Multi-branch global Transformer‐assisted network for fault diagnosis
Fault Diagnosis (FD) is critical in smart manufacturing, enabling predictive maintenance, reducing operational costs, and enhancing system reliability. To deal with this task more accurately, this paper proposes a generative, effective, and novel framework, a multi-branch global Transformer-assisted...
Saved in:
| Published in: | Applied soft computing Vol. 182; p. 113572 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01.10.2025
|
| Subjects: | |
| ISSN: | 1568-4946 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Fault Diagnosis (FD) is critical in smart manufacturing, enabling predictive maintenance, reducing operational costs, and enhancing system reliability. To deal with this task more accurately, this paper proposes a generative, effective, and novel framework, a multi-branch global Transformer-assisted network (MBGTNet), for accurate FD. First, a multi-branch global-wide one-dimension convolution operation (MBG-WideConv1D) is proposed to obtain global features in different views. Meanwhile, a Transformer assist scheme (TAS) is designed to leverage the Transformer's global feature extraction capacity. The features extracted by the Transformer are fused with those extracted with MBG-WideConv1D by minimizing their pairwise correlation alignment (CORAL) distances. Benefiting from the well-designed MBG-WideConv1D and TAS, the global features hidden in the raw signals are fully extracted from multiple viewpoints. Each branch of global features is then fed into a one-dimension convolutional neural network (1DCNN) to extract local features in a multi-supervised scheme (MSS) that helps each branch learn thoroughly. Furthermore, the proposed method employs a local feature correlation enhancement scheme (LFCS) to reduce distribution differences and increase robustness among the local features of each branch. As a result, the final features used for FD are a fusion of multi-view global and local features with strong robustness, enabling accurate FD in noisy environments. Comparative experiments on four datasets, including CWRU, MFPT, SU Bearing, and SU Gear, validate the proposed method's effectiveness, achieving over 99.6 % accuracy across four datasets. Moreover, the TAS and LFCS's generalities have been demonstrated on two 1DCNNs and hybrid CNN-LSTMs with four subsets. Also, the effectiveness of each component in the proposed framework has been thoroughly analyzed.
•The TAS ensures global feature extraction without meta-information loss.•The MB-WideConv1D extracts multi-global features.•The MSS guides each 1DCNN to learn local features thoroughly.•The LFCS increases the robustness of local features.•MBGTNet achieves an average accuracy of over 99.6 % for fault diagnosis. |
|---|---|
| AbstractList | Fault Diagnosis (FD) is critical in smart manufacturing, enabling predictive maintenance, reducing operational costs, and enhancing system reliability. To deal with this task more accurately, this paper proposes a generative, effective, and novel framework, a multi-branch global Transformer-assisted network (MBGTNet), for accurate FD. First, a multi-branch global-wide one-dimension convolution operation (MBG-WideConv1D) is proposed to obtain global features in different views. Meanwhile, a Transformer assist scheme (TAS) is designed to leverage the Transformer's global feature extraction capacity. The features extracted by the Transformer are fused with those extracted with MBG-WideConv1D by minimizing their pairwise correlation alignment (CORAL) distances. Benefiting from the well-designed MBG-WideConv1D and TAS, the global features hidden in the raw signals are fully extracted from multiple viewpoints. Each branch of global features is then fed into a one-dimension convolutional neural network (1DCNN) to extract local features in a multi-supervised scheme (MSS) that helps each branch learn thoroughly. Furthermore, the proposed method employs a local feature correlation enhancement scheme (LFCS) to reduce distribution differences and increase robustness among the local features of each branch. As a result, the final features used for FD are a fusion of multi-view global and local features with strong robustness, enabling accurate FD in noisy environments. Comparative experiments on four datasets, including CWRU, MFPT, SU Bearing, and SU Gear, validate the proposed method's effectiveness, achieving over 99.6 % accuracy across four datasets. Moreover, the TAS and LFCS's generalities have been demonstrated on two 1DCNNs and hybrid CNN-LSTMs with four subsets. Also, the effectiveness of each component in the proposed framework has been thoroughly analyzed.
