Saved in:
Bibliographic Details
Main Authors: Geuken, Gian-Luca, Kurzeja, Patrick, Wiedemann, David, Mosler, Jörn
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.08534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917506738814976
author Geuken, Gian-Luca
Kurzeja, Patrick
Wiedemann, David
Mosler, Jörn
author_facet Geuken, Gian-Luca
Kurzeja, Patrick
Wiedemann, David
Mosler, Jörn
contents This paper presents a novel framework of neural networks for isotropic hyperelasticity that enforces necessary physical and mathematical constraints while simultaneously satisfying the universal approximation theorem. The two key ingredients are an input convex network architecture and a formulation in the elementary polynomials of the signed singular values of the deformation gradient. In line with previously published networks, it can rigorously capture frame-indifference and polyconvexity - as well as further constraints like balance of angular momentum and growth conditions. However and in contrast to previous networks, a universal approximation theorem for the proposed approach is proven. To be more explicit, the proposed network can approximate any frame-indifferent, isotropic polyconvex energy (provided the network is large enough). This is possible by working with a sufficient and necessary criterion for frame-indifferent, isotropic polyconvex functions. Comparative studies with existing approaches identify the advantages of the proposed method, particularly in approximating non-polyconvex energies as well as computing polyconvex hulls.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
Geuken, Gian-Luca
Kurzeja, Patrick
Wiedemann, David
Mosler, Jörn
Computational Engineering, Finance, and Science
Artificial Intelligence
74B20, 68T07
J.2; I.2.1
This paper presents a novel framework of neural networks for isotropic hyperelasticity that enforces necessary physical and mathematical constraints while simultaneously satisfying the universal approximation theorem. The two key ingredients are an input convex network architecture and a formulation in the elementary polynomials of the signed singular values of the deformation gradient. In line with previously published networks, it can rigorously capture frame-indifference and polyconvexity - as well as further constraints like balance of angular momentum and growth conditions. However and in contrast to previous networks, a universal approximation theorem for the proposed approach is proven. To be more explicit, the proposed network can approximate any frame-indifferent, isotropic polyconvex energy (provided the network is large enough). This is possible by working with a sufficient and necessary criterion for frame-indifferent, isotropic polyconvex functions. Comparative studies with existing approaches identify the advantages of the proposed method, particularly in approximating non-polyconvex energies as well as computing polyconvex hulls.
title Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
topic Computational Engineering, Finance, and Science
Artificial Intelligence
74B20, 68T07
J.2; I.2.1
url https://arxiv.org/abs/2502.08534