Full metadata record

DC Field Value Language
dc.contributor.authorLee, Hodong-
dc.contributor.authorKim, Changsoo-
dc.contributor.authorJeong, Dong Hwi-
dc.contributor.authorLee, Jong Min-
dc.date.accessioned2024-01-19T13:03:51Z-
dc.date.available2024-01-19T13:03:51Z-
dc.date.created2022-01-25-
dc.date.issued2021-12-
dc.identifier.issn0256-1115-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/115978-
dc.description.abstractProcess monitoring plays an essential role in safe and profitable operations. Various data-driven fault detection models have been suggested, but they cannot perform properly when the training data are insufficient or the information to construct the manifold is confined to a specific region. In this study, a process monitoring framework integrated with data augmentation is proposed to supplement rare but informative samples for the boundary regions of the normal state. To generate data for augmentation, a variational autoencoder was employed to exploit its advantage of stable convergence. For the construction of the process monitoring system, an autoencoder that can extract useful features in an unsupervised manner was used. To illustrate the efficacy of the proposed method, a case study for the Tennessee Eastman process was applied. The results show that the proposed method can improve the monitoring performance compared to the autoencoder without data augmentation in terms of fault detection accuracy and delay, particularly within the feature space.-
dc.languageEnglish-
dc.publisher한국화학공학회-
dc.titleData-driven fault detection for chemical processes using autoencoder with data augmentation-
dc.typeArticle-
dc.identifier.doi10.1007/s11814-021-0894-1-
dc.description.journalClass1-
dc.identifier.bibliographicCitationKorean Journal of Chemical Engineering, v.38, no.12, pp.2406 - 2422-
dc.citation.titleKorean Journal of Chemical Engineering-
dc.citation.volume38-
dc.citation.number12-
dc.citation.startPage2406-
dc.citation.endPage2422-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.description.journalRegisteredClasskci-
dc.identifier.kciidART002779247-
dc.identifier.wosid000698034200002-
dc.identifier.scopusid2-s2.0-85115146159-
dc.relation.journalWebOfScienceCategoryChemistry, Multidisciplinary-
dc.relation.journalWebOfScienceCategoryEngineering, Chemical-
dc.relation.journalResearchAreaChemistry-
dc.relation.journalResearchAreaEngineering-
dc.type.docTypeArticle-
dc.subject.keywordPlusCOMPONENT ANALYSIS-
dc.subject.keywordPlusNEURAL-NETWORKS-
dc.subject.keywordPlusDIAGNOSIS-
dc.subject.keywordAuthorProcess Monitoring-
dc.subject.keywordAuthorFault Detection and Isolation (FDI)-
dc.subject.keywordAuthorAutoencoder-
dc.subject.keywordAuthorVariational Autoencoder-
dc.subject.keywordAuthorData Augmentation-
Appears in Collections:
KIST Article > 2021
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE