A coupled LSTM-GNN model reconstructs local elasto-plastic stress fields from macroscopic loading paths on a plate-with-hole microstructure, achieving 1000x speedup and mesh transferability with 1.9% error.
Bessa, and Wing Kam Liu
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CE 2years
2026 2roles
background 1polarities
background 1representative citing papers
EMSL groups material points into clusters, samples a reference strain per cluster once per increment, and computes a linearised stress estimate from the reference tangent and POD strain modes, yielding an affine reduced system that requires no iterations online and Pareto-dominates prior strain-cubc
citing papers explorer
-
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
A coupled LSTM-GNN model reconstructs local elasto-plastic stress fields from macroscopic loading paths on a plate-with-hole microstructure, achieving 1000x speedup and mesh transferability with 1.9% error.