•The TAS ensures global feature extraction without meta-information loss.•The MB-WideConv1D extracts multi-global features.•The MSS guides each 1DCNN to learn local features thoroughly.•The LFCS increases the robustness of local features.•MBGTNet achieves an average accuracy of over 99.6 % for fault diagnosis. |
| ArticleNumber | 113572 |
| Author | Kim, Chang-Soo Shao, Xiaorui |
| Author_xml | – sequence: 1 givenname: Xiaorui orcidid: 0000-0001-5454-6920 surname: Shao fullname: Shao, Xiaorui email: xrshao@gzu.edu.cn organization: Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, Guizhou 550025, China – sequence: 2 givenname: Chang-Soo orcidid: 0000-0003-2168-7983 surname: Kim fullname: Kim, Chang-Soo email: cskim@pknu.ac.kr organization: Information Systems, Pukyong National University, Busan 608737, South Korea |
| BookMark | eNp9j0FOwzAQRb0oEm3hAqxygQTbiVNHYoMqCkhFbMraGtvj4pLGyA4gdhyBM3ISXJU1q9Ho_zeaNyOTIQxIyAWjFaOsvdxVkIKpOOWiYqwWCz4hUyZaWTZd056SWUo7mosdl1OyenjrR1_qCIN5LrZ90NAXm7wlF-Ie48_XN6Tk04i2GHD8CPGlyEnhIHOF9bAdQo7PyImDPuH535yTp9XNZnlXrh9v75fX69JwUY9lK0EwwaSuBW24lrCwsNC65s4KCdgwl0PrOAAFi1R3wLQxbcu47EAzW88JP941MaQU0anX6PcQPxWj6mCvdupgrw726mifoasjhPmzd49RJeNxMGh9RDMqG_x_-C8BgGmb |
| Cites_doi | 10.1016/j.compind.2018.11.003 10.1109/TIM.2021.3118090 10.1007/s12206-008-0603-6 10.1016/j.ins.2024.121126 10.1016/j.engappai.2022.105794 10.21629/JSEE.2017.01.18 10.1109/TIE.2018.2844805 10.1016/j.eswa.2022.119057 10.1016/j.knosys.2024.111609 10.1016/j.asoc.2024.112324 10.1016/S0888-3270(03)00071-2 10.1016/j.jprocont.2023.103069 10.1016/j.ress.2024.110198 10.1006/mssp.2001.1462 10.1016/j.asoc.2021.107702 10.4324/9781003116929-18 10.1016/j.jmsy.2023.02.018 10.1016/j.neucom.2022.04.111 10.1109/TIE.2015.2417501 10.1007/s10845-020-01600-2 10.1109/TFUZZ.2024.3411389 10.1007/s10845-013-0772-8 10.1109/TII.2017.2672988 10.1016/j.compind.2018.12.001 10.1016/j.compind.2020.103378 10.1016/j.eswa.2023.121216 10.1007/s10462-021-09993-z 10.1109/TSMC.2017.2754287 10.1109/TII.2018.2864759 10.1016/j.apenergy.2023.122252 10.1016/j.ymssp.2015.04.021 10.1038/nature14539 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier B.V. |
| Copyright_xml | – notice: 2025 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2025.113572 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_asoc_2025_113572 S156849462500883X |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ 9DU AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABFRF ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFO ACGFS ACLOT ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGHFR AGQPQ AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFKBS 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- ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- ~HD AAYXX CITATION |
| ID | FETCH-LOGICAL-c253t-68a51518b35042b8a7da7bb32fd58ae41f518df2aa0ade0b9a1bcc661289ab1d3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001533753500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1568-4946 |
| IngestDate | Sat Nov 29 06:50:28 EST 2025 Wed Dec 10 14:40:34 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | LN PV TAS MHA DSMT-1DCNN multi-view global features DL-MSCNN RNN MBGTNet FFT DWT WARS WDCNNProposed IR GMP RF FD MSCNN WDCNN ANN Transformer CORAL GFC LFCS SVM BN SA AWF Fault diagnosis 2DCNN NLP CBAM SNR ACEL ProposedWo-MSS multi-supervised algorithm ViT CWT 1DCNN CE SU LSTM OR ProposedWo-LFCS MBLF MSS MGF CNN-LSTMProposed WSCNN-GMPProposed MBG-WideConv1D MFPT MSCNN-LSTMPropsoed CNNCombine DB |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c253t-68a51518b35042b8a7da7bb32fd58ae41f518df2aa0ade0b9a1bcc661289ab1d3 |
| ORCID | 0000-0001-5454-6920 0000-0003-2168-7983 |
| ParticipantIDs | crossref_primary_10_1016_j_asoc_2025_113572 elsevier_sciencedirect_doi_10_1016_j_asoc_2025_113572 |
| PublicationCentury | 2000 |
| PublicationDate | October 2025 2025-10-00 |
| PublicationDateYYYYMMDD | 2025-10-01 |
| PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE, ICLR 2021 - 9th Int. Conf. Learn. Represent. (2021). Wang, Xiahou, Zhang, He, Yang, Niu, Liu, Liu (bib44) 2024; 249 Shao, McAleer, Yan, Baldi (bib5) 2019; 15 Li, Lian, Guo, Zhao (bib2) 2015; 26 Qu, Sun, Qian, Wei, Zareipour (bib19) 2024; 355 Smith, Randall (bib50) 2015; 64–65 Chen, Huang, Yang, Xu, Zhang, Zhang (bib14) 2019; 106 Shao, Wang, Kim, Ra (bib33) 2021; 15 Lu, Cui, Hu, Yin (bib34) 2023; 213 Ge, Du, Zhang, Xu (bib9) 2004; 18 Jia, Chow, Yuan (bib35) 2023; 119 E. Bechhoefer, Condition Based Maintenance Fault Database for Testing Diagnostics and Prognostic Algorithms Huang, Zhang, Tang, Zhao (bib18) 2022; 55 Jin, Hou, Chen (bib42) 