Multiscale intelligent fault detection system based on agglomerative hierarchical clustering using stacked denoising autoencoder with temporal information
Deep learning-based process monitoring has achieved remarkable progress. Generally, a deep model is empirically selected before the data features are learned. In this study, the interpretability and suitability of stacked denoising autoencoder (SDAE) in process monitoring territory are theoretically...
Uloženo v:
| Vydáno v: | Applied soft computing Ročník 95; s. 106525 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.10.2020
|
| Témata: | |
| ISSN: | 1568-4946 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Deep learning-based process monitoring has achieved remarkable progress. Generally, a deep model is empirically selected before the data features are learned. In this study, the interpretability and suitability of stacked denoising autoencoder (SDAE) in process monitoring territory are theoretically analyzed and validated. Considering that the data will show different feature representations at different scales, such as overall outline, local information, and microscopic details, this study utilizes the concept of multiscale analysis to mine the feature information of raw data deeply in different scales. The multiscale analysis is performed on the basis of agglomerative hierarchical clustering and silhouette coefficient, which makes the analysis data characteristics-based and intelligently abandons the intervention of manual prior knowledge. Then, the SDAE models are established under each scale to learn the high-order and robust features from the data with noise and fluctuation, and all monitoring results of the different scales are integrated using the Bayesian inference. Finally, given the temporal information in sequence data, the state representation of previous events is embedded into the current decision through a sliding window. The numerical process, benchmark Tennessee Eastman and real steel plate process are used to analyze the superiority of the proposed method (MSDAE-TP) over other deep learning-based monitoring methods.
•SDAE is employed after theoretically analysis to establish a robust model to perform fault detection.•Multiscale analysis is employed based on agglomerative hierarchical clustering to achieve a more reasonable decomposition.•Temporal information is considered into the current statistical indicator to provide a comprehensive judgment. |
|---|---|
| AbstractList | Deep learning-based process monitoring has achieved remarkable progress. Generally, a deep model is empirically selected before the data features are learned. In this study, the interpretability and suitability of stacked denoising autoencoder (SDAE) in process monitoring territory are theoretically analyzed and validated. Considering that the data will show different feature representations at different scales, such as overall outline, local information, and microscopic details, this study utilizes the concept of multiscale analysis to mine the feature information of raw data deeply in different scales. The multiscale analysis is performed on the basis of agglomerative hierarchical clustering and silhouette coefficient, which makes the analysis data characteristics-based and intelligently abandons the intervention of manual prior knowledge. Then, the SDAE models are established under each scale to learn the high-order and robust features from the data with noise and fluctuation, and all monitoring results of the different scales are integrated using the Bayesian inference. Finally, given the temporal information in sequence data, the state representation of previous events is embedded into the current decision through a sliding window. The numerical process, benchmark Tennessee Eastman and real steel plate process are used to analyze the superiority of the proposed method (MSDAE-TP) over other deep learning-based monitoring methods.
•SDAE is employed after theoretically analysis to establish a robust model to perform fault detection.•Multiscale analysis is employed based on agglomerative hierarchical clustering to achieve a more reasonable decomposition.•Temporal information is considered into the current statistical indicator to provide a comprehensive judgment. |
| ArticleNumber | 106525 |
| Author | Yan, Xuefeng Yu, Jianbo |
