A recurrent Fourier neural operator can learn memory- and microstructure-dependent homogenized constitutive laws, with a universal approximation theorem for 1D Kelvin-Voigt viscoelasticity and demonstrations on viscoelastic and elasto-viscoplastic materials.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Memory and Material Dependent Constitutive Laws
A recurrent Fourier neural operator can learn memory- and microstructure-dependent homogenized constitutive laws, with a universal approximation theorem for 1D Kelvin-Voigt viscoelasticity and demonstrations on viscoelastic and elasto-viscoplastic materials.