Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions

Simple item page
dc.contributor.authorDiez-Olivan, Alberto
dc.contributor.authorOrtego, Patxi
dc.contributor.authorSer, Javier Del
dc.contributor.authorLanda-Torres, Itziar
dc.contributor.authorGalar, Diego
dc.contributor.authorCamacho, David
dc.contributor.authorSierra, Basilio
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionIA
dc.date.accessioned2024-07-24T12:05:08Z
dc.date.available2024-07-24T12:05:08Z
dc.date.issued2021-11
dc.descriptionPublisher Copyright: © 2005-2012 IEEE.
dc.description.abstractIndustrial prognosis refers to the prediction of failures of an industrial asset based on data collected by Internet of Things sensors. Prognostic models can experience the undesired effects of concept drift, namely, the presence of nonstationary phenomena that affects the data collected over time. Consequently, fault patterns learned from data become obsolete. To overcome this issue, contextual and operational changes must be detected and managed, triggering rapid model adaptation mechanisms. This article presents an adaptive learning approach based on a dendritic cell algorithm for drift detection and a deep neural network model that dynamically adapts to new operational conditions. A kernel density estimator with drift-based bandwidth is used to generate synthetic data for a faster adaptation, focusing on fine-tuning the lowest neural layers. Experimental results over a real-world industrial problem shed light on the outperforming behavior of the proposed approach when compared to other drift detectors and classification models.en
dc.description.sponsorshipThis work was supported by Basque Government through EMAITEK and ELKARTEK (ref. KK-2020/00 049) funding Grants and the consolidated research group MATHMODE (IT1294-19)
dc.description.statusPeer reviewed
dc.format.extent11
dc.identifier.citationDiez-Olivan , A , Ortego , P , Ser , J D , Landa-Torres , I , Galar , D , Camacho , D & Sierra , B 2021 , ' Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions ' , IEEE Transactions on Industrial Informatics , vol. 17 , no. 11 , 9352529 , pp. 7760-7770 . https://doi.org/10.1109/TII.2021.3058350
dc.identifier.doi10.1109/TII.2021.3058350
dc.identifier.issn1551-3203
dc.identifier.urihttps://hdl.handle.net/11556/3525
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85101477667&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofIEEE Transactions on Industrial Informatics
dc.relation.projectIDEusko Jaurlaritza, IT1294-19-KK-2020/00 049
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsAdaptive learning
dc.subject.keywordsDeep neural network (DNN)
dc.subject.keywordsDendritic cell algorithm (DCA)
dc.subject.keywordsImbalanced data
dc.subject.keywordsIndustrial prognosis
dc.subject.keywordsKernel density estimation (KDE)
dc.subject.keywordsControl and Systems Engineering
dc.subject.keywordsInformation Systems
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsElectrical and Electronic Engineering
dc.subject.keywordsSDG 9 - Industry, Innovation, and Infrastructure
dc.titleAdaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditionsen
dc.typejournal article
Files