| Author_xml | – sequence: 1 givenname: Jianbo surname: Yu fullname: Yu, Jianbo – sequence: 2 givenname: Xuefeng orcidid: 0000-0001-5622-8686 surname: Yan fullname: Yan, Xuefeng email: xfyan@ecust.edu.cn |
| BookMark | eNp9kEtOwzAQhr0oEm3hAqx8gZTYadxEYoMqXlIRG1hbjj1ppyR2ZbtFvQqnxaGsWHTjx2i-f-xvQkbWWSDkhuUzljNxu52p4PSM53woiJKXIzJmpaiyeT0Xl2QSwjZPjTWvxuT7dd9FDFp1QNFG6Dpcg420ValODUTQEZ2l4Rgi9LRRAQxNd7Ved64HryIegG4wnbzeYMqhutunXo92TfdhWENU-jNhBqzD34raRwdWOwOefmHc0JS9cz7BaFvnezXMvCIXreoCXP_tU_Lx-PC-fM5Wb08vy_tVpos8j1mry1aYeW3qRglV8lYIUwpeGF5CUQk256qBpii4Zo1gzDTaVE29SJ2iKHWxKKaEn3K1dyF4aOXOY6_8UbJcDkblVg5G5WBUnowmqPoHaYy_z45eYXcevTuhkD51SOZk0JhsgEGfbEvj8Bz-A-XQm-c |
| CitedBy_id | crossref_primary_10_3390_act13110440 crossref_primary_10_1016_j_ins_2021_12_106 crossref_primary_10_1109_ACCESS_2025_3596859 crossref_primary_10_1016_j_conengprac_2022_105156 crossref_primary_10_1016_j_engappai_2023_105859 crossref_primary_10_1016_j_asoc_2024_111594 crossref_primary_10_1007_s42243_024_01197_3 crossref_primary_10_1016_j_jii_2021_100216 crossref_primary_10_1016_j_asoc_2025_113407 crossref_primary_10_3390_machines13060507 crossref_primary_10_1109_JIOT_2024_3496927 crossref_primary_10_1007_s10845_023_02103_6 crossref_primary_10_1016_j_arcontrol_2022_09_005 crossref_primary_10_1016_j_ins_2022_05_024 crossref_primary_10_3390_electronics13234622 crossref_primary_10_1016_j_compind_2021_103394 crossref_primary_10_1016_j_psep_2021_07_002 crossref_primary_10_1109_ACCESS_2023_3299852 crossref_primary_10_1109_TIM_2025_3574904 crossref_primary_10_1016_j_ijrefrig_2023_09_002 crossref_primary_10_1016_j_artint_2023_104012 crossref_primary_10_1016_j_asoc_2024_111896 crossref_primary_10_1016_j_asoc_2021_107382 crossref_primary_10_1155_2022_1507630 crossref_primary_10_1177_10775463231217530 crossref_primary_10_3390_app11167733 crossref_primary_10_1109_TCYB_2022_3185588 |
| Cites_doi | 10.1109/TII.2019.2896665 10.1016/j.compchemeng.2019.106515 10.1109/TII.2017.2690940 10.1016/j.neucom.2018.12.041 10.1016/j.jprocont.2015.06.007 10.1016/j.isatra.2018.10.011 10.1016/0098-1354(93)80018-I 10.1016/S0169-7439(03)00063-7 10.1109/TIE.2017.2745452 10.1021/acs.iecr.9b02391 10.1016/S0959-1524(97)80001-7 10.1109/TNNLS.2018.2889776 10.1016/j.asoc.2013.09.024 10.1016/j.asoc.2019.105526 10.1016/j.asoc.2018.12.029 10.1021/acs.iecr.7b00949 10.1002/cjce.23249 10.1109/TII.2019.2902274 10.1016/j.asoc.2017.09.019 10.1109/TASE.2012.2230628 10.1016/j.jprocont.2016.01.001 10.1016/j.chemolab.2019.03.012 10.1016/S0098-1354(01)00683-4 10.1109/TPAMI.2017.2700381 10.1016/j.jprocont.2006.11.002 10.1016/j.arcontrol.2012.09.004 10.1021/acs.iecr.7b01721 10.1109/TIE.2018.2873100 10.1109/TIE.2018.2844805 10.1038/nature14539 10.1016/j.jprocont.2015.04.014 10.1109/TIE.2015.2466557 10.1016/j.asoc.2019.106060 10.1016/0377-0427(87)90125-7 10.1126/science.1127647 10.1109/NAFIPS.2010.5548298 10.1016/j.chemolab.2017.09.021 10.1016/j.ces.2003.09.012 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier B.V. |
| Copyright_xml | – notice: 2020 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2020.106525 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_asoc_2020_106525 S1568494620304646 |
| 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 AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFO ACGFS ACNNM ACRLP ACRPL ACZNC ADBBV ADEZE ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AFJKZ AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV CS3 EBS EFJIC 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 SSH SST SSV SSZ T5K UHS UNMZH ~G- 9DU AAYWO AAYXX ACLOT ACVFH ADCNI AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c300t-fc5f6d49d9ba6a52f66d5623d25e386142abeb332c1b611dbcd8b97a52635c373 |
| ISICitedReferencesCount | 31 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000576772600006&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 07:07:00 EST 2025 Tue Nov 18 22:42:29 EST 2025 Sun Apr 06 06:53:43 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Process monitoring Stacked denoising autoencoder Robust features Multiscale analysis Temporal information |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-fc5f6d49d9ba6a52f66d5623d25e386142abeb332c1b611dbcd8b97a52635c373 |
| ORCID | 0000-0001-5622-8686 |
| ParticipantIDs | crossref_primary_10_1016_j_asoc_2020_106525 crossref_citationtrail_10_1016_j_asoc_2020_106525 elsevier_sciencedirect_doi_10_1016_j_asoc_2020_106525 |
