Modeling isotropic polyconvex hyperelasticity by neural networks -- sufficient and necessary criteria for compressible and incompressible materials

TL;DR

This paper develops neural network models for isotropic polyconvex hyperelastic materials, providing criteria for their expressiveness and demonstrating their ability to approximate classical models and experimental data.

Contribution

It introduces CSSV-NNs and inc-CSSV-NNs that are universal approximators for frame-indifferent, isotropic polyconvex energies, expanding the expressiveness beyond existing methods.

Findings

Neural network models can accurately approximate classical hyperelastic models.

Ball's criterion for polyconvexity is sufficient but not necessary, as shown by explicit counterexamples.

Models demonstrate good performance on experimental data and classical benchmarks.

Abstract

This work investigates different sufficient and necessary criteria for hyperelastic, isotropic polyconvex material models, focusing on neural network implementations for compressible and incompressible materials. Furthermore, the expressiveness, accuracy, simplicity as well as the efficiency of those models is analyzed. This also enables an assessment of the practical applicability of the models. Convex Signed Singular Value Neural Networks (CSSV-NNs) are applied to compressible materials and tailored to incompressibility (inc-CSSV-NNs), resulting in a universal approximation for frame-indifferent, isotropic polyconvex energies for the compressible as well as incompressible case. While other existing approaches also guarantee frame-indifference, isotropy and polyconvexity, they impose too restrictive constraints and thus limit the expressiveness of the model. This is further substantiated by numerical examples of several, well-established classical models (Neo-Hooke, Mooney-Rivlin, Gent and Arruda-Boyce) and Treloar's experimental data. Moreover, the numerical examples include an explicitly constructed energy function that cannot be approximated by neural networks constrained by Ball's criterion for polyconvexity. This substantiates that Ball's criterion, though sufficient, is not necessary for polyconvexity.