Imbalanced class incremental learning system: A task incremental diagnosis method for imbalanced industrial streaming data
In recent years, machine learning has been widely used in various fault diagnosis scenarios. However, existing machine learning algorithms tend to work well in closed static environments and handle a constant number of categories. However, in industrial applications, the monitored data is streaming...
Uloženo v:
| Vydáno v: | Advanced engineering informatics Ročník 62; s. 102832 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.10.2024
|
| Témata: | |
| ISSN: | 1474-0346 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In recent years, machine learning has been widely used in various fault diagnosis scenarios. However, existing machine learning algorithms tend to work well in closed static environments and handle a constant number of categories. However, in industrial applications, the monitored data is streaming and new categories are constantly introduced into the diagnostic system. In real industrial scenarios, monitoring data is often characterized by an imbalanced distribution due to the uncertainty of machinery operation. The diagnosis of such imbalanced industrial streaming data is known as the imbalanced class incremental learning problem in industrial applications. A novel imbalanced class incremental learning system (ICILS) is proposed for imbalanced industrial streaming data and applied to intelligent fault diagnosis of mechanical equipment. Specifically, a novel graph convolutional sparse autoencoder is firstly designed for the imbalanced dataset to extract feature information with large inter-class scatter. Next, a classification loss function is designed to enhance the classification decision boundary between majority and minority classes by utilizing the prior distribution information of the imbalanced data. Finally, a novel imbalanced class incremental learning rule is derived to realize new class learning without replaying old class data. ICILS has high accuracy and computational efficiency, while ensuring data privacy and security. The designed experiments for the diagnosis of imbalanced industrial streaming data indicated that the proposed method has significant advantages over other methods and can effectively deal with imbalanced streaming data. |
|---|---|
| AbstractList | In recent years, machine learning has been widely used in various fault diagnosis scenarios. However, existing machine learning algorithms tend to work well in closed static environments and handle a constant number of categories. However, in industrial applications, the monitored data is streaming and new categories are constantly introduced into the diagnostic system. In real industrial scenarios, monitoring data is often characterized by an imbalanced distribution due to the uncertainty of machinery operation. The diagnosis of such imbalanced industrial streaming data is known as the imbalanced class incremental learning problem in industrial applications. A novel imbalanced class incremental learning system (ICILS) is proposed for imbalanced industrial streaming data and applied to intelligent fault diagnosis of mechanical equipment. Specifically, a novel graph convolutional sparse autoencoder is firstly designed for the imbalanced dataset to extract feature information with large inter-class scatter. Next, a classification loss function is designed to enhance the classification decision boundary between majority and minority classes by utilizing the prior distribution information of the imbalanced data. Finally, a novel imbalanced class incremental learning rule is derived to realize new class learning without replaying old class data. ICILS has high accuracy and computational efficiency, while ensuring data privacy and security. The designed experiments for the diagnosis of imbalanced industrial streaming data indicated that the proposed method has significant advantages over other methods and can effectively deal with imbalanced streaming data. |
