Material Parameters Identification of Thin Fiber-Based Materials Using the Method of Machine Learning Exploiting Numerically Generated Simulation Data

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

  • Cedric Wilfried Sanjon - , Fraunhofer-Institut für Verfahrenstechnik und Verpackung (Autor:in)
  • Yuchen Leng - , Technische Universität Darmstadt (Autor:in)
  • Marek Hauptmann - , Fraunhofer-Institut für Verfahrenstechnik und Verpackung (Autor:in)
  • Jens Peter Majschak - , Fraunhofer-Institut für Verfahrenstechnik und Verpackung (Autor:in)
  • Peter Groche - , Technische Universität Darmstadt (Autor:in)

Abstract

The determination and validation of material parameters required for finite element simulation of the forming processes of fiber-based materials such as paperboard can be accomplished by strain-based loading of a specimen in combination with a simulation-based reverse engineering approach. Due to the complexity of the material itself, such as anisotropy, the development of such approaches can be very time-consuming and requires programming skills as well as expertise in FEM analysis and optimization. Machine learning methods offer a practical alternative to optimization, parameterization, and reverse engineering approaches, assuming that the data is fully known, generalized, and learned by the machine learning model. More specifically, a machine learning model can compute the material parameters required for a finite element simulation directly from the experimental measurements, if the hypothetical mapping function in this case is learned from the numerical study between material parameters and deformation behavior. In this paper, such data generated by numerical studies are used to train the machine learning model and, based on this, to determine elastic (e.g., Young’s modulus), plastic, and Hill’s parameters.

Details

OriginalspracheEnglisch
TitelNumerical Methods in Industrial Forming Processes
Redakteure/-innenJan Kusiak, Łukasz Rauch, Krzysztof Regulski
Herausgeber (Verlag)Springer Science and Business Media B.V.
Seiten209-223
Seitenumfang15
ISBN (elektronisch)978-3-031-58006-2
ISBN (Print)978-3-031-58005-5, 978-3-031-58008-6
PublikationsstatusVeröffentlicht - 2024
Peer-Review-StatusJa
Extern publiziertJa

Publikationsreihe

ReiheLecture Notes in Mechanical Engineering
ISSN2195-4356

Konferenz

Titel14th International Conference on Numerical Methods in Industrial Forming Processes
KurztitelNumiform 2023
Veranstaltungsnummer14
Dauer25 - 29 Juni 2023
Webseite
OrtAGH University of Krakow & Online
StadtKraków
LandPolen

Schlagworte

Schlagwörter

  • Finite element analysis, Machine learning, Material identification, Material parameters, Materials analysis