_3390_w15091773 crossref_primary_10_1088_1361_6501_acce55 crossref_primary_10_1088_1361_6501_acf8e6 crossref_primary_10_1109_TII_2021_3121294 crossref_primary_10_1088_1361_6501_ad3fd2 crossref_primary_10_3390_act11100275 crossref_primary_10_1186_s10033_021_00580_5 crossref_primary_10_1016_j_measurement_2022_111935 crossref_primary_10_3390_su15118731 crossref_primary_10_3390_sym17010050 crossref_primary_10_1016_j_eswa_2022_116503 crossref_primary_10_1109_JSEN_2024_3421242 crossref_primary_10_1016_j_compind_2022_103638 crossref_primary_10_1016_j_eswa_2022_117716 crossref_primary_10_1088_1361_6501_acd01e crossref_primary_10_1016_j_automatica_2022_110350 crossref_primary_10_1109_ACCESS_2024_3412157 crossref_primary_10_1088_1361_6501_ad3b2c crossref_primary_10_1088_1361_6501_ac66c4 crossref_primary_10_1016_j_knosys_2024_111579 crossref_primary_10_1063_5_0158412 crossref_primary_10_1016_j_sigpro_2024_109683 crossref_primary_10_1109_JSEN_2023_3284044 crossref_primary_10_1016_j_ymssp_2023_110314 crossref_primary_10_1016_j_isatra_2022_06_035 crossref_primary_10_1088_1361_6501_ad11c9 crossref_primary_10_1007_s40430_025_05457_5 crossref_primary_10_21595_jve_2023_23398 crossref_primary_10_1109_JIOT_2024_3387538 crossref_primary_10_1016_j_measurement_2024_116067 crossref_primary_10_1007_s10489_024_05643_3 crossref_primary_10_1007_s10845_023_02133_0 crossref_primary_10_1016_j_engappai_2023_107052 crossref_primary_10_1109_TIM_2023_3298403 crossref_primary_10_3390_machines11070746 crossref_primary_10_1016_j_est_2022_105820 crossref_primary_10_3390_vibration6010002 crossref_primary_10_1016_j_measurement_2022_111950 crossref_primary_10_1109_TCYB_2024_3497597 crossref_primary_10_1177_10775463231211403 crossref_primary_10_3390_app14031198 crossref_primary_10_3390_a14070208 crossref_primary_10_1109_JSEN_2023_3234980 crossref_primary_10_1016_j_asoc_2023_110358 crossref_primary_10_1109_TIM_2023_3318686 crossref_primary_10_1109_TII_2023_3268407 crossref_primary_10_3390_jtaer18040110 crossref_primary_10_1016_j_jmsy_2021_12_003 crossref_primary_10_1109_ACCESS_2024_3430010 crossref_primary_10_1016_j_asoc_2021_107755 crossref_primary_10_1038_s41598_021_04545_5 crossref_primary_10_1088_1361_6501_ace278 crossref_primary_10_3390_s25010224 crossref_primary_10_34133_research_0176 crossref_primary_10_35377_saucis_04_02_912154 crossref_primary_10_1016_j_measurement_2022_110698 crossref_primary_10_1177_01423312231157118 crossref_primary_10_3390_machines11111029 crossref_primary_10_1016_j_eswa_2023_120957 crossref_primary_10_1186_s10033_021_00587_y crossref_primary_10_1007_s00170_023_12356_3 crossref_primary_10_1016_j_asoc_2024_112007 crossref_primary_10_1109_TIM_2022_3173278 crossref_primary_10_1088_1361_6501_ac8893 crossref_primary_10_23919_JSEE_2023_000129 crossref_primary_10_1016_j_jmsy_2022_11_012 crossref_primary_10_1109_JSEN_2023_3323276 crossref_primary_10_1088_1361_6501_ad5460 crossref_primary_10_1177_14759217241262956 crossref_primary_10_1109_TSMC_2024_3461668 crossref_primary_10_1016_j_apenergy_2024_123773 crossref_primary_10_1063_5_0130984 crossref_primary_10_1109_JSEN_2025_3529479 crossref_primary_10_1016_j_ress_2021_108017 crossref_primary_10_1088_1361_6501_ad99f4 crossref_primary_10_1016_j_apacoust_2022_108703 crossref_primary_10_1109_TIM_2023_3318747 crossref_primary_10_1016_j_asoc_2022_109554 crossref_primary_10_1007_s11465_021_0650_6 crossref_primary_10_3390_app13020718 crossref_primary_10_1109_TIM_2023_3314809 crossref_primary_10_1109_TR_2024_3381579 crossref_primary_10_1016_j_measurement_2023_112833 crossref_primary_10_1063_5_0174359 crossref_primary_10_1109_TII_2023_3243929 crossref_primary_10_1088_1361_6501_ad3293 crossref_primary_10_1016_j_isatra_2024_08_033 crossref_primary_10_1109_TNNLS_2022_3202234 crossref_primary_10_1088_1361_6501_ad356e crossref_primary_10_3390_en16104164 crossref_primary_10_1016_j_oceaneng_2024_118139 crossref_primary_10_1109_TIM_2023_3259031 crossref_primary_10_3390_math11143113 crossref_primary_10_1177_00202940221126497 |