| ArticleNumber | 102832 |
| Author | Ding, Chuancang Shi, Mingkuan Zhu, Zhongkui Shen, Changqing Huang, Weiguo |
| Author_xml | – sequence: 1 givenname: Mingkuan surname: Shi fullname: Shi, Mingkuan organization: School of Rail Transportation, Soochow University, Suzhou 215131, PR China – sequence: 2 givenname: Chuancang surname: Ding fullname: Ding, Chuancang organization: School of Rail Transportation, Soochow University, Suzhou 215131, PR China – sequence: 3 givenname: Changqing surname: Shen fullname: Shen, Changqing organization: School of Rail Transportation, Soochow University, Suzhou 215131, PR China – sequence: 4 givenname: Weiguo surname: Huang fullname: Huang, Weiguo organization: School of Rail Transportation, Soochow University, Suzhou 215131, PR China – sequence: 5 givenname: Zhongkui surname: Zhu fullname: Zhu, Zhongkui email: zhuzhongkui@suda.edu.cn organization: School of Rail Transportation, Soochow University, Suzhou 215131, PR China |
| BookMark | eNp9kM1KAzEUhbOoYKs-gLu8wNRkJk5mdFWKP4WCG12HO8lNTZ3JSBKF-vSmVBBddHW4cL4D95uRiR89EnLJ2ZwzXl9t54BuXrJS5LtsqnJCplxIUbBK1KdkFuOW5V7Tyin5Wg0d9OA1Gqp7iJE6rwMO6BP0tEcI3vkNjbuYcLihC5ogvv3pGAcbP0YX6YDpdTTUjoG631XnzUdMweVqDoRhv2cgwTk5sdBHvPjJM_Jyf_e8fCzWTw-r5WJd6LKVqaixlrblVVd22rZgRGUr22jATiJvsckPWtnZTjc1NsI25toIVkpRWwAtmKnOiDzs6jDGGNAq7RIkN_oUwPWKM7XXprYqa1N7beqgLZP8H_ke3ABhd5S5PTCYX_p0GFTUDvcmXECdlBndEfobmNCNcA |
| CitedBy_id | crossref_primary_10_1016_j_knosys_2025_113346 crossref_primary_10_1016_j_eti_2025_104154 crossref_primary_10_1109_TIM_2025_3589703 crossref_primary_10_1080_10589759_2025_2534431 crossref_primary_10_1016_j_ress_2025_111239 crossref_primary_10_1088_1361_6501_ade554 crossref_primary_10_1016_j_knosys_2025_114044 |
| Cites_doi | 10.1016/j.ins.2023.119496 10.1016/j.eswa.2021.116459 10.1016/j.ress.2023.109832 10.1007/s11831-024-10146-y 10.1016/j.ymssp.2023.110309 10.1016/j.knosys.2023.110395 10.1109/MCI.2022.3222049 10.1016/j.aei.2023.102157 10.1016/j.ins.2022.12.090 10.1007/s12559-014-9259-y 10.1038/s42256-022-00568-3 10.1016/j.aei.2024.102513 10.1007/s11704-016-6903-6 10.1016/j.ress.2023.109601 10.1073/pnas.1611835114 10.1016/j.ress.2023.109522 10.1016/j.ress.2023.109705 10.1016/j.ymssp.2022.108826 10.1109/TII.2021.3138558 10.1016/j.aei.2022.101725 10.1109/TIM.2024.3480206 10.1016/j.neunet.2019.01.012 10.1016/j.ymssp.2022.109353 10.1016/j.eswa.2023.121001 10.1016/j.aei.2020.101150 10.1016/j.compstruct.2023.117792 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd |
| Copyright_xml | – notice: 2024 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.aei.2024.102832 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| ExternalDocumentID | 10_1016_j_aei_2024_102832 S1474034624004804 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ AAAKF AAAKG AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AAXKI AAXUO AAYFN ABBOA ABFNM ABMAC ABUCO ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACZNC ADBBV ADEZE ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEKER AENEX AFJKZ AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM AXJTR BJAXD BKOJK BLXMC CS3 EBS EFJIC EJD EO8 EO9 EP2 EP3 FDB FEDTE FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 PC. Q38 RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSB SSD SST SSV SSZ T5K UHS XPP ZMT ~G- 9DU AATTM AAYWO AAYXX ABJNI ACLOT ACVFH ADCNI AEIPS AEUPX AFPUW AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c297t-6e67f913b2bcf9ad43f3f8caeb7e19e8283f7bfbc86e84f8d5d402746faac40d3 |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001320957200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1474-0346 |
| IngestDate | Sat Nov 29 03:19:54 EST 2025 Tue Nov 18 21:51:13 EST 2025 Sat Dec 14 16:15:11 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Industrial streaming data Intelligent fault diagnosis Rotating machinery Class imbalance Class incremental learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c297t-6e67f913b2bcf9ad43f3f8caeb7e19e8283f7bfbc86e84f8d5d402746faac40d3 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_aei_2024_102832 crossref_primary_10_1016_j_aei_2024_102832 elsevier_sciencedirect_doi_10_1016_j_aei_2024_102832 |
