Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions
dc.contributor.author | Diez-Olivan, Alberto | |
dc.contributor.author | Ortego, Patxi | |
dc.contributor.author | Ser, Javier Del | |
dc.contributor.author | Landa-Torres, Itziar | |
dc.contributor.author | Galar, Diego | |
dc.contributor.author | Camacho, David | |
dc.contributor.author | Sierra, Basilio | |
dc.contributor.institution | Tecnalia Research & Innovation | |
dc.contributor.institution | IA | |
dc.date.accessioned | 2024-07-24T12:05:08Z | |
dc.date.available | 2024-07-24T12:05:08Z | |
dc.date.issued | 2021-11 | |
dc.description | Publisher Copyright: © 2005-2012 IEEE. | |
dc.description.abstract | Industrial 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.sponsorship | This 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.status | Peer reviewed | |
dc.format.extent | 11 | |
dc.identifier.citation | Diez-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.doi | 10.1109/TII.2021.3058350 | |
dc.identifier.issn | 1551-3203 | |
dc.identifier.uri | https://hdl.handle.net/11556/3525 | |
dc.identifier.url | http://www.scopus.com/inward/record.url?scp=85101477667&partnerID=8YFLogxK | |
dc.language.iso | eng | |
dc.relation.ispartof | IEEE Transactions on Industrial Informatics | |
dc.relation.projectID | Eusko Jaurlaritza, IT1294-19-KK-2020/00 049 | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.subject.keywords | Adaptive learning | |
dc.subject.keywords | Deep neural network (DNN) | |
dc.subject.keywords | Dendritic cell algorithm (DCA) | |
dc.subject.keywords | Imbalanced data | |
dc.subject.keywords | Industrial prognosis | |
dc.subject.keywords | Kernel density estimation (KDE) | |
dc.subject.keywords | Control and Systems Engineering | |
dc.subject.keywords | Information Systems | |
dc.subject.keywords | Computer Science Applications | |
dc.subject.keywords | Electrical and Electronic Engineering | |
dc.subject.keywords | SDG 9 - Industry, Innovation, and Infrastructure | |
dc.title | Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions | en |
dc.type | journal article |