| PublicationCentury | 2000 |
| PublicationDate | October 2020 2020-10-00 |
| PublicationDateYYYYMMDD | 2020-10-01 |
| PublicationDate_xml | – month: 10 year: 2020 text: October 2020 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Krizhevsky, Sutskever, Hinton (b23) 2013; 60 Kim, Lee (b11) 2003; 67 Md Nor, Hussain, Che Hassan (b18) 2017; 61 M. Buscema, S. Terzi, W. Tastle, A new meta-classifier, in: 2010 Annual Meeting of the North American Fuzzy Information Processing Society, 2010, pp. 1–7. Jiang, Yan (b41) 2015; 32 Park, Kim, Kim (b24) 2018; 40 Pan, Chen, Zhou, Wang, He (b39) 2019; 15 Wang, Si, Huang, Lou (b1) 2018; 96 Yu, Yan (b32) 2018; 57 Zhang, Hao, Chen, Ding, Peng (b3) 2015; 33 Zhu, Cheng, Zhang, Wu, Shao (b27) 2020; 88 Liu, Jia, Vong, Bu, Han, Tang (b28) 2017; 13 Yu, Yan (b30) 2019 Lecun, Bengio, Hinton (b43) 2015; 521 Qin, Yu (b5) 2007; 17 Wang, Mao (b16) 2019; 76 Huang, Yan (b42) 2016; 39 Vincent, Larochelle, Bengio, Manzagol (b37) 2008 Ge (b4) 2017; 171 Ma, Sun, Chen (b25) 2018 Li, Zhao, Gao (b19) 2018; 65 Cheng, He, Zhao (b33) 2019; 129 Yu, Zhao (b17) 2018 Haidong, Junsheng, Hongkai, Yu, Zhantao (b36) 2019 Lee, Yoo, Sang, Vanrolleghem, Lee (b12) 2004; 59 Liu, Qin, Chai (b14) 2013; 10 Iqbal, Maniak, Doctor, Karyotis (b35) 2019; 15 Jiang, He, Yan, Xie (b40) 2019; 66 Ruder (b44) 2016 Xiao, Yan, Farajtabar, Song, Yang, Zha (b22) 2019; 30 Lou, Wang (b13) 2017; 56 Jiang, Yan, Huang (b6) 2019; 58 Qin (b7) 2012; 36 Deng, Tian, Chen, Harris (b10) 2018 Jiang, Song, Ge, Chen (b45) 2017; 56 Zhou, Guo, Celler, Su (b15) 2014; 14 Yan, Yan (b31) 2019; 81 Chen, Yang, Peng, Dan, Li, Gui (b20) 2019; 66 Hinton, Salakhutdinov (b21) 2006; 313 Plakias, Boutalis (b34) 2019; 332 Kutyniok, Labate (b38) 2012 Jiang, Yan, Huang (b47) 2015; 63 Downs, Vogel (b48) 1993; 17 Kano, Hasebe, Hashimoto, Ohno (b8) 2001; 25 Yu, Yan (b26) 2018; 84 Quiñones Grueiro, Prieto-Moreno, Verde, Llanes-Santiago (b2) 2019; 189 Rousseeuw (b46) 1987; 20 Costilla-Reyes, Scully, Ozanyan (b29) 2017 Dayal, Macgregor (b9) 1997; 7 Wang (10.1016/j.asoc.2020.106525_b16) 2019; 76 Jiang (10.1016/j.asoc.2020.106525_b40) 2019; 66 Ruder (10.1016/j.asoc.2020.106525_b44) 2016 Yu (10.1016/j.asoc.2020.106525_b32) 2018; 57 Chen (10.1016/j.asoc.2020.106525_b20) 2019; 66 Quiñones Grueiro (10.1016/j.asoc.2020.106525_b2) 2019; 189 Lou (10.1016/j.asoc.2020.106525_b13) 2017; 56 Ma (10.1016/j.asoc.2020.106525_b25) 2018 Pan (10.1016/j.asoc.2020.106525_b39) 2019; 15 Vincent (10.1016/j.asoc.2020.106525_b37) 2008 Ge (10.1016/j.asoc.2020.106525_b4) 2017; 171 Deng (10.1016/j.asoc.2020.106525_b10) 2018 Lee (10.1016/j.asoc.2020.106525_b12) 2004; 59 Kano (10.1016/j.asoc.2020.106525_b8) 2001; 25 Downs (10.1016/j.asoc.2020.106525_b48) 1993; 17 Kim (10.1016/j.asoc.2020.106525_b11) 2003; 67 Yu (10.1016/j.asoc.2020.106525_b26) 2018; 84 Yan (10.1016/j.asoc.2020.106525_b31) 2019; 81 Md Nor (10.1016/j.asoc.2020.106525_b18) 2017; 61 Wang (10.1016/j.asoc.2020.106525_b1) 2018; 96 Zhang (10.1016/j.asoc.2020.106525_b3) 2015; 33 10.1016/j.asoc.2020.106525_b49 Costilla-Reyes (10.1016/j.asoc.2020.106525_b29) 2017 Yu (10.1016/j.asoc.2020.106525_b17) 2018 Liu (10.1016/j.asoc.2020.106525_b28) 2017; 13 Jiang (10.1016/j.asoc.2020.106525_b45) 2017; 56 Cheng (10.1016/j.asoc.2020.106525_b33) 2019; 129 Zhou (10.1016/j.asoc.2020.106525_b15) 2014; 14 Qin (10.1016/j.asoc.2020.106525_b5) 2007; 17 Jiang (10.1016/j.asoc.2020.106525_b41) 2015; 32 Park (10.1016/j.asoc.2020.106525_b24) 2018; 40 Yu (10.1016/j.asoc.2020.106525_b30) 2019 Lecun (10.1016/j.asoc.2020.106525_b43) 2015; 521 Zhu (10.1016/j.asoc.2020.106525_b27) 2020; 88 Jiang (10.1016/j.asoc.2020.106525_b47) 2015; 63 Dayal (10.1016/j.asoc.2020.106525_b9) 1997; 7 Rousseeuw (10.1016/j.asoc.2020.106525_b46) 1987; 20 Qin (10.1016/j.asoc.2020.106525_b7) 2012; 36 Plakias (10.1016/j.asoc.2020.106525_b34) 2019; 332 Xiao (10.1016/j.asoc.2020.106525_b22) 2019; 30 Huang (10.1016/j.asoc.2020.106525_b42) 2016; 39 Jiang (10.1016/j.asoc.2020.106525_b6) 2019; 58 Kutyniok (10.1016/j.asoc.2020.106525_b38) 2012 Liu (10.1016/j.asoc.2020.106525_b14) 2013; 10 Li (10.1016/j.asoc.2020.106525_b19) 2018; 65 Haidong (10.1016/j.asoc.2020.106525_b36) 2019 Iqbal (10.1016/j.asoc.2020.106525_b35) 2019; 15 Krizhevsky (10.1016/j.asoc.2020.106525_b23) 2013; 60 Hinton (10.1016/j.asoc.2020.106525_b21) 2006; 313 |