| PublicationCentury | 2000 |
| PublicationDate | October 2024 2024-10-00 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: October 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Advanced engineering informatics |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – sequence: 0 name: Elsevier Ltd |
| References | Wu, Zhang, Guo, Ji, Pecht (b0140) 2022; 193 Zhao, Ding, Lu, Wang, Ma, Tao, Ma (b0030) 2023; 234 Parisi, Kemker, Part, Kanan, Wermter (b0090) 2019; 113 Kirkpatrick, Pascanu, Rabinowitz, Veness, Desjardins, Rusu, Milan, Quan, Ramalho, Grabska-Barwinska (b0155) 2017; 114 Pan, Xu, Zheng, Tong (b0035) 2023; 624 Hu, He, Cheng, Peng (b0085) 2024; 241 Shi, Ding, Chang, Shen, Huang, Zhu (b0065) 2024 Chen, Shen, Wang, Kong, Chen, Zhu (b0115) 2022; 71 Fu, Cao, Chen, Ding (b0120) 2022; 178 Mallya, Lazebnik (b0165) 2018 Zhu, Zhang, Wang, Yin, Liu (b0180) 2021 Zhiyi, Haidong, Xiang, Yu, Junsheng (b0045) 2020; 46 Zhu, Zhai, Cao, Luo, Zha (b0170) 2022 Han, Xie, Pei (b0060) 2023; 648 Wang, Xiong, He (b0125) 2023; 266 Zhao, Yao, Deng, Jia, Liu (b0145) 2022; 170 Tian, Jiang, Zhang, Luo, Yin (b0150) 2024; 243 Yan, Zhong, Shao, Ming, Liu, Liu (b0025) 2023; 239 Rannen, Aljundi, Blaschko, Tuytelaars (b0160) 2017 Azad, Kim (b0055) 2024; 329 Zhao, Chen, Chen, Wang, Wang (b0195) 2014; 6 Zhu, Huang, Shen, Shen (b0005) 2022; 18 Qin, Liu, Mao (b0050) 2024; 61 Hou, Pan, Loy, Wang, Lin (b0205) 2019; 2019 Defferrard, Bresson, Vandergheynst (b0190) 2016; 29 Zhou, Wang, Qi, Ye, Zhan, Liu (b0075) 2024 Shi, Ding, Wang, Shen, Huang, Zhu (b0135) 2023; 240 van de Ven, Tuytelaars, Tolias (b0080) 2022; 4 Peng, Zhang, Li, Peng, Wang, Shen (b0105) 2023 Bruna, Zaremba, Szlam, LeCun (b0185) 2013 Ren, Lin, Feng, Zhu, Liu, Yan (b0010) 2023; 72 Shi, Ding, Chang, Wang, Huang, Zhu (b0015) 2023; 58 Liu, Chen, Wang, Kong, Shi, Shen (b0110) 2023; 72 Rebuffi, Kolesnikov, Sperl, Lampert (b0175) 2017 Liu, Huang, Ma, Luo (b0130) 2023; 196 Castro, Marín-Jiménez, Guil, Schmid, Alahari (b0200) 2018 Azad, Cheon, Raouf, Khalid, Kim (b0020) 2024 Febrinanto, Xia, Moore, Thapa, Aggarwal (b0100) 2023; 18 Zhu, Wang, Huang, Shen, Chen (b0070) 2024; 73 Liu, Zhong, Lin, Zhao, Fu, Liu (b0040) 2022; 54 Liu (b0095) 2017; 11 Azad (10.1016/j.aei.2024.102832_b0055) 2024; 329 Liu (10.1016/j.aei.2024.102832_b0095) 2017; 11 Zhu (10.1016/j.aei.2024.102832_b0180) 2021 Castro (10.1016/j.aei.2024.102832_b0200) 2018 Zhu (10.1016/j.aei.2024.102832_b0170) 2022 Liu (10.1016/j.aei.2024.102832_b0040) 2022; 54 Zhou (10.1016/j.aei.2024.102832_b0075) 2024 Hu (10.1016/j.aei.2024.102832_b0085) 2024; 241 Wu (10.1016/j.aei.2024.102832_b0140) 2022; 193 Kirkpatrick (10.1016/j.aei.2024.102832_b0155) 2017; 114 Zhao (10.1016/j.aei.2024.102832_b0030) 2023; 234 Liu (10.1016/j.aei.2024.102832_b0130) 2023; 196 Shi (10.1016/j.aei.2024.102832_b0065) 2024 Pan (10.1016/j.aei.2024.102832_b0035) 2023; 624 Chen (10.1016/j.aei.2024.102832_b0115) 2022; 71 Shi (10.1016/j.aei.2024.102832_b0015) 2023; 58 Zhiyi (10.1016/j.aei.2024.102832_b0045) 2020; 46 Fu (10.1016/j.aei.2024.102832_b0120) 2022; 178 Wang (10.1016/j.aei.2024.102832_b0125) 2023; 266 Defferrard (10.1016/j.aei.2024.102832_b0190) 2016; 29 Liu (10.1016/j.aei.2024.102832_b0110) 2023; 72 Febrinanto (10.1016/j.aei.2024.102832_b0100) 2023; 18 Zhu (10.1016/j.aei.2024.102832_b0005) 2022; 18 van de Ven (10.1016/j.aei.2024.102832_b0080) 2022; 4 Zhao (10.1016/j.aei.2024.102832_b0145) 2022; 170 Rebuffi (10.1016/j.aei.2024.102832_b0175) 2017 Tian (10.1016/j.aei.2024.102832_b0150) 2024; 243 Ren (10.1016/j.aei.2024.102832_b0010) 2023; 72 Zhu (10.1016/j.aei.2024.102832_b0070) 2024; 73 Rannen (10.1016/j.aei.2024.102832_b0160) 2017 Zhao (10.1016/j.aei.2024.102832_b0195) 2014; 6 Yan (10.1016/j.aei.2024.102832_b0025) 2023; 239 Hou (10.1016/j.aei.2024.102832_b0205) 2019; 2019 Qin (10.1016/j.aei.2024.102832_b0050) 2024; 61 Han (10.1016/j.aei.2024.102832_b0060) 2023; 648 Shi (10.1016/j.aei.2024.102832_b0135) 2023; 240 Bruna (10.1016/j.aei.2024.102832_b0185) 2013 Peng (10.1016/j.aei.2024.102832_b0105) 2023 Mallya (10.1016/j.aei.2024.102832_b0165) 2018 Azad (10.1016/j.aei.2024.102832_b0020) 2024 Parisi (10.1016/j.aei.2024.102832_b0090) 2019; 113 |
| References_xml | – volume: 46 year: 2020 ident: b0045 article-title: An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE publication-title: Adv. Eng. Inf. – start-page: 5871 year: 2021 end-page: 5880 ident: b0180 article-title: Prototype augmentation and self-supervision for incremental learning publication-title: Proc. IEEE/CVF Conference on Comp. Vis. Pattern Recognition – year: 2023 ident: b0105 article-title: SCLIFD: supervised contrastive knowledge distillation for incremental fault diagnosis under limited fault data publication-title: ArXiv abs/2302.05929 – volume: 240 year: 2023 ident: b0135 article-title: Graph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery publication-title: Reliab. Eng. Syst. Saf. – volume: 624 start-page: 395 year: 2023 end-page: 415 ident: b0035 article-title: Non-parallel bounded support matrix machine and its application in roller bearing fault diagnosis publication-title: Inf. Sci. – volume: 234 year: 2023 ident: b0030 article-title: An adaptive fault diagnosis framework under class-imbalanced conditions based on contrastive augmented deep reinforcement learning publication-title: Expert Syst. Appl. – volume: 2019 start-page: 831 year: 2019 end-page: 839 ident: b0205 article-title: Learning a unified classifier incrementally via rebalancing, in publication-title: IEEE/CVF Conference on Comp. Vis. Pattern Recognition (CVPR) – volume: 266 year: 2023 ident: b0125 article-title: Bearing fault diagnosis under various conditions using an incremental learning-based multi-task shared classifier publication-title: Knowl.-Based Syst. – volume: 6 start-page: 423 year: 2014 end-page: 431 ident: b0195 article-title: A class incremental extreme learning machine for activity recognition publication-title: Cogn. Comput. – year: 2013 ident: b0185 article-title: Spectral networks and locally connected networks on graphs publication-title: arXiv preprint arXiv:1312.6203 – year: 2024 ident: b0075 article-title: Class-incremental learning: a survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 241 year: 2024 ident: b0085 article-title: Adaptive incremental diagnosis model for intelligent fault diagnosis with dynamic weight correction publication-title: Reliab. Eng. Syst. Saf. – volume: 58 year: 2023 ident: b0015 article-title: Cross-domain privacy-preserving broad network for fault diagnosis of rotating machinery publication-title: Adv. Eng. Inf. – volume: 170 year: 2022 ident: b0145 article-title: Normalized conditional variational auto-encoder with adaptive focal loss for imbalanced fault diagnosis of bearing-rotor system publication-title: Mech. Syst. Sig. Process. – year: 2024 ident: b0020 article-title: Intelligent computational methods for damage detection of laminated composite structures for mobility applications: a comprehensive review publication-title: Arch. Comput. Meth. Eng. – volume: 71 start-page: 1 year: 2022 ident: b0115 article-title: A lifelong learning method for gearbox diagnosis with incremental fault types publication-title: IEEE Trans. Instrum. Meas. – volume: 113 start-page: 54 year: 2019 end-page: 71 ident: b0090 article-title: Continual lifelong learning with neural networks: a review publication-title: Neural Netw. – volume: 193 year: 2022 ident: b0140 article-title: Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network publication-title: Expert Syst. Appl. – volume: 73 start-page: 1 year: 2024 end-page: 14 ident: b0070 article-title: A new incremental learning for bearing fault diagnosis