2022; 494 Zhang, Wang, Si, Wang (bib22) 2022; 71 (2013). . Lecun, Bengio, Hinton (bib13) 2015; 521 Shao, Soo Kim, Geun Kim (bib24) 2020; 65 Liu, Wang, Liu, Qin, Peng (bib12) 2021; 70 Shao, Kim (bib53) 2024; 679 An, Lu, Zhu, Wang, De Silva, Xia, Lu (bib15) 2023; 72 Shao, Li, Ra, Kim (bib26) 2024; 292 Sun, Zhao, Yan, Shao, Chen (bib4) 2017; 13 Jiang, Yang, Wang, Xu, Wang, Cheng (bib16) 2021; 110 Veltman, Pulle, De Doncker (bib38) 2017 Acheampong, Nunoo-Mensah, Chen (bib40) 2021 Liu, Huang, Jia (bib17) 2024 Wu, Jiang, Ding, Feng, Chen (bib20) 2019; 108 Zhao, Duan, Roy, Zhang (bib30) 2024; 249 Wen, Gao, Li (bib32) 2019; 49 Wu, Zheng (bib29) 2024; 79 Devlin, Chang, Lee, Toutanova (bib39) 2019; 1 Shao, Yan, Lu, Wang, Gao (bib3) 2020; 18 Jiang, He, Yan, Xie (bib23) 2019; 66 Shao, Lee, Kim (bib25) 2023 He, Zhang, Ren, Sun (bib46) 2016 Zhu, Qian, Zhang, He, Xu (bib45) 2023; 130 Chen, Zhang, Gao (bib28) 2021; 32 Z. Cui, W. Chen, Y. Chen, Multi-Scale Convolutional neural networks for time series classification, ArXiv:1603.06995. (n.d.) 169. Gao, Cecati, Ding (bib7) 2015; 62 Yang, Di, Han (bib10) 2008; 22 Wu, Triebe, Sutherland (bib36) 2023; 67 Sun, Feng, Saenko (bib47) 2016; 2016 Li, Zhang, Liu, Feng, Zhou, Duan (bib43) 2024 Sun, Saenko (bib48) 2016 Wang, Liu, Luo, Yang (bib37) 2023; 34 Gao, Cecati, Ding (bib6) 2015; 62 Shao, Kim (bib8) 2024; 236 Jiang, Wu, Zhu, Gao (bib31) 2024; 32 Zhang, Peng, Li, Chen, Zhang (bib21) 2017; 17 Wei, Chen, Yuan, Huang, Wen, Jiao (bib1) 2024; 167 Kingma, Ba (bib49) 2015 Jalayer, Orsenigo, Vercellis (bib27) 2021; 125 Samanta, Al-Balushi (bib11) 2003; 17 Wang (10.1016/j.asoc.2025.113572_bib37) 2023; 34 Zhu (10.1016/j.asoc.2025.113572_bib45) 2023; 130 Jin (10.1016/j.asoc.2025.113572_bib42) 2022; 494 Liu (10.1016/j.asoc.2025.113572_bib17) 2024 Jiang (10.1016/j.asoc.2025.113572_bib23) 2019; 66 Wu (10.1016/j.asoc.2025.113572_bib36) 2023; 67 10.1016/j.asoc.2025.113572_bib41 Wu (10.1016/j.asoc.2025.113572_bib20) 2019; 108 Devlin (10.1016/j.asoc.2025.113572_bib39) 2019; 1 Acheampong (10.1016/j.asoc.2025.113572_bib40) 2021 Shao (10.1016/j.asoc.2025.113572_bib8) 2024; 236 Chen (10.1016/j.asoc.2025.113572_bib14) 2019; 106 Qu (10.1016/j.asoc.2025.113572_bib19) 2024; 355 Shao (10.1016/j.asoc.2025.113572_bib24) 2020; 65 Wu (10.1016/j.asoc.2025.113572_bib29) 2024; 79 Lu (10.1016/j.asoc.2025.113572_bib34) 2023; 213 Shao (10.1016/j.asoc.2025.113572_bib3) 2020; 18 Li (10.1016/j.asoc.2025.113572_bib2) 2015; 26 Chen (10.1016/j.asoc.2025.113572_bib28) 2021; 32 Kingma (10.1016/j.asoc.2025.113572_bib49) 2015 Jiang (10.1016/j.asoc.2025.113572_bib16) 2021; 110 He (10.1016/j.asoc.2025.113572_bib46) 2016 Veltman (10.1016/j.asoc.2025.113572_bib38) 2017 10.1016/j.asoc.2025.113572_bib52 10.1016/j.asoc.2025.113572_bib51 Zhao (10.1016/j.asoc.2025.113572_bib30) 2024; 249 Shao (10.1016/j.asoc.2025.113572_bib5) 2019; 15 Liu (10.1016/j.asoc.2025.113572_bib12) 2021; 70 An (10.1016/j.asoc.2025.113572_bib15) 2023; 72 Gao (10.1016/j.asoc.2025.113572_bib7) 2015; 62 Shao (10.1016/j.asoc.2025.113572_bib33) 2021; 15 Sun (10.1016/j.asoc.2025.113572_bib4) 2017; 13 Samanta (10.1016/j.asoc.2025.113572_bib11) 2003; 17 Ge (10.1016/j.asoc.2025.113572_bib9) 2004; 18 Jia (10.1016/j.asoc.2025.113572_bib35) 2023; 119 Smith (10.1016/j.asoc.2025.113572_bib50) 2015; 64–65 Shao (10.1016/j.asoc.2025.113572_bib53) 2024; 679 Sun (10.1016/j.asoc.2025.113572_bib48) 2016 Wang (10.1016/j.asoc.2025.113572_bib44) 2024; 249 Lecun (10.1016/j.asoc.2025.113572_bib13) 2015; 521 Huang (10.1016/j.asoc.2025.113572_bib18) 2022; 55 Gao (10.1016/j.asoc.2025.113572_bib6) 2015; 62 Zhang (10.1016/j.asoc.2025.113572_bib22) 2022; 71 Jalayer (10.1016/j.asoc.2025.113572_bib27) 2021; 125 Zhang (10.1016/j.asoc.2025.113572_bib21) 2017; 17 Wei (10.1016/j.asoc.2025.113572_bib1) 2024; 167 Shao (10.1016/j.asoc.2025.113572_bib25) 2023 Wen (10.1016/j.asoc.2025.113572_bib32) 2019; 49 Li (10.1016/j.asoc.2025.113572_bib43) 2024 Shao (10.1016/j.asoc.2025.113572_bib26) 2024; 292 Sun (10.1016/j.asoc.2025.113572_bib47) 2016; 2016 Jiang (10.1016/j.asoc.2025.113572_bib31) 2024; 32 Yang (10.1016/j.asoc.2025.113572_bib10) 2008; 22 |