| References_xml | – volume: 59 start-page: 223 year: 2004 end-page: 234 ident: b12 article-title: Nonlinear process monitoring using kernel principal component analysis publication-title: Chem. Eng. Sci. – volume: 17 start-page: 245 year: 1993 end-page: 255 ident: b48 article-title: A plant-wide industrial process control problem publication-title: Comput. Chem. Eng. – year: 2019 ident: b30 article-title: Whole process monitoring based on unstable neuron output information in hidden layers of deep belief network publication-title: IEEE Trans. Cybern. – volume: 33 start-page: 112 year: 2015 end-page: 126 ident: b3 article-title: A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches publication-title: J. Process Control – volume: 171 start-page: 16 year: 2017 end-page: 25 ident: b4 article-title: Review on data-driven modeling and monitoring for plant-wide industrial processes publication-title: Chemometr. Intell. Lab. Syst. – volume: 15 start-page: 5119 year: 2019 end-page: 5128 ident: b39 article-title: A novel deep learning network via multiscale inner product with locally connected feature extraction for intelligent fault detection publication-title: IEEE Trans. Ind. Inf. – volume: 313 start-page: 504 year: 2006 ident: b21 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – volume: 10 start-page: 687 year: 2013 end-page: 698 ident: b14 article-title: Decentralized fault diagnosis of continuous annealing processes based on multilevel PCA publication-title: IEEE Trans. Autom. Sci. Eng. – volume: 20 year: 1987 ident: b46 article-title: Silhouettes : A graphical aid to the interpretation and validation of cluster analysis publication-title: J. Comput. Appl. Math. – volume: 30 start-page: 3124 year: 2019 end-page: 3136 ident: b22 article-title: Learning time series associated event sequences with recurrent point process networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 63 start-page: 377 year: 2015 end-page: 386 ident: b47 article-title: Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference publication-title: IEEE Trans. Ind. Electron. – volume: 40 start-page: 945 year: 2018 end-page: 957 ident: b24 article-title: Retrieval of sentence sequences for an image stream via coherence recurrent convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 25 start-page: 1103 year: 2001 end-page: 1113 ident: b8 article-title: A new multivariate statistical process monitoring method using principal component analysis publication-title: Comput. Chem. Eng. – volume: 88 year: 2020 ident: b27 article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings publication-title: Appl. Soft Comput. – year: 2012 ident: b38 article-title: Shearlets: Multiscale Analysis for Multivariate Data – reference: M. Buscema, S. Terzi, W. Tastle, A new meta-classifier, in: 2010 Annual Meeting of the North American Fuzzy Information Processing Society, 2010, pp. 1–7. – start-page: 1 year: 2017 ident: b29 article-title: Deep neural networks for learning spatio-temporal features from tomography sensors publication-title: IEEE Trans. Ind. Electron. – volume: 332 start-page: 396 year: 2019 end-page: 405 ident: b34 article-title: Exploiting the generative adversarial framework for one-class multi-dimensional fault detection publication-title: Neurocomputing – volume: 521 start-page: 436 year: 2015 ident: b43 article-title: Deep learning publication-title: Nature – volume: 65 start-page: 2683 year: 2018 end-page: 2692 ident: b19 article-title: Linearity evaluation and variable subset partition based hierarchical process modeling and monitoring publication-title: IEEE Trans. Ind. Electron. – volume: 76 start-page: 505 year: 2019 end-page: 516 ident: b16 article-title: Outlier detection based on Gaussian process with application to industrial processes publication-title: Appl. Soft Comput. – volume: 67 start-page: 109 year: 2003 end-page: 123 ident: b11 article-title: Process monitoring based on probabilistic PCA publication-title: Chemometr. Intell. Lab. Syst. – volume: 66 start-page: 3196 year: 2019 end-page: 3207 ident: b40 article-title: Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox publication-title: IEEE Trans. Ind. Electron. – volume: 189 start-page: 56 year: 2019 end-page: 71 ident: b2 article-title: Data-driven monitoring of multimode continuous processes: A review publication-title: Chemometr. Intell. Lab. Syst. – volume: 13 start-page: 1213 year: 2017 end-page: 1226 ident: b28 article-title: Capturing high-discriminative fault features for electronics-rich analog system via deep learning publication-title: IEEE Trans. Ind. Inf. – volume: 15 start-page: 3077 year: 2019 end-page: 3084 ident: b35 article-title: Fault detection and isolation in industrial processes using deep learning approaches publication-title: IEEE Trans. Ind. Inf. – volume: 14 start-page: 4 year: 2014 end-page: 11 ident: b15 article-title: Fault detection and identification spanning multiple processes by integrating PCA with neural network publication-title: Appl. Soft Comput. – year: 2019 ident: b36 article-title: Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing publication-title: Knowl.-Based Syst. – volume: 56 start-page: 7503 year: 2017 end-page: 7515 ident: b45 article-title: Robust self-supervised model and its application for fault detection publication-title: Ind. Eng. Chem. Res. – year: 2018 ident: b10 article-title: Deep principal component analysis based on layerwise feature extraction and its application to nonlinear process monitoring publication-title: IEEE Trans. Control Syst. Technol. – volume: 56 year: 2017 ident: b13 article-title: Multimode continuous processes monitoring based on hidden semi-Markov model and principle component analysis publication-title: Ind. Eng. Chem. Res. – volume: 60 start-page: 2012 year: 2013 ident: b23 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM – volume: 66 start-page: 6321 year: 2019 end-page: 6330 ident: b20 article-title: A cumulative canonical correlation analysis-based sensor precision degradation detection method publication-title: IEEE Trans. Ind. Electron. – volume: 81 year: 2019 ident: b31 article-title: Design teacher and supervised dual stacked auto-encoders for quality-relevant fault detection in industrial process publication-title: Appl. Soft Comput. – volume: 7 start-page: 169 year: 1997 end-page: 179 ident: b9 article-title: Recursive exponentially weighted PLS and its applications to adaptive control and prediction publication-title: J. Process Control – year: 2018 ident: b17 article-title: Recursive exponential slow feature analysis for fine-scale adaptive processes monitoring with comprehensive operation status identification publication-title: IEEE Trans. Ind. Inf. – volume: 57 start-page: 15479 year: 2018 end-page: 15490 ident: b32 article-title: Layer-by-layer enhancement strategy of favorable features of the deep belief network for industrial process monitoring publication-title: Ind. Eng. Chem. Res. – volume: 17 start-page: 221 year: 2007 end-page: 227 ident: b5 article-title: Recent developments in multivariable controller performance monitoring publication-title: J. Process Control – volume: 39 start-page: 88 year: 2016 end-page: 99 ident: b42 article-title: Related and independent variable fault detection based on KPCA and SVDD publication-title: J. Process Control – start-page: 1096 year: 2008 end-page: 1103 ident: b37 article-title: Extracting and composing robust features with denoising autoencoders publication-title: Proceedings of the 25th International Conference on Machine Learning – volume: 96 start-page: 2073 year: 2018 end-page: 2085 ident: b1 article-title: Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008–2017 publication-title: Can. J. Chem. Eng. – volume: 32 start-page: 38 year: 2015 end-page: 50 ident: b41 article-title: Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA publication-title: J. Process Control – volume: 58 start-page: 12899 year: 2019 end-page: 12912 ident: b6 article-title: Review and perspectives of data-driven distributed monitoring for industrial plant-wide processes publication-title: Ind. Eng. Chem. Res. – volume: 129 year: 2019 ident: b33 article-title: A novel process monitoring approach based on variational recurrent autoencoder publication-title: Comput. Chem. Eng. – volume: 61 start-page: 959 year: 2017 end-page: 972 ident: b18 article-title: Fault diagnosis and classification framework using multi-scale classification based on kernel Fisher discriminant analysis for chemical process system publication-title: Appl. Soft Comput. – year: 2016 ident: b44 article-title: An overview of gradient descent optimization algorithms – volume: 36 start-page: 220 year: 2012 end-page: 234 ident: b7 article-title: Survey on data-driven industrial process monitoring and diagnosis publication-title: Annu. Rev. Control – start-page: 1 year: 2018 ident: b25 article-title: Deep coupling autoencoder for fault diagnosis with multimodal sensory data publication-title: IEEE Trans. Ind. Inf. – volume: 84 start-page: 247 year: 2018 end-page: 261 ident: b26 article-title: Active features extracted by deep belief network for process monitoring publication-title: ISA Trans. – volume: 15 start-page: 5119 year: 2019 ident: 10.1016/j.asoc.2020.106525_b39 article-title: A novel deep learning network via multiscale inner product with locally connected feature extraction for intelligent fault detection publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2019.2896665 – volume: 129 year: 2019 ident: 10.1016/j.asoc.2020.106525_b33 article-title: A novel process monitoring approach based on variational recurrent autoencoder publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2019.106515 – volume: 13 start-page: 1213 year: 2017 ident: 10.1016/j.asoc.2020.106525_b28 article-title: Capturing high-discriminative fault features for electronics-rich analog system via deep learning publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2017.2690940 – volume: 332 start-page: 396 year: 2019 ident: 10.1016/j.asoc.2020.106525_b34 article-title: Exploiting the generative adversarial framework for one-class multi-dimensional fault detection publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.12.041 – volume: 57 start-page: 15479 year: 2018 ident: 10.1016/j.asoc.2020.106525_b32 article-title: Layer-by-layer enhancement strategy of favorable features of the deep belief network for industrial process monitoring publication-title: Ind. Eng. Chem. Res. – year: 2018 ident: 10.1016/j.asoc.2020.106525_b17 article-title: Recursive exponential slow feature analysis for fine-scale adaptive processes monitoring with comprehensive operation status identification publication-title: IEEE Trans. Ind. Inf. – volume: 33 start-page: 112 year: 2015 ident: 10.1016/j.asoc.2020.106525_b3 article-title: A comparison and evaluation of key performance indicator-based multivariate statistics process monitoring approaches publication-title: J. Process Control doi: 10.1016/j.jprocont.2015.06.007 – volume: 84 start-page: 247 year: 2018 ident: 10.1016/j.asoc.2020.106525_b26 article-title: Active features extracted by deep belief network for process monitoring publication-title: ISA Trans. doi: 10.1016/j.isatra.2018.10.011 – volume: 17 start-page: 245 year: 1993 ident: 10.1016/j.asoc.2020.106525_b48 article-title: A plant-wide industrial process control problem publication-title: Comput. Chem. Eng. doi: 10.1016/0098-1354(93)80018-I – volume: 67 start-page: 109 year: 2003 ident: 10.1016/j.asoc.2020.106525_b11 article-title: Process monitoring based on probabilistic PCA publication-title: Chemometr. Intell. Lab. Syst. doi: 10.1016/S0169-7439(03)00063-7 – volume: 65 start-page: 2683 year: 2018 ident: 10.1016/j.asoc.2020.106525_b19 article-title: Linearity evaluation and variable subset partition based hierarchical process modeling and monitoring publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2017.2745452 – start-page: 1096 year: 2008 ident: 10.1016/j.asoc.2020.106525_b37 article-title: Extracting and composing robust features with denoising autoencoders – volume: 58 start-page: 12899 year: 2019 ident: 10.1016/j.asoc.2020.106525_b6 article-title: Review and perspectives of data-driven distributed monitoring for industrial plant-wide processes publication-title: Ind. Eng. Chem. Res. doi: 10.1021/acs.iecr.9b02391 – volume: 7 start-page: 169 year: 1997 ident: 10.1016/j.asoc.2020.106525_b9 article-title: Recursive exponentially weighted PLS and its applications to adaptive control and prediction publication-title: J. Process Control doi: 10.1016/S0959-1524(97)80001-7 – volume: 30 start-page: 3124 year: 2019 ident: 10.1016/j.asoc.2020.106525_b22 article-title: Learning time series associated event sequences with recurrent point process networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2018.2889776 – volume: 14 start-page: 4 year: 2014 ident: 10.1016/j.asoc.2020.106525_b15 article-title: Fault detection and identification spanning multiple processes by integrating PCA with neural network publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2013.09.024 – volume: 81 year: 2019 ident: 10.1016/j.asoc.2020.106525_b31 article-title: Design teacher and supervised