under noisy conditions using classification and feature-level information publication-title: IEEE Trans. Instrum. Meas. – volume: 4 start-page: 1185 year: 2022 end-page: 1197 ident: b0080 article-title: Three types of incremental learning publication-title: Nature Machine Intelligence – start-page: 9296 year: 2022 end-page: 9305 ident: b0170 article-title: Self-sustaining representation expansion for non-exemplar class-incremental learning publication-title: Proce. IEEE/CVF Conference on Com. Vis. Pattern Recognition – start-page: 1320 year: 2017 end-page: 1328 ident: b0160 article-title: Encoder based lifelong learning publication-title: Proc. IEEE int. conference on Com. Vis. – volume: 11 start-page: 359 year: 2017 end-page: 361 ident: b0095 article-title: Lifelong machine learning: a paradigm for continuous learning publication-title: Front. Comp. Sci. – volume: 18 start-page: 32 year: 2023 end-page: 51 ident: b0100 article-title: Graph lifelong learning: a survey publication-title: IEEE Comput. Intell. Mag. – volume: 72 start-page: 1 year: 2023 end-page: 11 ident: b0110 article-title: A lifelong learning method based on generative feature replay for bearing diagnosis with incremental fault types publication-title: IEEE Trans. Instrum. Meas. – volume: 61 year: 2024 ident: b0050 article-title: Faulty rolling bearing digital twin model and its application in fault diagnosis with imbalanced samples publication-title: Adv. Eng. Inf. – volume: 29 year: 2016 ident: b0190 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Adv. Neural Inf. Proces. Syst. – start-page: 1 year: 2024 end-page: 13 ident: b0065 article-title: Cross-domain class incremental broad network for continuous diagnosis of rotating machinery faults under variable operating conditions publication-title: IEEE Trans. Ind. Inf. – volume: 178 year: 2022 ident: b0120 article-title: Broad auto-encoder for machinery intelligent fault diagnosis with incremental fault samples and fault modes publication-title: Mech. Syst. Sig. Process. – volume: 18 start-page: 8077 year: 2022 end-page: 8086 ident: b0005 article-title: Cross-domain open-set machinery fault diagnosis based on adversarial network with multiple auxiliary classifiers publication-title: IEEE Trans. Ind. Inf. – volume: 114 start-page: 3521 year: 2017 end-page: 3526 ident: b0155 article-title: Overcoming catastrophic forgetting in neural networks publication-title: Proc. Natl. Acad. Sci. – volume: 54 year: 2022 ident: b0040 article-title: Highly imbalanced fault diagnosis of gas turbines via clustering-based downsampling and deep siamese self-attention network publication-title: Adv. Eng. Inf. – volume: 243 year: 2024 ident: b0150 article-title: A novel data augmentation approach to fault diagnosis with class-imbalance problem publication-title: Reliab. Eng. Syst. Saf. – start-page: 5533 year: 2017 end-page: 5542 ident: b0175 article-title: iCaRL: incremental classifier and representation learning publication-title: IEEE Conference on Comp. Vis. Pattern Recognition (CVPR) – volume: 196 year: 2023 ident: b0130 article-title: Class-incremental continual learning model for plunger pump faults based on weight space meta-representation publication-title: Mech. Syst. Sig. Process. – volume: 239 year: 2023 ident: b0025 article-title: Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization publication-title: Reliab. Eng. Syst. Saf. – volume: 329 year: 2024 ident: b0055 article-title: Hybrid deep convolutional networks for the autonomous damage diagnosis of laminated composite structures publication-title: Compos. Struct. – start-page: 241 year: 2018 end-page: 257 ident: b0200 article-title: End-to-End Incremental Learning publication-title: Computer Vision – ECCV 2018 – start-page: 7765 year: 2018 end-page: 7773 ident: b0165 article-title: Packnet: adding multiple tasks to a single network by iterative pruning publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. – volume: 72 start-page: 