| References_xml | – volume: 249 year: 2024 ident: bib44 article-title: Convolutional preprocessing Transformer-based fault diagnosis for rectifier-filter circuits in nuclear power plants publication-title: Reliab. Eng. Syst. Saf. – volume: 2016 start-page: 2058 year: 2016 end-page: 2065 ident: bib47 article-title: Return of frustratingly easy domain adaptation publication-title: 30th AAAI Conf. Artif. Intell. AAAI – start-page: 770 year: 2016 end-page: 778 ident: bib46 article-title: Deep residual learning for image recognition, Proc. IEEE Comput. Soc. Conf. Comput. Vis publication-title: Pattern Recognit. 2016Decem – volume: 119 year: 2023 ident: bib35 article-title: GTFE-Net: a Gramian time frequency enhancement CNN for bearing fault diagnosis publication-title: Eng. Appl. Artif. Intell. – volume: 355 year: 2024 ident: bib19 article-title: Fault diagnosis for PV arrays considering dust impact based on transformed graphical features of characteristic curves and convolutional neural network with CBAM modules publication-title: Appl. Energy – volume: 130 year: 2023 ident: bib45 article-title: Multi-scale Transformer-CNN domain adaptation network for complex processes fault diagnosis publication-title: J. Process Control – reference: A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE, ICLR 2021 - 9th Int. Conf. Learn. Represent. (2021). – volume: 32 start-page: 971 year: 2021 end-page: 987 ident: bib28 article-title: Bearing fault diagnosis base on multi-scale CNN and LSTM model publication-title: J. Intell. Manuf. – start-page: 582 year: 2024 end-page: 590 ident: bib43 article-title: Research on transformer fault diagnosis method based on NRS-PSO-ANFIS, Meas publication-title: Sci. Technol. 1168 LNEE – reference: Z. Cui, W. Chen, Y. Chen, Multi-Scale Convolutional neural networks for time series classification, ArXiv:1603.06995. (n.d.) 169. – volume: 66 start-page: 3196 year: 2019 end-page: 3207 ident: bib23 article-title: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox publication-title: IEEE Trans. Ind. Electron – volume: 32 start-page: 4735 year: 2024 end-page: 4746 ident: bib31 article-title: Multimodel fusion health assessment for multistate industrial robot via fuzzy deep residual shrinkage network and versatile cluster publication-title: IEEE Trans. Fuzzy Syst. – volume: 22 start-page: 1716 year: 2008 end-page: 1725 ident: bib10 article-title: Random forests classifier for machine fault diagnosis, J publication-title: Mech. Sci. Technol. – volume: 72 start-page: 1 year: 2023 end-page: 12 ident: bib15 article-title: Edge solution for real-time motor fault diagnosis based on efficient convolutional neural network publication-title: IEEE Trans. Instrum. Meas. – volume: 494 start-page: 379 year: 2022 end-page: 395 ident: bib42 article-title: A Time Series Transformer based method for the rotating machinery fault diagnosis publication-title: Neurocomputing – volume: 71 start-page: 1 year: 2022 end-page: 15 ident: bib22 article-title: An improved convolutional neural network for three-phase inverter fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – volume: 292 start-page: 1 year: 2024 end-page: 13 ident: bib26 article-title: DSMT-1DCNN: densely supervised multitask 1DCNN for fault diagnosis publication-title: Knowl. Based Syst. – volume: 13 start-page: 1350 year: 2017 end-page: 1359 ident: bib4 article-title: Convolutional discriminative feature learning for induction motor fault diagnosis, IEEE Trans publication-title: Ind. Inform. – volume: 79 start-page: 4395 year: 2024 end-page: 4411 ident: bib29 article-title: Fault diagnosis method of rolling bearing based on MSCNN-LSTM, Comput publication-title: Mater. Contin. – volume: 167 year: 2024 ident: bib1 article-title: Novel imbalanced multi-class fault diagnosis method using transfer learning and oversampling strategies-based multi-layer support vector machines (ML-SVMs) publication-title: Appl. Soft Comput. – volume: 15 start-page: 2446 year: 2019 end-page: 2455 ident: bib5 article-title: Highly accurate machine fault diagnosis using deep transfer learning, IEEE Trans publication-title: Ind. Inform. – volume: 18 start-page: 1527 year: 2020 end-page: 1554 ident: bib3 article-title: DCNN-based multi-signal induction motor fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – volume: 15 start-page: 1610 year: 2021 end-page: 1629 ident: bib33 article-title: Fault diagnosis of bearing based on convolutional neural network using multi-domain features, KSII Trans publication-title: Internet Inf. Syst. – volume: 679 year: 2024 ident: bib53 article-title: TFFS: a trainable federal fusion strategy for multistep time series forecasting publication-title: Inf. Sci. – volume: 17 start-page: 317 year: 2003 end-page: 328 ident: bib11 article-title: Artificial neural network based fault diagnostics of rolling element bearings using time-domain features publication-title: Mech. Syst. Signal Process – reference: E. Bechhoefer, Condition Based Maintenance Fault Database for Testing Diagnostics and Prognostic Algorithms, – volume: 67 start-page: 439 year: 2023 end-page: 452 ident: bib36 article-title: A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: a rotary system application, J publication-title: Manuf. Syst. – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: bib13 article-title: Deep learning publication-title: Nature – volume: 249 year: 2024 ident: bib30 article-title: A deep learning methodology based on adaptive multiscale CNN and enhanced highway LSTM for industrial process fault diagnosis, Reliab publication-title: Eng. Syst. Saf. – volume: 62 start-page: 3757 year: 2015 end-page: 3767 ident: bib7 article-title: A survey of fault diagnosis and fault-tolerant techniques—part II: fault diagnosis with knowledge-based and hybrid/active approaches publication-title: IEEE Trans. Ind. Electron – volume: 110 year: 2021 ident: bib16 article-title: OrbitNet: a new CNN model for automatic fault diagnostics of turbomachines publication-title: Appl. Soft Comput. – volume: 18 start-page: 143 year: 2004 end-page: 159 ident: bib9 article-title: Fault diagnosis using support vector machine with an application in sheet metal stamping operations publication-title: Mech. Syst. Signal Process – volume: 65 start-page: 543 year: 2020 end-page: 561 ident: bib24 article-title: Accurate multi-scale feature fusion CNN for time series classification in smart factory publication-title: Comput. Mater. Contin. – start-page: 1 year: 2015 end-page: 15 ident: bib49 article-title: Adam: A method for stochastic optimization publication-title: 3rd Int. Conf. Learn. Represent. ICLR 2015 Conf. Track Proc. – volume: 125 year: 2021 ident: bib27 article-title: Fault detection and diagnosis for rotating machinery: a model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms publication-title: Comput. Ind. – volume: 62 start-page: 3757 year: 2015 end-page: 3767 ident: bib6 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 – year: 2023 ident: bib25 article-title: DL-MSCNN: a general and lightweight framework for fault diagnosis with limited training samples publication-title: J. Intell. Manuf. – volume: 64–65 start-page: 100 year: 2015 end-page: 131 ident: bib50 article-title: Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study publication-title: Mech. Syst. Signal Process – volume: 108 start-page: 53 year: 2019 end-page: 61 ident: bib20 article-title: Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network publication-title: Comput. Ind. – volume: 70 start-page: 1 year: 2021 end-page: 11 ident: bib12 article-title: Multitask learning based on lightweight 1DCNN for fault diagnosis of wheelset bearings publication-title: IEEE Trans. Instrum. Meas. – start-page: 2400828 year: 2024 ident: bib17 article-title: Knowledge distillation-based zero-shot learning for process fault diagnosis, Adv publication-title: Intell. Syst. – volume: 1 start-page: 4171 year: 2019 end-page: 4186 ident: bib39 article-title: BERT: pre-training of deep bidirectional transformers for language understanding, NAACL HLT 2019 - 2019 Conf publication-title: North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. Proc. Conf. – start-page: 47 year: 2017 end-page: 82 ident: bib38 article-title: Attention is all you need publication-title: 31st Conf. Neural Inf. Process. Syst. (NIPS 2017) – start-page: 443 year: 2016 end-page: 450 ident: bib48 article-title: Deep CORAL: Correlation Alignment for Deep Domain Adaptation, Comput publication-title: Vis. ECCV 2016 Work – volume: 213 year: 2023 ident: bib34 article-title: Multi-view and multi-level network for fault diagnosis accommodating feature transferability publication-title: Expert Syst. Appl. – volume: 26 start-page: 189 year: 2015 end-page: 198 ident: bib2 article-title: Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination, J publication-title: Intell. Manuf. – volume: 49 start-page: 136 year: 2019 end-page: 144 ident: bib32 article-title: A new deep transfer learning based on sparse auto-encoder for fault diagnosis publication-title: IEEE Trans. Syst. Man Cybern. Syst. – volume: 17 year: 2017 ident: bib21 article-title: A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals publication-title: Sens. (Switz. ) – volume: 55 start-page: 1289 year: 2022 end-page: 1315 ident: bib18 article-title: A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems publication-title: Artif. Intell. Rev. – year: 2021 ident: bib40 article-title: Transformer models for text-based emotion detection: a review of BERT-based approaches – volume: 34 year: 2023 ident: bib37 article-title: Identification of engine faults based on acoustic emission signals using a 1DCNN-ViT ensemble model publication-title: Meas. Sci. Technol. – reference: . – reference: . (2013). – volume: 106 start-page: 48 year: 2019 end-page: 59 ident: bib14 article-title: Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform publication-title: Comput. Ind. – volume: 236 year: 2024 ident: bib8 article-title: Adaptive multi-scale attention convolution neural network for cross-domain fault diagnosis publication-title: Expert Syst. Appl. – volume: 106 start-page: 48 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib14 article-title: Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform publication-title: Comput. Ind. doi: 10.1016/j.compind.2018.11.003 – start-page: 582 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib43 article-title: Research on transformer fault diagnosis method based on NRS-PSO-ANFIS, Meas publication-title: Sci. Technol. 1168 LNEE – volume: 249 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib30 article-title: A deep learning methodology based on adaptive multiscale CNN and enhanced highway LSTM for industrial process fault diagnosis, Reliab publication-title: Eng. Syst. Saf. – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.asoc.2025.113572_bib12 article-title: Multitask learning based on lightweight 1DCNN for fault diagnosis of wheelset bearings publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2021.3118090 – start-page: 770 year: 2016 ident: 10.1016/j.asoc.2025.113572_bib46 article-title: Deep residual learning for image recognition, Proc. IEEE Comput. Soc. Conf. Comput. Vis publication-title: Pattern Recognit. 2016Decem – volume: 18 start-page: 1527 year: 2020 ident: 10.1016/j.asoc.2025.113572_bib3 article-title: DCNN-based multi-signal induction motor fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – volume: 22 start-page: 1716 year: 2008 ident: 10.1016/j.asoc.2025.113572_bib10 article-title: Random forests classifier for machine fault diagnosis, J publication-title: Mech. Sci. Technol. doi: 10.1007/s12206-008-0603-6 – start-page: 47 year: 2017 ident: 10.1016/j.asoc.2025.113572_bib38 article-title: Attention is all you need publication-title: 31st Conf. Neural Inf. Process. Syst. (NIPS 2017) – volume: 679 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib53 article-title: TFFS: a trainable federal fusion strategy for multistep time series forecasting publication-title: Inf. Sci. doi: 10.1016/j.ins.2024.121126 – volume: 72 start-page: 1 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib15 article-title: Edge solution for real-time motor fault diagnosis based on efficient convolutional neural network publication-title: IEEE Trans. Instrum. Meas. – volume: 119 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib35 article-title: GTFE-Net: a Gramian time frequency enhancement CNN for bearing fault diagnosis publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2022.105794 – ident: 10.1016/j.asoc.2025.113572_bib52 doi: 10.21629/JSEE.2017.01.18 – volume: 79 start-page: 4395 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib29 article-title: Fault diagnosis method of rolling bearing based on MSCNN-LSTM, Comput publication-title: Mater. Contin. – start-page: 443 year: 2016 ident: 10.1016/j.asoc.2025.113572_bib48 article-title: Deep CORAL: Correlation Alignment for Deep Domain Adaptation, Comput publication-title: Vis. ECCV 2016 Work – volume: 66 start-page: 3196 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib23 article-title: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox publication-title: IEEE Trans. Ind. Electron doi: 10.1109/TIE.2018.2844805 – volume: 213 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib34 article-title: Multi-view and multi-level network for fault diagnosis accommodating feature transferability publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2022.119057 – year: 2023 ident: 10.1016/j.asoc.2025.113572_bib25 article-title: DL-MSCNN: a general and lightweight framework for fault diagnosis with limited training samples publication-title: J. Intell. Manuf. – volume: 292 start-page: 1 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib26 article-title: DSMT-1DCNN: densely supervised multitask 1DCNN for fault diagnosis publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2024.111609 – volume: 2016 start-page: 2058 year: 2016 ident: 10.1016/j.asoc.2025.113572_bib47 article-title: Return of frustratingly easy domain adaptation publication-title: 30th AAAI Conf. Artif. Intell. AAAI – volume: 167 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib1 article-title: Novel imbalanced multi-class fault diagnosis method using transfer learning and oversampling strategies-based multi-layer support vector machines (ML-SVMs) publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2024.112324 – volume: 18 start-page: 143 year: 2004 ident: 10.1016/j.asoc.2025.113572_bib9 article-title: Fault diagnosis using support vector machine with an application in sheet metal stamping operations publication-title: Mech. Syst. Signal Process doi: 10.1016/S0888-3270(03)00071-2 – volume: 130 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib45 article-title: Multi-scale Transformer-CNN domain adaptation network for complex processes fault diagnosis publication-title: J. Process Control doi: 10.1016/j.jprocont.2023.103069 – volume: 249 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib44 article-title: Convolutional preprocessing Transformer-based fault diagnosis for rectifier-filter circuits in nuclear power plants publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2024.110198 – volume: 17 start-page: 317 year: 2003 ident: 10.1016/j.asoc.2025.113572_bib11 article-title: Artificial neural network based fault diagnostics of rolling element bearings using time-domain features publication-title: Mech. Syst. Signal Process doi: 10.1006/mssp.2001.1462 – volume: 110 year: 2021 ident: 10.1016/j.asoc.2025.113572_bib16 article-title: OrbitNet: a new CNN model for automatic fault diagnostics of turbomachines publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2021.107702 – year: 2021 ident: 10.1016/j.asoc.2025.113572_bib40 – start-page: 2400828 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib17 article-title: Knowledge distillation-based zero-shot learning for process fault diagnosis, Adv publication-title: Intell. Syst. – ident: 10.1016/j.asoc.2025.113572_bib51 doi: 10.4324/9781003116929-18 – volume: 67 start-page: 439 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib36 article-title: A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: a rotary system application, J publication-title: Manuf. Syst. doi: 10.1016/j.jmsy.2023.02.018 – start-page: 1 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib49 article-title: Adam: A method for stochastic optimization publication-title: 3rd Int. Conf. Learn. Represent. ICLR 2015 Conf. Track Proc. – volume: 494 start-page: 379 year: 2022 ident: 10.1016/j.asoc.2025.113572_bib42 article-title: A Time Series Transformer based method for the rotating machinery fault diagnosis publication-title: Neurocomputing doi: 10.1016/j.neucom.2022.04.111 – volume: 62 start-page: 3757 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib6 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: 65 start-page: 543 year: 2020 ident: 10.1016/j.asoc.2025.113572_bib24 article-title: Accurate multi-scale feature fusion CNN for time series classification in smart factory publication-title: Comput. Mater. Contin. – volume: 15 start-page: 1610 year: 2021 ident: 10.1016/j.asoc.2025.113572_bib33 article-title: Fault diagnosis of bearing based on convolutional neural network using multi-domain features, KSII Trans publication-title: Internet Inf. Syst. – volume: 32 start-page: 971 year: 2021 ident: 10.1016/j.asoc.2025.113572_bib28 article-title: Bearing fault diagnosis base on multi-scale CNN and LSTM model publication-title: J. Intell. Manuf. doi: 10.1007/s10845-020-01600-2 – volume: 32 start-page: 4735 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib31 article-title: Multimodel fusion health assessment for multistate industrial robot via fuzzy deep residual shrinkage network and versatile cluster publication-title: IEEE Trans. Fuzzy Syst. doi: 10.1109/TFUZZ.2024.3411389 – volume: 26 start-page: 189 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib2 article-title: Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination, J publication-title: Intell. Manuf. doi: 10.1007/s10845-013-0772-8 – ident: 10.1016/j.asoc.2025.113572_bib41 – volume: 34 year: 2023 ident: 10.1016/j.asoc.2025.113572_bib37 article-title: Identification of engine faults based on acoustic emission signals using a 1DCNN-ViT ensemble model publication-title: Meas. Sci. Technol. – volume: 1 start-page: 4171 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib39 article-title: BERT: pre-training of deep bidirectional transformers for language understanding, NAACL HLT 2019 - 2019 Conf publication-title: North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. Proc. Conf. – volume: 13 start-page: 1350 year: 2017 ident: 10.1016/j.asoc.2025.113572_bib4 article-title: Convolutional discriminative feature learning for induction motor fault diagnosis, IEEE Trans publication-title: Ind. Inform. doi: 10.1109/TII.2017.2672988 – volume: 108 start-page: 53 