Adaptive Dendritic Cell-Deep Learning Approach for Industrial Prognosis under Changing Conditions
No Thumbnail Available
Identifiers
Publication date
2021-11
Advisors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Export
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.
Description
Publisher Copyright: © 2005-2012 IEEE.
Keywords
Adaptive learning , Deep neural network (DNN) , Dendritic cell algorithm (DCA) , Imbalanced data , Industrial prognosis , Kernel density estimation (KDE) , Control and Systems Engineering , Information Systems , Computer Science Applications , Electrical and Electronic Engineering , SDG 9 - Industry, Innovation, and Infrastructure
Type
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