Parametrised polyconvex hyperelasticity with physics-augmented neural networks
Preprint
Abstract
In the present work, neural networks are applied to formulate parametrised hyperelastic constitutive models. The models fulfill all common mechanical conditions of hyperelasticity by construction. In particular, partially input-convex neural network (pICNN) architectures are applied based on feed-forward neural networks. Receiving two different sets of input arguments, pICNNs are convex in one of them, while for the other, they represent arbitrary relationships which are not necessarily convex. In this way, the model can fulfill convexity conditions stemming from mechanical considerations without being too restrictive on the functional relationship in additional parameters, which may not necessarily be convex. Two different models are introduced, where one can represent arbitrary functional relationships in the additional parameters, while the other is monotonic in the additional parameters. As a first proof of concept, the model is calibrated to data generated with two differently parametrised analytical potentials, whereby three different pICNN architectures are investigated. In all cases, the proposed model shows excellent performance.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Multiscale modeling of functionally graded shell lattice metamaterials for additive manufacturingEngineering with Computers, 2023
- Benchmarking physics-informed frameworks for data-driven hyperelasticityComputational Mechanics, 2023
- FE${}^\textrm{ANN}$: an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data miningComputational Mechanics, 2023
- What Machine Learning Can Do for Computational Solid Mechanics2022
- Material modeling for parametric, anisotropic finite strain hyperelasticity based on machine learning with application in optimization of metamaterialsInternational Journal for Numerical Methods in Engineering, 2021
- Nonlinear multiscale simulation of elastic beam lattices with anisotropic homogenized constitutive models based on artificial neural networksComputational Mechanics, 2021
- On the Convexity of Nonlinear Elastic Energies in the Right Cauchy-Green TensorJournal of Elasticity, 2016
- Geometry of Logarithmic Strain Measures in Solid MechanicsArchive for Rational Mechanics and Analysis, 2016
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Convexity conditions and existence theorems in nonlinear elasticityArchive for Rational Mechanics and Analysis, 1976