Cross-domain fault diagnosis through optimal transport for a CSTR process

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorMontesuma, Eduardo Fernandesen_US
dc.contributor.authorMulas, Michelaen_US
dc.contributor.authorCorona, Francescoen_US
dc.contributor.authorMboula, Fred Maurice Ngoleen_US
dc.contributor.departmentDepartment of Chemical and Metallurgical Engineeringen
dc.contributor.groupauthorProcess Control and Automationen
dc.contributor.organizationUniversidade Federal do Cearáen_US
dc.contributor.organizationUniversité Paris-Saclayen_US
dc.date.accessioned2022-09-21T06:06:09Z
dc.date.available2022-09-21T06:06:09Z
dc.date.issued2022-08-05en_US
dc.descriptionPublisher Copyright: © 2022 Elsevier B.V.. All rights reserved.
dc.description.abstractFault diagnosis is a key task for developing safer control systems, especially in chemical plants. Nonetheless, acquiring good labeled fault data involves sampling from dangerous system conditions. A possible workaround to this limitation is to use simulation data for training data-driven fault diagnosis systems. However, due to modelling errors or unknown factors, simulation data may differ in distribution from real-world data. This setting is known as cross-domain fault diagnosis (CDFD). We use optimal transport for: (i) exploring how modelling errors relate to the distance between simulation (source) and real-world (target) data distributions, and (ii) matching source and target distributions through the framework of optimal transport for domain adaptation (OTDA), resulting in new training data that follows the target distribution. Comparisons show that OTDA outperforms other CDFD methods.en
dc.description.versionPeer revieweden
dc.format.extent6
dc.format.extent946-951
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationMontesuma, E F, Mulas, M, Corona, F & Mboula, F M N 2022, ' Cross-domain fault diagnosis through optimal transport for a CSTR process ', IFAC-PapersOnLine, vol. 55, no. 7, pp. 946-951 . https://doi.org/10.1016/j.ifacol.2022.07.566en
dc.identifier.doi10.1016/j.ifacol.2022.07.566en_US
dc.identifier.issn2405-8963
dc.identifier.otherPURE UUID: 9942f4fa-5d55-4c2f-916a-f2bb2d461e71en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/9942f4fa-5d55-4c2f-916a-f2bb2d461e71en_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85137010984&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/88212310/CHEM_Fernandes_Montesuma_et_al_Cross_domain_fault_2022_IFAC_Papers_Online.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/116871
dc.identifier.urnURN:NBN:fi:aalto-202209215669
dc.language.isoenen
dc.publisherElsevier Science Publishers
dc.relation.ispartofseriesIFAC-PapersOnLineen
dc.relation.ispartofseriesVolume 55, issue 7en
dc.rightsopenAccessen
dc.subject.keywordFault Diagnosisen_US
dc.subject.keywordOptimal Transporten_US
dc.subject.keywordTransfer Learningen_US
dc.titleCross-domain fault diagnosis through optimal transport for a CSTR processen
dc.typeA4 Artikkeli konferenssijulkaisussafi
dc.type.versionpublishedVersion

Files