A single long short-term memory network for enhancing the prediction of path-dependent plasticity with material heterogeneity and anisotropy
EM Haghighi, SH Na - arxiv preprint arxiv:2204.01466, 2022 - arxiv.org
This study presents the applicability of conventional deep recurrent neural networks (RNN)
to predict path-dependent plasticity associated with material heterogeneity and anisotropy …
to predict path-dependent plasticity associated with material heterogeneity and anisotropy …
Operator learning for homogenizing hyperelastic materials, without PDE data
In this work, we address operator learning for stochastic homogenization in nonlinear
elasticity. A Fourier neural operator is employed to learn the map between the input field …
elasticity. A Fourier neural operator is employed to learn the map between the input field …
[HTML][HTML] Evaluation of the Relevance of Global and By-Step Homogenization for Composites and Heterogeneous Materials at Several Scales
N Kenisse, M Masmoudi, T Kanit, O Ounissi… - Applied Sciences, 2024 - mdpi.com
Two hypotheses divide experts on determining the effective properties of composite
materials using multi–scale homogenization methods. The first hypothesis states that multi …
materials using multi–scale homogenization methods. The first hypothesis states that multi …
Revisiting Preparation of Phase Space for Learning Path-Dependent Behavior via Deep Neural Networks
This technical note investigates the preparation of a phase space of two simple constitutive
laws, von Mises (J2) and Drucker-Prager (DP) models, for deep neural networks with special …
laws, von Mises (J2) and Drucker-Prager (DP) models, for deep neural networks with special …