An enriched deep material network with cohesive layers, trained only on linear-elastic data, predicts nonlinear interface failure in composites with large speedups over direct numerical simulation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis
An enriched deep material network with cohesive layers, trained only on linear-elastic data, predicts nonlinear interface failure in composites with large speedups over direct numerical simulation.