1 year: 2023 end-page: 35 ident: b0010 article-title: A systematic review on imbalanced learning methods in intelligent fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – volume: 648 year: 2023 ident: b0060 article-title: Semi-supervised adversarial discriminative learning approach for intelligent fault diagnosis of wind turbine publication-title: Inf. Sci. – volume: 648 year: 2023 ident: 10.1016/j.aei.2024.102832_b0060 article-title: Semi-supervised adversarial discriminative learning approach for intelligent fault diagnosis of wind turbine publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.119496 – volume: 72 start-page: 1 year: 2023 ident: 10.1016/j.aei.2024.102832_b0010 article-title: A systematic review on imbalanced learning methods in intelligent fault diagnosis publication-title: IEEE Trans. Instrum. Meas. – start-page: 5533 year: 2017 ident: 10.1016/j.aei.2024.102832_b0175 article-title: iCaRL: incremental classifier and representation learning publication-title: IEEE Conference on Comp. Vis. Pattern Recognition (CVPR) – volume: 193 year: 2022 ident: 10.1016/j.aei.2024.102832_b0140 article-title: Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2021.116459 – volume: 243 year: 2024 ident: 10.1016/j.aei.2024.102832_b0150 article-title: A novel data augmentation approach to fault diagnosis with class-imbalance problem publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2023.109832 – year: 2024 ident: 10.1016/j.aei.2024.102832_b0020 article-title: Intelligent computational methods for damage detection of laminated composite structures for mobility applications: a comprehensive review publication-title: Arch. Comput. Meth. Eng. doi: 10.1007/s11831-024-10146-y – volume: 196 year: 2023 ident: 10.1016/j.aei.2024.102832_b0130 article-title: Class-incremental continual learning model for plunger pump faults based on weight space meta-representation publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2023.110309 – volume: 266 year: 2023 ident: 10.1016/j.aei.2024.102832_b0125 article-title: Bearing fault diagnosis under various conditions using an incremental learning-based multi-task shared classifier publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2023.110395 – volume: 18 start-page: 32 year: 2023 ident: 10.1016/j.aei.2024.102832_b0100 article-title: Graph lifelong learning: a survey publication-title: IEEE Comput. Intell. Mag. doi: 10.1109/MCI.2022.3222049 – volume: 29 year: 2016 ident: 10.1016/j.aei.2024.102832_b0190 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Adv. Neural Inf. Proces. Syst. – volume: 58 year: 2023 ident: 10.1016/j.aei.2024.102832_b0015 article-title: Cross-domain privacy-preserving broad network for fault diagnosis of rotating machinery publication-title: Adv. Eng. Inf. doi: 10.1016/j.aei.2023.102157 – year: 2024 ident: 10.1016/j.aei.2024.102832_b0075 article-title: Class-incremental learning: a survey publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 5871 year: 2021 ident: 10.1016/j.aei.2024.102832_b0180 article-title: Prototype augmentation and self-supervision for incremental learning publication-title: Proc. IEEE/CVF Conference on Comp. Vis. Pattern Recognition – year: 2013 ident: 10.1016/j.aei.2024.102832_b0185 article-title: Spectral networks and locally connected networks on graphs publication-title: arXiv preprint arXiv:1312.6203 – volume: 624 start-page: 395 year: 2023 ident: 10.1016/j.aei.2024.102832_b0035 article-title: Non-parallel bounded support matrix machine and its application in roller bearing fault diagnosis publication-title: Inf. Sci. doi: 10.1016/j.ins.2022.12.090 – start-page: 241 year: 2018 ident: 10.1016/j.aei.2024.102832_b0200 article-title: End-to-End Incremental Learning – volume: 6 start-page: 423 year: 2014 ident: 10.1016/j.aei.2024.102832_b0195 article-title: A class incremental extreme learning machine for activity recognition publication-title: Cogn. Comput. doi: 10.1007/s12559-014-9259-y – volume: 