The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 46 of 3254
Back to Result List

Continual learning for neural regression networks to cope with concept drift in industrial processes using convex optimisation

  • Process models in industrial applications, e.g. predictive maintenance or automation, are subject to both divergence from the underlying system due to their time-variant nature and to high complexity resulting from a wide operational range being covered. Hence, regression models require high accuracy for the present system state and at the same time need to be valid across the whole system operating space. While accuracy for the current system state can be gained by updating the model on the current data, the overall validity must often be retrieved from historical or design data. We propose a method to find an appropriate compromise for these two demands. A pre-trained artificial neural network (ANN) is continually updated on the current sensor data stream using convex optimisation. Thus, a unique and optimal solution is generated in each update step, while robust regression accuracy on the domain that is not covered by the arriving data subset is maintained. This is achieved byProcess models in industrial applications, e.g. predictive maintenance or automation, are subject to both divergence from the underlying system due to their time-variant nature and to high complexity resulting from a wide operational range being covered. Hence, regression models require high accuracy for the present system state and at the same time need to be valid across the whole system operating space. While accuracy for the current system state can be gained by updating the model on the current data, the overall validity must often be retrieved from historical or design data. We propose a method to find an appropriate compromise for these two demands. A pre-trained artificial neural network (ANN) is continually updated on the current sensor data stream using convex optimisation. Thus, a unique and optimal solution is generated in each update step, while robust regression accuracy on the domain that is not covered by the arriving data subset is maintained. This is achieved by introducing a data management system to provide some historical data, constraining the optimisation problem and manipulating the architecture of the ANN. Models updated with this method show reasonable stability but display plastic behaviour at the current operating point.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Wolfgang Grote-Ramm, David Lanuschny, Finn Lorenzen, Marcel Oliveira Brito, Felix Schönig
Fachbereich/Einrichtung:Hochschule Düsseldorf / Fachbereich - Maschinenbau und Verfahrenstechnik
Document Type:Article
Year of Completion:2023
Language of Publication:English
Publisher:Elsevier
Place of publication:New York
Parent Title (English):Engineering Applications of Artificial Intelligence
Volume:120
Article Number:105927
Page Number:10
DOI:https://doi.org/10.1016/j.engappai.2023.105927
ISSN:1873-6769
Tag:Catastrophic forgetting; Concept drift; Continual learning; Convex optimization
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 62 Ingenieurwissenschaften / 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Licence (German):keine Lizenz - nur Metadaten
Release Date:2024/01/24
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.