A monotonic ICNN architecture with domain reduction to the positive octant approximates polyconvex envelopes of isotropic functions more efficiently than existing necessary-and-sufficient methods, demonstrated on Saint Venant-Kirchhoff energy.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
EquiNO with Q-DEIM creates reduced-order physics-informed surrogates for 3D hyperelastic RVEs that enforce equilibrium and periodicity by construction, achieve 10^3 speedups, and accurately interpolate and extrapolate stresses from few snapshots.
Numerical simulations show equilibrium configurations of flat hyperelastic bodies on curved surfaces where elastic restoring forces cancel gravitational pull, producing a levitation-like balance.
citing papers explorer
-
Compression of Polyconvex Envelopes of Isotropic Functions via Monotonic Input Convex Neural Networks
A monotonic ICNN architecture with domain reduction to the positive octant approximates polyconvex envelopes of isotropic functions more efficiently than existing necessary-and-sufficient methods, demonstrated on Saint Venant-Kirchhoff energy.
-
Physics-Informed Reduced-Order Operator Learning for Hyperelasticity in Continuum Micromechanics
EquiNO with Q-DEIM creates reduced-order physics-informed surrogates for 3D hyperelastic RVEs that enforce equilibrium and periodicity by construction, achieve 10^3 speedups, and accurately interpolate and extrapolate stresses from few snapshots.
-
Curvature-Induced Force Fields in Hyperelasticity
Numerical simulations show equilibrium configurations of flat hyperelastic bodies on curved surfaces where elastic restoring forces cancel gravitational pull, producing a levitation-like balance.