FE-LSTM: a hybrid approach to accelerate multiscale simulations of architectured materials using recurrent neural networks and finite element analysis

DOI10.1016/j.cma.2024.117192MaRDI QIDQ6588352

Yves Chemisky, Unnamed Author, Etienne Pruliere

Publication date: 15 August 2024

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

zbMATH Keywords

homogenization artificial intelligence finite element analysis multi-scale modeling architectured materials recurrent neural network (RNN)

Mathematics Subject Classification ID

Finite element methods applied to problems in solid mechanics (74S05) Mathematical modeling or simulation for problems pertaining to mechanics of deformable solids (74-10)

This page was built for publication: FE-LSTM: a hybrid approach to accelerate multiscale simulations of architectured materials using recurrent neural networks and finite element analysis