| Cites_doi | 10.3390/s20010166 10.1016/j.ymssp.2018.03.025 10.1109/5.726791 10.1162/neco.1997.9.8.1735 10.1016/j.ymssp.2018.05.050 10.1016/j.sigpro.2019.03.019 10.1038/323533a0 10.3115/v1/D14-1179 10.1109/ACCESS.2019.2907131 10.1109/ACCESS.2019.2962734 10.1109/TIE.2018.2838070 10.18653/v1/P16-2034 10.3390/s19092034 10.1007/s10845-015-1110-0 10.1109/TIE.2016.2627020 10.1016/j.neucom.2018.06.078 10.1109/TII.2019.2912428 10.1016/j.jsv.2016.05.027 10.1016/j.ymssp.2019.106587 10.1109/ACCESS.2019.2948661 10.1016/j.isatra.2020.08.010 10.1038/nature14539 10.1088/1361-6501/ab3072 10.18653/v1/D15-1166 10.3390/en12203937 10.1109/TIE.2017.2762639 10.1016/j.asoc.2019.105919 10.18653/v1/N16-1174 10.1016/j.neucom.2018.04.048 10.1016/j.ymssp.2017.11.024 10.1109/JSEN.2020.2980596 10.1016/j.measurement.2020.108202 10.3390/app9091823 10.1016/j.compind.2019.01.001 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier B.V. |
| Copyright_xml | – notice: 2020 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2020.106829 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-9681 |
| ExternalDocumentID | 10_1016_j_asoc_2020_106829 S1568494620307675 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- AATTM AAXKI AAYWO AAYXX ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c300t-a1e0b32975101be72a8b7d482197dd9e02f5fb659380923b2115a248d97394493 |
| IEDL.DBID | .~1 |
| ISSN | 1568-4946 |
| IngestDate | Tue Jul 01 01:50:07 EDT 2025 Thu Apr 24 23:08:45 EDT 2025 Fri Feb 23 02:46:38 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Bearing fault diagnosis Attention mechanism Interpretability |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c300t-a1e0b32975101be72a8b7d482197dd9e02f5fb659380923b2115a248d97394493 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_asoc_2020_106829 crossref_primary_10_1016_j_asoc_2020_106829 elsevier_sciencedirect_doi_10_1016_j_asoc_2020_106829 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | December 2020 2020-12-00 |
| PublicationDateYYYYMMDD | 2020-12-01 |
| PublicationDate_xml | – month: 12 year: 2020 text: December 2020 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | LeCun, Bengio, Hinton (b4) 2015; 521 Li, Chen, Shen, Yang, Zhu (b23) 2019; 30 Lecun, Bottou, Bengio, Haffner (b34) 1998; 86 Bearing data center Lei, Yang, Jiang, Jia, Li, Nandi (b3) 2020; 138 Pan, He, Tang, Meng (b13) 2018; 64 Li, Zhang, Ding (b29) 2019; 161 K. Cho, B. Van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. V. Mnih, N. Heess, A. Graves, K. Kavukcuoglu, Recurrent models of visual attention, in: Advances in Neural Information Processing Systems 27, Vol. 3, pp. 2204–2212. Lu, Liang, Cheng, Meng, Yang, Zhang (b12) 2017; 64 Shao, Wang, Yan (b24) 2019; 106 A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, u. Kaiser, I. Polosukhin, Attention is all you need, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5998–6008. Janssens, Slavkovikj, Vervisch, Stockman, Loccufier, Verstockt, Van de Walle, Van Hoecke (b5) 2016; 377 Wei, Changqing, Dong, Liang, Xingxing, Zhongkui (b18) 2020; 8 K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, Y. Bengio, Show, attend and tell: Neural image caption generation with visual attention, in: Proceedings of the 32nd International Conference on Machine Learning, pp. 2048–2057. M.T. Luong, H. Pham, C.D. Manning, Effective approaches to attention-based neural machine translation, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412–1421. Huang, Fu, Feng, Kuang (b30) 2019; 12 Zhao, Wu, Qiao, Wang, Chen (b2) 2019; 66 Wang, Mo, Zhang, Miao (b17) 2019; 7 Tang, Shen, Wang, Li, Huang, Zhu (b19) 2018; 305 Qi, Shen, Zhu, Jiang, Shi, Zhu (b9) 2019; 7 Chung, Gulcehre, Cho, Bengio (b37) 2014 Jiang, Lee, Zeng (b32) 2019; 20 Rumelhart, Hinton, Williams (b42) 1986; 323 Li, Huang, Ji (b8) 2019; 19 Jia, Lei, Lu, Xing (b25) 2018; 110 Chen, Peng, Zhu, Li (b31) 2020; 86 D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: ICLR 2015: International Conference on Learning Representations 2015. Xu, Zheng, Guo, Wu, Zheng (b22) 2019; 9 Ma, Sun, Chen, Zhang, Yan (b10) 2019; 15 Zhao, Kang, Tang, Pecht (b16) 2018; 65 Bahdanau, Cho, Bengio (b27) 2015 . Zhao, Yan, Chen, Mao, Wang, Gao (b6) 2019; 115 Zhuang, Lv, Xu, Huang, Qin (b14) 2019; 9 Zhao, Li, Wu, Sun, Wang, Yan, Chen (b15) 2020 Khan, Yairi (b1) 2018; 107 Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, Hierarchical attention networks for document classification, in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480–1489. Hoang, Kang (b7) 2019; 335 Santos, Maudes, Bustillo (b20) 2015; 29 Li, Zhao, Sun, Yan, Chen (b11) 2020; 20 Wu, Zhao, Sun, Yan, Chen (b21) 2020; 166 Hochreiter, Schmidhuber (b35) 1997; 9 P. Zhou, W. Shi, J. Tian, Z.Y. Qi, B.C. Li, H.W. Hao, B. Xu, Attention-based bidirectional long short-term memory networks for relation classification, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Acl 2016), Vol. 2, pp. 207–212. Wu (10.1016/j.asoc.2020.106829_b21) 2020; 166 10.1016/j.asoc.2020.106829_b26 Rumelhart (10.1016/j.asoc.2020.106829_b42) 1986; 323 Shao (10.1016/j.asoc.2020.106829_b24) 2019; 106 10.1016/j.asoc.2020.106829_b28 Li (10.1016/j.asoc.2020.106829_b11) 2020; 20 Tang (10.1016/j.asoc.2020.106829_b19) 2018; 305 Hochreiter (10.1016/j.asoc.2020.106829_b35) 1997; 9 Jia (10.1016/j.asoc.2020.106829_b25) 2018; 110 Zhao (10.1016/j.asoc.2020.106829_b15) 2020 10.1016/j.asoc.2020.106829_b40 Li (10.1016/j.asoc.2020.106829_b8) 2019; 19 10.1016/j.asoc.2020.106829_b41 Li (10.1016/j.asoc.2020.106829_b29) 2019; 161 10.1016/j.asoc.2020.106829_b43 Lei (10.1016/j.asoc.2020.106829_b3) 2020; 138 Zhao (10.1016/j.asoc.2020.106829_b16) 2018; 65 LeCun (10.1016/j.asoc.2020.106829_b4) 2015; 521 Xu (10.1016/j.asoc.2020.106829_b22) 2019; 9 Qi (10.1016/j.asoc.2020.106829_b9) 2019; 7 Pan (10.1016/j.asoc.2020.106829_b13) 2018; 64 Santos (10.1016/j.asoc.2020.106829_b20) 2015; 29 Zhao (10.1016/j.asoc.2020.106829_b6) 2019; 115 10.1016/j.asoc.2020.106829_b36 Li (10.1016/j.asoc.2020.106829_b23) 2019; 30 10.1016/j.asoc.2020.106829_b39 10.1016/j.asoc.2020.106829_b38 Janssens (10.1016/j.asoc.2020.106829_b5) 2016; 377 Zhao (10.1016/j.asoc.2020.106829_b2) 2019; 66 10.1016/j.asoc.2020.106829_b33 Huang (10.1016/j.asoc.2020.106829_b30) 2019; 12 Ma (10.1016/j.asoc.2020.106829_b10) 2019; 15 Wei (10.1016/j.asoc.2020.106829_b18) 2020; 8 Lu (10.1016/j.asoc.2020.106829_b12) 2017; 64 Chen (10.1016/j.asoc.2020.106829_b31) 2020; 86 Chung (10.1016/j.asoc.2020.106829_b37) 2014 Wang (10.1016/j.asoc.2020.106829_b17) 2019; 7 Khan (10.1016/j.asoc.2020.106829_b1) 2018; 107 Hoang (10.1016/j.asoc.2020.106829_b7) 2019; 335 Zhuang (10.1016/j.asoc.2020.106829_b14) 2019; 9 Jiang (10.1016/j.asoc.2020.106829_b32) 2019; 20 Lecun (10.1016/j.asoc.2020.106829_b34) 1998; 86 Bahdanau (10.1016/j.asoc.2020.106829_b27) 2015 |