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib20 article-title: Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network publication-title: Comput. Ind. doi: 10.1016/j.compind.2018.12.001 – volume: 125 year: 2021 ident: 10.1016/j.asoc.2025.113572_bib27 article-title: Fault detection and diagnosis for rotating machinery: a model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms publication-title: Comput. Ind. doi: 10.1016/j.compind.2020.103378 – volume: 236 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib8 article-title: Adaptive multi-scale attention convolution neural network for cross-domain fault diagnosis publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.121216 – volume: 71 start-page: 1 year: 2022 ident: 10.1016/j.asoc.2025.113572_bib22 article-title: An improved convolutional neural network for three-phase inverter fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – volume: 55 start-page: 1289 year: 2022 ident: 10.1016/j.asoc.2025.113572_bib18 article-title: A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems publication-title: Artif. Intell. Rev. doi: 10.1007/s10462-021-09993-z – volume: 49 start-page: 136 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib32 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 – volume: 15 start-page: 2446 year: 2019 ident: 10.1016/j.asoc.2025.113572_bib5 article-title: Highly accurate machine fault diagnosis using deep transfer learning, IEEE Trans publication-title: Ind. Inform. doi: 10.1109/TII.2018.2864759 – volume: 355 year: 2024 ident: 10.1016/j.asoc.2025.113572_bib19 article-title: Fault diagnosis for PV arrays considering dust impact based on transformed graphical features of characteristic curves and convolutional neural network with CBAM modules publication-title: Appl. Energy doi: 10.1016/j.apenergy.2023.122252 – volume: 62 start-page: 3757 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib7 article-title: A survey of fault diagnosis and fault-tolerant techniques—part II: fault diagnosis with knowledge-based and hybrid/active approaches publication-title: IEEE Trans. Ind. Electron doi: 10.1109/TIE.2015.2417501 – volume: 17 year: 2017 ident: 10.1016/j.asoc.2025.113572_bib21 article-title: A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals publication-title: Sens. (Switz. ) – volume: 64–65 start-page: 100 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib50 article-title: Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study publication-title: Mech. Syst. Signal Process doi: 10.1016/j.ymssp.2015.04.021 – volume: 521 start-page: 436 year: 2015 ident: 10.1016/j.asoc.2025.113572_bib13 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 |
| SSID | ssj0016928 |
| Score | 2.449378 |
| Snippet | Fault Diagnosis (FD) is critical in smart manufacturing, enabling predictive maintenance, reducing operational costs, and enhancing system reliability. To deal... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 113572 |
| SubjectTerms | 1DCNN Fault diagnosis multi-supervised algorithm multi-view global features Transformer |
| Title | Multi-branch global Transformer‐assisted network for fault diagnosis |
| URI | https://dx.doi.org/10.1016/j.asoc.2025.113572 |
| Volume | 182 |
| WOSCitedRecordID | wos001533753500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 1568-4946 databaseCode: AIEXJ dateStart: 20010601 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0016928 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Jat0wFBVt0kU36ZSSdEKL7oJCLFm2vAwloQ0hBPJavDNXkt2-QPzCG0qW_YR-Y7-kV5Nj0lDSQjbG2Eg294jj46s7EPK-sxw_7LZghRA5c-zHdK4NKwvJOwDFha-z_eW4PDlRdV2dxo56C99OoOx7dXVVXd4r1HgNwXaps_8A9zApXsBzBB2PCDse7wS8T6ll2jXM-JbqfUySPEWAUnQDqmYHsd3pQyS4DzjsAEc7h6yLv5suxtI16dUFErePRF8t02fPl3gE73StpzCbr6bXW_sXcVO__8rOZrOxk4HLIVwter7-yH4JZFkollfRhTiwKb-VmYOT4HwXcNHtuke4bjIytO25UfH6zE3s5kV5hiQo6odknZeyQt5d3_90UB8N20RF5ZvnDi8Ss6JCAN_NJ92uPEZqYvKUbMTfALof4HtGHrT9c_IktdigkXFfkMMxmjSgSUdo_vrxM-FII44U71CPIx1w3CSfDw8mHz6y2PqCGS7FkhUKUGhmSguJrKoVlBZKrQXvrFTQ5lmHN23HAfbAtnu6gkwbg1oL_59BZ1a8JGv9rG-3CHWZzVpK1Yo2y01mlAVZCpUbEJ0tc7NNdpJZmstQ4aRJoX_njTNi44zYBCNuE5ks10SNFrRXg0D_Zdyr_xz3mjy-Xo9vyNpyvmrfkkfm-3K6mL-L6-E3Trxhow |
| linkProvider | Elsevier |
| 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=Multi-branch+global+Transformer%E2%80%90assisted+network+for+fault+diagnosis&rft.jtitle=Applied+soft+computing&rft.au=Shao%2C+Xiaorui&rft.au=Kim%2C+Chang-Soo&rft.date=2025-10-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.volume=182&rft_id=info:doi/10.1016%2Fj.asoc.2025.113572&rft.externalDocID=S156849462500883X |
| 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 |