Online data assimilation of a hybrid flow stress model by particle filtering
Metadata only
Author
Date
2021Type
- Journal Article
ETH Bibliography
yes
Altmetrics
Abstract
Models for the evolution of hidden microstructural states are needed for fast prediction and closed-loop control of workpiece properties. Machine learning allows to obtain models by learning from experimental data, avoiding the limitations of explicitly defined physics-based models. However, the identification of the parameters of deep network structures, reliable extrapolation and fast online assimilation to new measurements are open problems. At the example of titanium forging, a new approach is investigated that combines a hybrid physics-informed microstructure and flow stress model that draws upon a long short-term memory network with a particle filter for online data assimilation to new measurements. © 2021 CIRP. Published by Elsevier Ltd. Show more
Publication status
publishedExternal links
Journal / series
CIRP Annals - Manufacturing TechnologyVolume
Pages / Article No.
Publisher
ElsevierSubject
Metal forming; Process control; Machine learningOrganisational unit
09706 - Bambach, Markus / Bambach, Markus
More
Show all metadata
ETH Bibliography
yes
Altmetrics