Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning

DOI10.1016/j.jcp.2020.110010OpenAlexW3108491918MaRDI QIDQ2120033

Kevin Linka, Kian P. Abdolazizi, Roland C. Aydin, Markus Hillgärtner, Mikhail Itskov, Christian J. Cyron

Publication date: 31 March 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcp.2020.110010

zbMATH Keywords

hyperelasticitydeep learningconstitutive modelingdata-driven

Mathematics Subject Classification ID

Numerical and other methods in solid mechanics (74Sxx) Elastic materials (74Bxx) Homogenization, determination of effective properties in solid mechanics (74Qxx)

Related Items (30)

Image inversion and uncertainty quantification for constitutive laws of pattern formation ⋮ On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling ⋮ CANN ⋮ Accelerating the distance-minimizing method for data-driven elasticity with adaptive hyperparameters ⋮ Nonlinear multiscale simulation of elastic beam lattices with anisotropic homogenized constitutive models based on artificial neural networks ⋮ Learning Invariant Representation of Multiscale Hyperelastic Constitutive Law from Sparse Experimental Data ⋮ A micromechanics‐based recurrent neural networks model for path‐dependent cyclic deformation of short fiber composites ⋮ Distance minimizing based <scp>data‐driven</scp> computational method for the finite deformation of hyperelastic materials ⋮ Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues ⋮ Enhanced physics‐informed neural networks for hyperelasticity ⋮ A new family of constitutive artificial neural networks towards automated model discovery ⋮ A comparative study on different neural network architectures to model inelasticity ⋮ Automatic generation of interpretable hyperelastic material models by symbolic regression ⋮ Automated model discovery for skin: discovering the best model, data, and experiment ⋮ Discovering the mechanics of artificial and real meat ⋮ \(\mathrm{FE^{ANN}}\): an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining ⋮ Incompressible rubber thermoelasticity: a neural network approach ⋮ Adaptive goal-oriented data sampling in data-driven computational mechanics ⋮ A reduced order model for geometrically parameterized two-scale simulations of elasto-plastic microstructures under large deformations ⋮ On automated model discovery and a universal material subroutine for hyperelastic materials ⋮ Gradient enhanced Gaussian process regression for constitutive modelling in finite strain hyperelasticity ⋮ Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria ⋮ Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios ⋮ Viscoelastic constitutive artificial neural networks (vCANNs) -- a framework for data-driven anisotropic nonlinear finite viscoelasticity ⋮ Data-driven nonparametric identification of material behavior based on physics-informed neural network with full-field data ⋮ Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method ⋮ Finite electro-elasticity with physics-augmented neural networks ⋮ A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method ⋮ Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method: extension to geometrical parameterizations ⋮ Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks

Uses Software

• ABAQUS
• TensorFlow
• Keras

Cites Work

• Unnamed Item
• Computational homogenization of porous materials of Green type
• Hyperelastic models for rubber-like materials: consistent tangent operators and suitability for Treloar's data
• Data-driven non-linear elasticity: constitutive manifold construction and problem discretization
• A numerical method for homogenization in nonlinear elasticity
• A manifold learning approach to data-driven computational elasticity and inelasticity
• A class of orthotropic and transversely isotropic hyperelastic constitutive models based on a polyconvex strain energy function
• Computational homogenization analysis in finite plasticity. Simulation of texture development in polycrystalline materials
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• Model-free data-driven inelasticity
• A new class of plastic flow evolution equations for anisotropic multiplicative elastoplasticity based on the notion of a corrector elastic strain rate
• Data-based derivation of material response
• A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites
• Model-free data-driven methods in mechanics: material data identification and solvers
• Data-driven computational mechanics
• Reduced basis hybrid computational homogenization based on a mixed incremental formulation
• Computational homogenization of nonlinear elastic materials using neural networks
• Numerical implementation of a neural network based material model in finite element analysis
• Tensor algebra and tensor analysis for engineers. With applications to continuum mechanics

This page was built for publication: Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning