A methodology for direct parameter identification for experimental results using machine learning — Real world application to the highly non-linear deformation behavior of FRP

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Abstract

In this work, we demonstrate how Machine Learning (ML) techniques can be employed to externalize the knowledge and time intensive process of material parameter identification. This is done on the example of a recent data driven material model for the non-linear shear behavior of glass fiber reinforced polypropylene (GF/PP) (Gerritzen, 2022). A convolutional neural network (CNN) based model architecture is trained to predict material modeling parameters based on the input of stress–strain-curves. The optimal model architecture and training setup are determined by hyperparameter optimization (HPO). Solely virtual data, generated using the target material model, is used throughout the training and HPO. The final CNN is capable of calculating model parameter combinations from experimental stress–strain-curves which lead to excellent agreement between experimental and associated model curve.

Details

OriginalspracheEnglisch
Aufsatznummer113274
Seitenumfang10
FachzeitschriftComputational Materials Science
Jahrgang244
Frühes Online-Datum6 Aug. 2024
PublikationsstatusVeröffentlicht - Sept. 2024
Peer-Review-StatusJa

Externe IDs

ORCID /0000-0002-0169-8602/work/165453561
ORCID /0000-0003-1370-064X/work/165453757
ORCID /0000-0003-2653-7546/work/165454122
WOS 001290603700001

Schlagworte

Schlagwörter

  • Constitutive modeling, Fiber reinforced plastics, Machine learning, Neural networks, Parameter identification