Finite element model updating is among the most general approaches to discover constitutive models from structural experiments: since the displacement field is computed rather than measured, it accommodates arbitrary geometries, boundary conditions, and sparse or noisy data. However, every loss evaluation requires a no...
H. Holthusen, Matthias Knipper, Kevin Linka· 0 citations
We propose a non-intrusive, Autoencoder-based framework for reduced-order modeling in continuum mechanics. Our method integrates three stages: (i) an unsupervised Autoencoder compresses high-dimensional finite element solutions into a compact latent space, (ii) a supervised regression network maps problem parameters...
Jannick Kehls, Ellen Kuhl, T. Brepols et al.· Computational Mechanics· 0 citations
Hyperreduced nonlinear solid-mechanics components can be generated offline and reused as transferable building blocks across different assemblies, boundary conditions, meshes, material parameters, and constitutive models. We use proper orthogonal decomposition (POD) and energy conserving sampling and weighting (ECSW) o...
S. Ritzert, Jannick Kehls, Erik Faust et al.· 0 citations
The classic experimental data of Treloar is used to benchmark popular frameworks for hyperelasticity: (Generalized-Invariant) Constitutive Artificial Neural Networks, Physics-Augmented Neural Networks, (Adaptive) Material Fingerprinting, and Efficient Unsupervised Constitutive Law Identification&Discovery and highlight...
H. Holthusen, Moritz Flaschel, Denisa Martonová et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