4 start-page: 1185 year: 2022 ident: 10.1016/j.aei.2024.102832_b0080 article-title: Three types of incremental learning publication-title: Nature Machine Intelligence doi: 10.1038/s42256-022-00568-3 – volume: 61 year: 2024 ident: 10.1016/j.aei.2024.102832_b0050 article-title: Faulty rolling bearing digital twin model and its application in fault diagnosis with imbalanced samples publication-title: Adv. Eng. Inf. doi: 10.1016/j.aei.2024.102513 – volume: 11 start-page: 359 year: 2017 ident: 10.1016/j.aei.2024.102832_b0095 article-title: Lifelong machine learning: a paradigm for continuous learning publication-title: Front. Comp. Sci. doi: 10.1007/s11704-016-6903-6 – volume: 240 year: 2023 ident: 10.1016/j.aei.2024.102832_b0135 article-title: Graph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2023.109601 – start-page: 1 year: 2024 ident: 10.1016/j.aei.2024.102832_b0065 article-title: Cross-domain class incremental broad network for continuous diagnosis of rotating machinery faults under variable operating conditions publication-title: IEEE Trans. Ind. Inf. – volume: 71 start-page: 1 year: 2022 ident: 10.1016/j.aei.2024.102832_b0115 article-title: A lifelong learning method for gearbox diagnosis with incremental fault types publication-title: IEEE Trans. Instrum. Meas. – volume: 114 start-page: 3521 year: 2017 ident: 10.1016/j.aei.2024.102832_b0155 article-title: Overcoming catastrophic forgetting in neural networks publication-title: Proc. Natl. Acad. Sci. doi: 10.1073/pnas.1611835114 – volume: 239 year: 2023 ident: 10.1016/j.aei.2024.102832_b0025 article-title: Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2023.109522 – volume: 241 year: 2024 ident: 10.1016/j.aei.2024.102832_b0085 article-title: Adaptive incremental diagnosis model for intelligent fault diagnosis with dynamic weight correction publication-title: Reliab. Eng. Syst. Saf. doi: 10.1016/j.ress.2023.109705 – year: 2023 ident: 10.1016/j.aei.2024.102832_b0105 article-title: SCLIFD: supervised contrastive knowledge distillation for incremental fault diagnosis under limited fault data publication-title: ArXiv abs/2302.05929 – volume: 170 year: 2022 ident: 10.1016/j.aei.2024.102832_b0145 article-title: Normalized conditional variational auto-encoder with adaptive focal loss for imbalanced fault diagnosis of bearing-rotor system publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2022.108826 – start-page: 1320 year: 2017 ident: 10.1016/j.aei.2024.102832_b0160 article-title: Encoder based lifelong learning publication-title: Proc. IEEE int. conference on Com. Vis. – volume: 18 start-page: 8077 year: 2022 ident: 10.1016/j.aei.2024.102832_b0005 article-title: Cross-domain open-set machinery fault diagnosis based on adversarial network with multiple auxiliary classifiers publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2021.3138558 – volume: 54 year: 2022 ident: 10.1016/j.aei.2024.102832_b0040 article-title: Highly imbalanced fault diagnosis of gas turbines via clustering-based downsampling and deep siamese self-attention network publication-title: Adv. Eng. Inf. doi: 10.1016/j.aei.2022.101725 – volume: 73 start-page: 1 year: 2024 ident: 10.1016/j.aei.2024.102832_b0070 article-title: A new incremental learning for bearing fault diagnosis under noisy conditions using classification and feature-level information publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2024.3480206 – volume: 113 start-page: 54 year: 2019 ident: 10.1016/j.aei.2024.102832_b0090 article-title: Continual lifelong learning with neural networks: a review publication-title: Neural Netw. doi: 10.1016/j.neunet.2019.01.012 – volume: 178 year: 2022 ident: 10.1016/j.aei.2024.102832_b0120 article-title: Broad auto-encoder for machinery intelligent fault diagnosis with incremental fault samples and fault modes publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2022.109353 – volume: 2019 start-page: 831 year: 2019 ident: 10.1016/j.aei.2024.102832_b0205 