RT Journal Article
T1 Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions
A1 Diez-Olivan, Alberto
A1 Ortego, Patxi
A1 Ser, Javier Del
A1 Landa-Torres, Itziar
A1 Galar, Diego
A1 Camacho, David
A1 Sierra, Basilio
AB 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.
SN 1551-3203
YR 2021
FD 2021-11
LK https://hdl.handle.net/11556/3525
UL https://hdl.handle.net/11556/3525
LA eng
NO 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
NO Publisher Copyright: © 2005-2012 IEEE.
NO 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)
DS TECNALIA Publications
RD 1 ago 2024