Researchers embed consistent recurrent neural networks in FEM simulations for damage prediction
A new arXiv paper presents embedding consistent recurrent neural networks into finite element simulations to predict path-dependent damage, targeting sheet-metal localisation physics with trained surrogates inside FEM solvers.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-09 05:00 · arXiv cs.LG
Embedding Consistent Recurrent Neural Networks in Finite Element Simulations for Path-Dependent Damage Prediction