Polyconvex anisotropic hyperelasticity with neural networks

by   Dominik Klein, et al.

In the present work, two machine learning based constitutive models for finite deformations are proposed. Using input convex neural networks, the models are hyperelastic, anisotropic and fulfill the polyconvexity condition, which implies ellipticity and thus ensures material stability. The first constitutive model is based on a set of polyconvex, anisotropic and objective invariants. The second approach is formulated in terms of the deformation gradient, its cofactor and determinant, uses group symmetrization to fulfill the material symmetry condition, and data augmentation to fulfill objectivity approximately. The extension of the dataset for the data augmentation approach is based on mechanical considerations and does not require additional experimental or simulation data. The models are calibrated with highly challenging simulation data of cubic lattice metamaterials, including finite deformations and lattice instabilities. A moderate amount of calibration data is used, based on deformations which are commonly applied in experimental investigations. While the invariant-based model shows drawbacks for several deformation modes, the model based on the deformation gradient alone is able to reproduce and predict the effective material behavior very well and exhibits excellent generalization capabilities. Thus, in particular the second model presents a highly flexible constitutive modeling approach, that leads to a mathematically well-posed problem.


Finite electro-elasticity with physics-augmented neural networks

In the present work, a machine learning based constitutive model for ele...

Predicting the Mechanical Properties of Fibrin Using Neural Networks Trained on Discrete Fiber Network Data

Fibrin is a structural protein key for processes such as wound healing a...

Neural networks meet hyperelasticity: A guide to enforcing physics

In the present work, a hyperelastic constitutive model based on neural n...

On the stability of the generalized, finite deformation correspondence model of peridynamics

A class of peridynamic material models known as constitutive corresponde...

Hybrid Numerical Modeling of Ballistic Clay under Low-Speed Impact using Artificial Neural Networks

Roma Plastilina No. 1 clay has been widely used as a conservative bounda...

Parametrised polyconvex hyperelasticity with physics-augmented neural networks

In the present work, neural networks are applied to formulate parametris...

Denture reinforcement via topology optimization

We present a computational design method that optimizes the reinforcemen...

Please sign up or login with your details

Forgot password? Click here to reset