article-title: Learning a unified classifier incrementally via rebalancing, in publication-title: IEEE/CVF Conference on Comp. Vis. Pattern Recognition (CVPR) – volume: 234 year: 2023 ident: 10.1016/j.aei.2024.102832_b0030 article-title: An adaptive fault diagnosis framework under class-imbalanced conditions based on contrastive augmented deep reinforcement learning publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.121001 – start-page: 7765 year: 2018 ident: 10.1016/j.aei.2024.102832_b0165 article-title: Packnet: adding multiple tasks to a single network by iterative pruning publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. – volume: 72 start-page: 1 year: 2023 ident: 10.1016/j.aei.2024.102832_b0110 article-title: A lifelong learning method based on generative feature replay for bearing diagnosis with incremental fault types publication-title: IEEE Trans. Instrum. Meas. – start-page: 9296 year: 2022 ident: 10.1016/j.aei.2024.102832_b0170 article-title: Self-sustaining representation expansion for non-exemplar class-incremental learning publication-title: Proce. IEEE/CVF Conference on Com. Vis. Pattern Recognition – volume: 46 year: 2020 ident: 10.1016/j.aei.2024.102832_b0045 article-title: An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE publication-title: Adv. Eng. Inf. doi: 10.1016/j.aei.2020.101150 – volume: 329 year: 2024 ident: 10.1016/j.aei.2024.102832_b0055 article-title: Hybrid deep convolutional networks for the autonomous damage diagnosis of laminated composite structures publication-title: Compos. Struct. doi: 10.1016/j.compstruct.2023.117792 |
| SSID | ssj0016897 |
| Score | 2.442499 |
| Snippet | In recent years, machine learning has been widely used in various fault diagnosis scenarios. However, existing machine learning algorithms tend to work well in... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102832 |
| SubjectTerms | Class imbalance Class incremental learning Industrial streaming data Intelligent fault diagnosis Rotating machinery |
| Title | Imbalanced class incremental learning system: A task incremental diagnosis method for imbalanced industrial streaming data |
| URI | https://dx.doi.org/10.1016/j.aei.2024.102832 |
| Volume | 62 |
| WOSCitedRecordID | wos001320957200001&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: 1474-0346 databaseCode: AIEXJ dateStart: 20020101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0016897 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELa2Sw-9UPpSoQ_50FNXWSWxN3a4rSgIKhVVKlX3FtmOTQNLeGyCUP9N_2nt2I53EVTl0EsUJc4kynyZjMffzADwgYkyo4ShiE-4iDBP9ScVKxoxZtaETC4IY12zCXJ4SGez_Otg8NvnwlzPSV3Tm5v84r-qWh_Tyjapsw9Qdy9UH9D7Wul6q9Wut_-k-IMzbuiKZl1fGNd4VNXCBgG1NuY-EmIrONu89IYtTldGlZZ_Vy1cg-mOi1gFuVXo92FyTdiZkeiy3HpXd-rZBTKUPBy5Oq3NEsf-W9dWePRFnz5tA1Y_uWYrOz9bE3ZxP1hbTNITBerjyyqc2G9d7PuHrI7b8-V4Rop7Zpw3wZjgKEYuMOlstLPY1sh2PlF6p_23oYiTMZPV2Agfh7GrtbZv_QN7ZqInvZ0UWkRhRBRWxCOwlpJJTodgbXqwO_vcL1Vl1Hbw8Y_tl847EuGt57jb-VlyaI42wLqbicCpRdAzMJD1c_DUzUqgs_mLF-BXABTsAAWXoAI9oKAF1DacQgOnlTE9nKCFE9QYgAFOMMAJ9nCCBk4vwfe93aOd_ch17IhEmpMmymRGVJ4gnnKhclZipJCigklOZJJLPbtHinDFBc0kxYqWkxKbuEimGBM4LtErMKzPa_kaQJRKikqmTQhj2BSZ0z5WziY0VkksEpFsgti_ykK4cvamq8q8uFeFm-Bjf8mFreXyt8HY66dwzqh1MguNtfsv23rIPd6AJ-ELeAuGzVUr34HH4rqpFlfvHdD-ANitr_w |
| 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=Imbalanced+class+incremental+learning+system%3A+A+task+incremental+diagnosis+method+for+imbalanced+industrial+streaming+data&rft.jtitle=Advanced+engineering+informatics&rft.au=Shi%2C+Mingkuan&rft.au=Ding%2C+Chuancang&rft.au=Shen%2C+Changqing&rft.au=Huang%2C+Weiguo&rft.date=2024-10-01&rft.issn=1474-0346&rft.volume=62&rft.spage=102832&rft_id=info:doi/10.1016%2Fj.aei.2024.102832&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_aei_2024_102832 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1474-0346&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1474-0346&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1474-0346&client=summon |