dual stacked auto-encoders for quality-relevant fault detection in industrial process publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.105526 – volume: 76 start-page: 505 year: 2019 ident: 10.1016/j.asoc.2020.106525_b16 article-title: Outlier detection based on Gaussian process with application to industrial processes publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.12.029 – volume: 56 start-page: 7503 year: 2017 ident: 10.1016/j.asoc.2020.106525_b45 article-title: Robust self-supervised model and its application for fault detection publication-title: Ind. Eng. Chem. Res. doi: 10.1021/acs.iecr.7b00949 – volume: 96 start-page: 2073 year: 2018 ident: 10.1016/j.asoc.2020.106525_b1 article-title: Survey on the theoretical research and engineering applications of multivariate statistics process monitoring algorithms: 2008–2017 publication-title: Can. J. Chem. Eng. doi: 10.1002/cjce.23249 – volume: 15 start-page: 3077 year: 2019 ident: 10.1016/j.asoc.2020.106525_b35 article-title: Fault detection and isolation in industrial processes using deep learning approaches publication-title: IEEE Trans. Ind. Inf. doi: 10.1109/TII.2019.2902274 – year: 2018 ident: 10.1016/j.asoc.2020.106525_b10 article-title: Deep principal component analysis based on layerwise feature extraction and its application to nonlinear process monitoring publication-title: IEEE Trans. Control Syst. Technol. – year: 2019 ident: 10.1016/j.asoc.2020.106525_b36 article-title: Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing publication-title: Knowl.-Based Syst. – volume: 61 start-page: 959 year: 2017 ident: 10.1016/j.asoc.2020.106525_b18 article-title: Fault diagnosis and classification framework using multi-scale classification based on kernel Fisher discriminant analysis for chemical process system publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2017.09.019 – volume: 10 start-page: 687 year: 2013 ident: 10.1016/j.asoc.2020.106525_b14 article-title: Decentralized fault diagnosis of continuous annealing processes based on multilevel PCA publication-title: IEEE Trans. Autom. Sci. Eng. doi: 10.1109/TASE.2012.2230628 – volume: 39 start-page: 88 year: 2016 ident: 10.1016/j.asoc.2020.106525_b42 article-title: Related and independent variable fault detection based on KPCA and SVDD publication-title: J. Process Control doi: 10.1016/j.jprocont.2016.01.001 – volume: 189 start-page: 56 year: 2019 ident: 10.1016/j.asoc.2020.106525_b2 article-title: Data-driven monitoring of multimode continuous processes: A review publication-title: Chemometr. Intell. Lab. Syst. doi: 10.1016/j.chemolab.2019.03.012 – volume: 25 start-page: 1103 year: 2001 ident: 10.1016/j.asoc.2020.106525_b8 article-title: A new multivariate statistical process monitoring method using principal component analysis publication-title: Comput. Chem. Eng. doi: 10.1016/S0098-1354(01)00683-4 – volume: 40 start-page: 945 year: 2018 ident: 10.1016/j.asoc.2020.106525_b24 article-title: Retrieval of sentence sequences for an image stream via coherence recurrent convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2700381 – start-page: 1 year: 2018 ident: 10.1016/j.asoc.2020.106525_b25 article-title: Deep coupling autoencoder for fault diagnosis with multimodal sensory data publication-title: IEEE Trans. Ind. Inf. – volume: 17 start-page: 221 year: 2007 ident: 10.1016/j.asoc.2020.106525_b5 article-title: Recent developments in multivariable controller performance monitoring publication-title: J. Process Control doi: 10.1016/j.jprocont.2006.11.002 – volume: 36 start-page: 220 year: 2012 ident: 10.1016/j.asoc.2020.106525_b7 article-title: Survey on data-driven industrial process monitoring and diagnosis publication-title: Annu. Rev. Control doi: 10.1016/j.arcontrol.2012.09.004 – volume: 56 year: 2017 ident: 10.1016/j.asoc.2020.106525_b13 article-title: Multimode continuous processes monitoring based on hidden semi-Markov model and principle component analysis publication-title: Ind. Eng. Chem. Res. doi: 10.1021/acs.iecr.7b01721 – volume: 66 start-page: 6321 year: 2019 ident: 10.1016/j.asoc.2020.106525_b20 article-title: A cumulative canonical correlation analysis-based sensor precision degradation detection method publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2018.2873100 – volume: 66 start-page: 3196 year: 2019 ident: 10.1016/j.asoc.2020.106525_b40 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 – year: 2019 ident: 10.1016/j.asoc.2020.106525_b30 article-title: Whole process monitoring based on unstable neuron output information in hidden layers of deep belief network publication-title: IEEE Trans. Cybern. – volume: 521 start-page: 436 year: 2015 ident: 10.1016/j.asoc.2020.106525_b43 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 32 start-page: 38 year: 2015 ident: 10.1016/j.asoc.2020.106525_b41 article-title: Nonlinear plant-wide process monitoring using MI-spectral clustering and Bayesian inference-based multiblock KPCA publication-title: J. Process Control doi: 10.1016/j.jprocont.2015.04.014 – volume: 63 start-page: 377 year: 2015 ident: 10.1016/j.asoc.2020.106525_b47 article-title: Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2015.2466557 – year: 2012 ident: 10.1016/j.asoc.2020.106525_b38 – volume: 60 start-page: 2012 year: 2013 ident: 10.1016/j.asoc.2020.106525_b23 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM – volume: 88 year: 2020 ident: 10.1016/j.asoc.2020.106525_b27 article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.106060 – volume: 20 year: 1987 ident: 10.1016/j.asoc.2020.106525_b46 article-title: Silhouettes : A graphical aid to the interpretation and validation of cluster analysis publication-title: J. Comput. Appl. Math. doi: 10.1016/0377-0427(87)90125-7 – year: 2016 ident: 10.1016/j.asoc.2020.106525_b44 – volume: 313 start-page: 504 year: 2006 ident: 10.1016/j.asoc.2020.106525_b21 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – start-page: 1 year: 2017 ident: 10.1016/j.asoc.2020.106525_b29 article-title: Deep neural networks for learning spatio-temporal features from tomography sensors publication-title: IEEE Trans. Ind. Electron. – ident: 10.1016/j.asoc.2020.106525_b49 doi: 10.1109/NAFIPS.2010.5548298 – volume: 171 start-page: 16 year: 2017 ident: 10.1016/j.asoc.2020.106525_b4 article-title: Review on data-driven modeling and monitoring for plant-wide industrial processes publication-title: Chemometr. Intell. Lab. Syst. doi: 10.1016/j.chemolab.2017.09.021 – volume: 59 start-page: 223 year: 2004 ident: 10.1016/j.asoc.2020.106525_b12 article-title: Nonlinear process monitoring using kernel principal component analysis publication-title: Chem. Eng. Sci. doi: 10.1016/j.ces.2003.09.012 |
| SSID | ssj0016928 |
| Score | 2.4419405 |
| Snippet | Deep learning-based process monitoring has achieved remarkable progress. Generally, a deep model is empirically selected before the data features are learned.... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 106525 |
| SubjectTerms | Multiscale analysis Process monitoring Robust features Stacked denoising autoencoder Temporal information |
| Title | Multiscale intelligent fault detection system based on agglomerative hierarchical clustering using stacked denoising autoencoder with temporal information |
| URI | https://dx.doi.org/10.1016/j.asoc.2020.106525 |
| Volume | 95 |
| WOSCitedRecordID | wos000576772600006&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/eLvHCXMwtV07b9RAEF4dCQVNCC8RXtqC7uSTH-e1t4xQEKSIKIJ0nbUvR0QnO8rZUVr-Rn4tM_s6J0BEChrrbrUeW57Ps7PjmW8I-Si0ElKkIlFY1oOU5kmtdJZUZmmYhB2REMI2m6hOTurVin-bzX6GWpirddV19fU1v_ivqoYxUDaWzj5A3VEoDMBvUDocQe1w_CfF25LaDTx6Y7kgHN_mMG8FjM-1GYxrDu4onOe4imn8YiDOztY9RqhsLhF2yLbfGCx_yHpEOgUMKowbH3-Al1-DtK7_YUfEOPRIiYnMFC606yivkNEj1kdOHeHg_W5gGbB57eMQFlHbJsyiC6Ar-zjmQrWr0bTGz_TRCtiahry3aGAREtyHHb0F5uXEhMIetXS10L9ZdxdoOF8IAO4CpS-2k29Tad9Z4mLiYchpO29QRoMyGifjEdnNq5KDYdw9_Hq0Oo6fohi3DXrjjfvKK5ckePdO_uzdTDyW032y57ca9NBB5BmZme45eRraeFBv1V-Qmy1i6AQx1CKGRsRQhxhqEUPh_y3E0Cli6BYx1CKGesTQiBg6QQxFxNCAGDpBzEvy_fPR6acviW_ZkagiTYekVWXL9JJrLgUTZd4yptHD1nlpihpcwVxII4siV5lkWaal0rXkFcwEx1cVVfGK7HR9Z14Tmqaq1EIoybRetrqqVc6XhRSKCdhm5MUBycKjbpTns8e2Kuvm70o-IPN4zoVjc7l3dhk02Hh_1PmZDQDynvPePOgqb8mT7YvyjuwMl6N5Tx6rK9D85QePxl9D9Le9 |
| 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=Multiscale+intelligent+fault+detection+system+based+on+agglomerative+hierarchical+clustering+using+stacked+denoising+autoencoder+with+temporal+information&rft.jtitle=Applied+soft+computing&rft.au=Yu%2C+Jianbo&rft.au=Yan%2C+Xuefeng&rft.date=2020-10-01&rft.issn=1568-4946&rft.volume=95&rft.spage=106525&rft_id=info:doi/10.1016%2Fj.asoc.2020.106525&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_asoc_2020_106525 |
| 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 |