Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis Under Changing Conditions
TECNALIA, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastién, Spain; University of the Basque Country (UPV/EHU), 20018 Donostia-San Sebastián, Spain.
TECNALIA, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastién, Spain; University of the Basque Country (UPV/EHU), 20018 Donostia-San Sebastián, Spain.
TECNALIA, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastién, Spain; University of the Basque Country (UPV/EHU), 20018 Donostia-San Sebastián, Spain.
Petronor Innovación S.L., 48550 Muskiz, Spain.
Vise andre og tillknytning
2021 (engelsk)Inngår i: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 17, nr 11, s. 7760-7770Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

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.

sted, utgiver, år, opplag, sider
IEEE, 2021. Vol. 17, nr 11, s. 7760-7770
Emneord [en]
Adaptive learning, deep neural network (DNN), dendritic cell algorithm (DCA), imbalanced data, industrial prognosis, kernel density estimation (KDE)
HSV kategori
Forskningsprogram
Drift och underhållsteknik
Identifikatorer
URN: urn:nbn:se:ltu:diva-86874DOI: 10.1109/TII.2021.3058350ISI: 000679533900057Scopus ID: 2-s2.0-85101477667OAI: oai:DiVA.org:ltu-86874DiVA, id: diva2:1588442
Merknad

Validerad;2021;Nivå 2;2021-09-01 (alebob);

Forskningsfinansiär: Basque Government (KK-2020/00 049); MATHMODE (IT1294-19)

Tilgjengelig fra: 2021-08-27 Laget: 2021-08-27 Sist oppdatert: 2021-12-21bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Galar, Diego

Søk i DiVA

Av forfatter/redaktør
Galar, Diego
Av organisasjonen
I samme tidsskrift
IEEE Transactions on Industrial Informatics

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 69 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf