A strategy to train machine learning material models for finite element simulations on data acquirable from physical experiments

DOI10.1016/j.cma.2023.115894OpenAlexW4320475464MaRDI QIDQ2686894

David Koch, Daniel Sommer, Celalettin Karadogan, Martin Barteczko, Joachim Sprave, Pauline Böhringer, Markus Stoll, Thomas Haase, Peter Middendorf, Mathias Liewald

Publication date: 1 March 2023

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2023.115894

zbMATH Keywords

finite element analysismachine learningoptimization strategiesmaterials modelling

Mathematics Subject Classification ID

Mechanics of deformable solids (74-XX) Biology and other natural sciences (92-XX)

Uses Software

• SciPy
• Python
• TensorFlow
• Adam

Cites Work

• Identification of plastic constitutive parameters at large deformations from three dimensional displacement fields
• Characterisation of materials subjected to large strains by inverse modelling based on in-plane displacement fields
• A machine learning based plasticity model using proper orthogonal decomposition
• Unsupervised discovery of interpretable hyperelastic constitutive laws
• Computational mechanics enhanced by deep learning
• Model-free data-driven methods in mechanics: material data identification and solvers
• Data-driven computational mechanics
• Application of digital image correlation to the study of planar anisotropy of sheet metals at large strains
• Numerical issues in the virtual fields method
• Learning representations by back-propagating errors
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A strategy to train machine learning material models for finite element simulations on data acquirable from physical experiments