| References_xml | – volume: 66 start-page: 2143 year: 2019 end-page: 2153 ident: b2 article-title: Enhanced sparse period-group lasso for bearing fault diagnosis publication-title: IEEE Trans. Ind. Electron. – volume: 335 start-page: 327 year: 2019 end-page: 335 ident: b7 article-title: A survey on deep learning based bearing fault diagnosis publication-title: Neurocomputing – reference: Bearing data center, – volume: 19 year: 2019 ident: b8 article-title: Bearing fault diagnosis with a feature fusion method based on an ensemble convolutional neural network and deep neural network publication-title: Sensors (Basel) – year: 2014 ident: b37 article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling – volume: 107 start-page: 241 year: 2018 end-page: 265 ident: b1 article-title: A review on the application of deep learning in system health management publication-title: Mech. Syst. Signal Process. – volume: 377 start-page: 331 year: 2016 end-page: 345 ident: b5 article-title: Convolutional neural network based fault detection for rotating machinery publication-title: J. Sound Vib. – reference: D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, in: ICLR 2015: International Conference on Learning Representations 2015. – reference: A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, u. Kaiser, I. Polosukhin, Attention is all you need, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5998–6008. – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: b34 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE – reference: M.T. Luong, H. Pham, C.D. Manning, Effective approaches to attention-based neural machine translation, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412–1421. – reference: V. Mnih, N. Heess, A. Graves, K. Kavukcuoglu, Recurrent models of visual attention, in: Advances in Neural Information Processing Systems 27, Vol. 3, pp. 2204–2212. – volume: 86 year: 2020 ident: b31 article-title: A novel deep learning method based on attention mechanism for bearing remaining useful life prediction publication-title: Appl. Soft Comput. – volume: 64 start-page: 2296 year: 2017 end-page: 2305 ident: b12 article-title: Deep model based domain adaptation for fault diagnosis publication-title: IEEE Trans. Ind. Electron. – volume: 30 year: 2019 ident: b23 article-title: Enhanced generative adversarial networks for fault diagnosis of rotating machinery with imbalanced data publication-title: Meas. Sci. Technol. – volume: 106 start-page: 85 year: 2019 end-page: 93 ident: b24 article-title: Generative adversarial networks for data augmentation in machine fault diagnosis publication-title: Comput. Ind. – volume: 9 year: 2019 ident: b22 article-title: SDD-CNN: Small data-driven convolution neural networks for subtle roller defect inspection publication-title: Appl. Sci.-Basel – volume: 305 start-page: 1 year: 2018 end-page: 14 ident: b19 article-title: Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis publication-title: Neurocomputing – reference: Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, Hierarchical attention networks for document classification, in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480–1489. – volume: 166 year: 2020 ident: b21 article-title: Few-shot transfer learning for intelligent fault diagnosis of machine publication-title: Measurement – year: 2015 ident: b27 article-title: Neural machine translation by jointly learning to align and translate publication-title: ICLR 2015 : International Conference on Learning Representations 2015 – volume: 12 year: 2019 ident: b30 article-title: Bearing fault diagnosis based on shallow multi-scale convolutional neural network with attention publication-title: Energies – volume: 115 start-page: 213 year: 2019 end-page: 237 ident: b6 article-title: Deep learning and its applications to machine health monitoring publication-title: Mech. Syst. Signal Process. – volume: 8 start-page: 1975 year: 2020 end-page: 1985 ident: b18 article-title: An intelligent deep feature learning method with improved activation functions for machine fault diagnosis publication-title: IEEE Access – volume: 323 start-page: 533 year: 1986 end-page: 536 ident: b42 article-title: Learning representations by back propagating errors publication-title: Nature – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b35 article-title: Long short-term memory publication-title: Neural Comput. – volume: 161 start-page: 136 year: 2019 end-page: 154 ident: b29 article-title: Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism publication-title: Signal Process. – volume: 65 start-page: 4290 year: 2018 end-page: 4300 ident: b16 article-title: Deep residual networks with dynamically weighted wavelet coefficients for fault diagnosis of planetary gearboxes publication-title: IEEE Trans. Ind. Electron. – volume: 64 start-page: 443 year: 2018 end-page: 452 ident: b13 article-title: An improved bearing fault diagnosis method using one-dimensional CNN and LSTM publication-title: Stroj. Vestn. - J. Mech. Eng. – volume: 9 year: 2019 ident: b14 article-title: A deep learning method for bearing fault diagnosis through stacked residual dilated convolutions publication-title: Appl. Sci. – volume: 7 start-page: 42373 year: 2019 end-page: 42383 ident: b17 article-title: A deep learning method for bearing fault diagnosis based on time-frequency image publication-title: IEEE Access – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b4 article-title: Deep learning publication-title: Nature – reference: . – year: 2020 ident: b15 article-title: Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study publication-title: ISA Trans. – volume: 20 start-page: 8364 year: 2020 end-page: 8373 ident: b11 article-title: Adaptive channel weighted CNN with multisensor fusion for condition monitoring of helicopter transmission system publication-title: IEEE Sensors J. – volume: 20 year: 2019 ident: b32 article-title: Time series multiple channel convolutional neural network with attention-based long short-term memory for predicting bearing remaining useful life publication-title: Sensors (Basel) – reference: K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, Y. Bengio, Show, attend and tell: Neural image caption generation with visual attention, in: Proceedings of the 32nd International Conference on Machine Learning, pp. 2048–2057. – reference: K. Cho, B. Van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. – volume: 110 start-page: 349 year: 2018 end-page: 367 ident: b25 article-title: Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization publication-title: Mech. Syst. Signal Process. – volume: 138 year: 2020 ident: b3 article-title: Applications of machine learning to machine fault diagnosis: A review and roadmap publication-title: Mech. Syst. Signal Process. – reference: P. Zhou, W. Shi, J. Tian, Z.Y. Qi, B.C. Li, H.W. Hao, B. Xu, Attention-based bidirectional long short-term memory networks for relation classification, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Acl 2016), Vol. 2, pp. 207–212. – volume: 29 start-page: 333 year: 2015 end-page: 351 ident: b20 article-title: Identifying maximum imbalance in datasets for fault diagnosis of gearboxes publication-title: J. Intell. Manuf. – volume: 7 start-page: 152552 year: 2019 end-page: 152563 ident: b9 article-title: A new deep fusion network for automatic mechanical fault feature learning publication-title: IEEE Access – volume: 15 start-page: 6415 year: 2019 end-page: 6424 ident: b10 article-title: A deep coupled network for health state assessment of cutting tools based on fusion of multisensory signals publication-title: IEEE Trans. Ind. Inform. – volume: 20 issue: 1 year: 2019 ident: 10.1016/j.asoc.2020.106829_b32 article-title: Time series multiple channel convolutional neural network with attention-based long short-term memory for predicting bearing remaining useful life publication-title: Sensors (Basel) doi: 10.3390/s20010166 – volume: 110 start-page: 349 year: 2018 ident: 10.1016/j.asoc.2020.106829_b25 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 – volume: 86 start-page: 2278 issue: 11 year: 1998 ident: 10.1016/j.asoc.2020.106829_b34 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.asoc.2020.106829_b35 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – volume: 115 start-page: 213 year: 2019 ident: 10.1016/j.asoc.2020.106829_b6 article-title: Deep learning and its applications to machine health monitoring publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2018.05.050 – volume: 161 start-page: 136 year: 2019 ident: 10.1016/j.asoc.2020.106829_b29 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 – ident: 10.1016/j.asoc.2020.106829_b39 – volume: 323 start-page: 533 issue: 6088 year: 1986 ident: 10.1016/j.asoc.2020.106829_b42 article-title: Learning representations by back propagating errors publication-title: Nature doi: 10.1038/323533a0 – ident: 10.1016/j.asoc.2020.106829_b36 doi: 10.3115/v1/D14-1179 – volume: 7 start-page: 42373 year: 2019 ident: 10.1016/j.asoc.2020.106829_b17 article-title: A deep learning method for bearing fault diagnosis based on time-frequency image publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2907131 – volume: 8 start-page: 1975 year: 2020 ident: 10.1016/j.asoc.2020.106829_b18 article-title: An intelligent deep feature learning method with improved activation functions for machine fault diagnosis publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2962734 – volume: 66 start-page: 2143 issue: 3 year: 2019 ident: 10.1016/j.asoc.2020.106829_b2 article-title: Enhanced sparse period-group lasso for bearing fault diagnosis publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2018.2838070 – ident: 10.1016/j.asoc.2020.106829_b33 doi: 10.18653/v1/P16-2034 – volume: 19 issue: 9 year: 2019 ident: 10.1016/j.asoc.2020.106829_b8 article-title: Bearing fault diagnosis with a feature fusion method based on an ensemble convolutional neural network and deep neural network publication-title: Sensors (Basel) doi: 10.3390/s19092034 – volume: 29 start-page: 333 issue: 2 year: 2015 ident: 10.1016/j.asoc.2020.106829_b20 article-title: Identifying maximum imbalance in datasets for fault diagnosis of gearboxes publication-title: J. Intell. Manuf. doi: 10.1007/s10845-015-1110-0 – volume: 64 start-page: 2296 issue: 3 year: 2017 ident: 10.1016/j.asoc.2020.106829_b12 article-title: Deep model based domain adaptation for fault diagnosis publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2016.2627020 – volume: 335 start-page: 327 year: 2019 ident: 10.1016/j.asoc.2020.106829_b7 article-title: A survey on deep learning based bearing fault diagnosis publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.06.078 – volume: 15 start-page: 6415 issue: 12 year: 2019 ident: 10.1016/j.asoc.2020.106829_b10 article-title: A deep coupled network for health state assessment of cutting tools based on fusion of multisensory signals publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2019.2912428 – volume: 377 start-page: 331 year: 2016 ident: 10.1016/j.asoc.2020.106829_b5 article-title: Convolutional neural network based fault detection for rotating machinery publication-title: J. Sound Vib. doi: 10.1016/j.jsv.2016.05.027 – volume: 138 year: 2020 ident: 10.1016/j.asoc.2020.106829_b3 article-title: Applications of machine learning to machine fault diagnosis: A review and roadmap publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2019.106587 – volume: 7 start-page: 152552 year: 2019 ident: 10.1016/j.asoc.2020.106829_b9 article-title: A new deep fusion network for automatic mechanical fault feature learning publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2948661 – year: 2015 ident: 10.1016/j.asoc.2020.106829_b27 article-title: Neural machine translation by jointly learning to align and translate – year: 2020 ident: 10.1016/j.asoc.2020.106829_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 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.asoc.2020.106829_b4 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 30 issue: 11 year: 2019 ident: 10.1016/j.asoc.2020.106829_b23 article-title: Enhanced generative adversarial networks for fault diagnosis of rotating machinery with imbalanced data publication-title: Meas. Sci. Technol. doi: 10.1088/1361-6501/ab3072 – ident: 10.1016/j.asoc.2020.106829_b38 – ident: 10.1016/j.asoc.2020.106829_b40 doi: 10.18653/v1/D15-1166 – volume: 12 issue: 20 year: 2019 ident: 10.1016/j.asoc.2020.106829_b30 article-title: Bearing fault diagnosis based on shallow multi-scale convolutional neural network with attention publication-title: Energies doi: 10.3390/en12203937 – volume: 65 start-page: 4290 issue: 5 year: 2018 ident: 10.1016/j.asoc.2020.106829_b16 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: 86 year: 2020 ident: 10.1016/j.asoc.2020.106829_b31 article-title: A novel deep learning method based on attention mechanism for bearing remaining useful life prediction publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.105919 – year: 2014 ident: 10.1016/j.asoc.2020.106829_b37 – ident: 10.1016/j.asoc.2020.106829_b41 doi: 10.18653/v1/N16-1174 – volume: 64 start-page: 443 issue: 7–8 year: 2018 ident: 10.1016/j.asoc.2020.106829_b13 article-title: An improved bearing fault diagnosis method using one-dimensional CNN and LSTM publication-title: Stroj. Vestn. - J. Mech. Eng. – volume: 305 start-page: 1 year: 2018 ident: 10.1016/j.asoc.2020.106829_b19 article-title: Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.04.048 – ident: 10.1016/j.asoc.2020.106829_b28 – volume: 107 start-page: 241 year: 2018 ident: 10.1016/j.asoc.2020.106829_b1 article-title: A review on the application of deep learning in system health management publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2017.11.024 – volume: 20 start-page: 8364 issue: 15 year: 2020 ident: 10.1016/j.asoc.2020.106829_b11 article-title: Adaptive channel weighted CNN with multisensor fusion for condition monitoring of helicopter transmission system publication-title: IEEE Sensors J. doi: 10.1109/JSEN.2020.2980596 – volume: 166 year: 2020 ident: 10.1016/j.asoc.2020.106829_b21 article-title: Few-shot transfer learning for intelligent fault diagnosis of machine publication-title: Measurement doi: 10.1016/j.measurement.2020.108202 – volume: 9 issue: 9 year: 2019 ident: 10.1016/j.asoc.2020.106829_b14 article-title: A deep learning method for bearing fault diagnosis through stacked residual dilated convolutions publication-title: Appl. Sci. doi: 10.3390/app9091823 – volume: 106 start-page: 85 year: 2019 ident: 10.1016/j.asoc.2020.106829_b24 article-title: Generative adversarial networks for data augmentation in machine fault diagnosis publication-title: Comput. Ind. doi: 10.1016/j.compind.2019.01.001 – ident: 10.1016/j.asoc.2020.106829_b26 – ident: 10.1016/j.asoc.2020.106829_b43 – volume: 9 issue: 7 year: 2019 ident: 10.1016/j.asoc.2020.106829_b22 article-title: SDD-CNN: Small data-driven convolution neural networks for subtle roller defect inspection publication-title: Appl. Sci.-Basel |
| SSID | ssj0016928 |
| Score | 2.607527 |
| Snippet | Condition monitoring and fault diagnosis of bearings play important roles in production safety and limiting the cost of maintenance on a reasonable level.... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 106829 |
| SubjectTerms | Attention mechanism Bearing fault diagnosis Interpretability |
| Title | Interpreting network knowledge with attention mechanism for bearing fault diagnosis |
| URI | https://dx.doi.org/10.1016/j.asoc.2020.106829 |
| Volume | 97 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07a8MwEBYhXbr0XZo-goZuxY38lDSG0JC-QmkayGYkWwaXxA1Nsva3986yTQslQydhoQP743wP8d0dIdecJWDjssjRWSidQCjlaKaFY7IEvKfvcR5icfLzOBpNg4dZOGuRQV0Lg7TKyvZbm15a62qnV6HZW-Z5bwKZhwhkEHmopxD3YgV7wFHLb78amocbyXK-Kh528HRVOGM5XgoQgBzRw41IlGHmH87ph8MZHpC9KlKkffsyh6RliiOyX09hoNVPeUwmDW8QvBAtLK2bNndlFG9aKXbRLHmNdGGw1jdfLSiEq1SDoqNYpjbzNU0t7y5fnZDp8O5tMHKqUQlO4jO2dpRrmPaxSha-TBvuKaF5GgiwRzxNpWFeFmY6CqUvGIR0GtK-UHmBSCXHyljpn5J28VGYM0JD7hthIqF0VnZzl5CRuSqBhWmWKNMhbo1RnFR9xHGcxTyuCWPvMeIaI66xxbVDbhqZpe2isfV0WEMf_9KFGMz8Frnzf8pdkF18siSVS9Jef27MFYQaa90tdalLdvqD16cXXO8fR-NvsCLT6w |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1La8JAEB6sHtpL36X2uYfeSnBNssnmKFLR-rio4C3sJhuwqJWq_78zyUZaKB56Cmx2IPmYzGPzzQzAS8gTtHFZ4OhMRI4vlXI019IxWYLe03PDUFBx8nAUdKf--0zMKtAua2GIVmltf2HTc2ttVxoWzcZ6Pm-MMfOQfuQHLukpxr1HUKPuVKIKtVav3x3tfyYEUT5ilfY7JGBrZwqal0IQME10aSGQeaT5h3_64XM653Bqg0XWKp7nAipmdQln5SAGZr_LKxjvqYPoiNiqYHaz_XEZo8NWRo00c2ojWxoq951vlgwjVqZR10ksU7vFlqUF9W6-uYZp523S7jp2WoKTeJxvHdU0XHtUKItvpk3oKqnD1JdoksI0jQx3M5HpQESe5BjVacz8hHJ9mUYhFcdG3g1UV58rcwtMhJ6RJpBKZ3lD9wiTsqZK8MI1T5SpQ7PEKE5sK3GaaLGIS87YR0y4xoRrXOBah9e9zLpopHFwtyihj3-pQ4yW_oDc3T_lnuG4OxkO4kFv1L-HE7pTcFYeoLr92plHjDy2-slq1jdfPtUH |
| 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=Interpreting+network+knowledge+with+attention+mechanism+for+bearing+fault+diagnosis&rft.jtitle=Applied+soft+computing&rft.au=Yang%2C+Zhi-bo&rft.au=Zhang%2C+Jun-peng&rft.au=Zhao%2C+Zhi-bin&rft.au=Zhai%2C+Zhi&rft.date=2020-12-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.eissn=1872-9681&rft.volume=97&rft_id=info:doi/10.1016%2Fj.asoc.2020.106829&rft.externalDocID=S1568494620307675 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |