Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies

Abstract

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.

References in corpus (11)

• Data-driven computational mechanics
• A new family of Constitutive Artificial Neural Networks towards automated model discovery
• Physics informed neural networks for continuum micromechanics
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Neural networks meet hyperelasticity: A guide to enforcing physics
• Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• A hybrid approach to simulate the homogenized irreversible elastic-plastic deformations and damage of foams by neural networks
• Consistent machine learning for topology optimization with microstructure-dependent neural network material models
• Recovering Mullins damage hyperelastic behaviour with physics augmented neural networks
• A computational framework for nanotrusses: input convex neural networks approach
• Characterization of polyconvex isotropic functions

Cited by in corpus (4)

• A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
• In search of constitutive conditions in isotropic hyperelasticity: polyconvexity versus true-stress-true-strain monotonicity
• A physics-augmented neural network framework for finite strain incompressible viscoelasticity
• Hetero-EUCLID: Interpretable model discovery for heterogeneous hyperelastic materials using stress-unsupervised learning