Smart constitutive laws: inelastic homogenization through machine learning

DOI10.1016/J.CMA.2020.113482zbMath1506.74336OpenAlexW3093832692MaRDI QIDQ2020776

Hernan J. Logarzo, Julian J. Rimoli, German Capuano

Publication date: 26 April 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2020.113482

zbMATH Keywords

homogenizationmachine learningmultiscale modelingconstitutive modelinginelasticity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Effective constitutive equations in solid mechanics (74Q15)

Related Items (29)

On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling ⋮ Finite element coupled positive definite deep neural networks mechanics system for constitutive modeling of composites ⋮ Accelerated offline setup of homogenized microscopic model for multi‐scale analyses using neural network with knowledge transfer ⋮ A micromechanics‐based recurrent neural networks model for path‐dependent cyclic deformation of short fiber composites ⋮ Integrated finite element neural network (I-FENN) for non-local continuum damage mechanics ⋮ Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials ⋮ Synergistic integration of deep neural networks and finite element method with applications of nonlinear large deformation biomechanics ⋮ Intelligent stiffness computation for plate and beam structures by neural network enhanced finite element analysis ⋮ Surrogate modeling for the homogenization of elastoplastic composites based on RBF interpolation ⋮ A monolithic hyper ROM \(\mathrm{FE}^2\) method with clustered training at finite deformations ⋮ Pre-trained transformer model as a surrogate in multiscale computational homogenization framework for elastoplastic composite materials subjected to generic loading paths ⋮ Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios ⋮ Incremental neural controlled differential equations for modeling of path-dependent material behavior ⋮ Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions ⋮ Transfer learning of recurrent neural network‐based plasticity models ⋮ Neural integration for constitutive equations using small data ⋮ Reducing internal variables and improving efficiency in data-driven modelling of anisotropic damage from RVE simulations ⋮ Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate ⋮ Model-data-driven constitutive responses: application to a multiscale computational framework ⋮ Micromechanics-based material networks revisited from the interaction viewpoint; robust and efficient implementation for multi-phase composites ⋮ Cell division in deep material networks applied to multiscale strain localization modeling ⋮ Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method ⋮ Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks ⋮ Interaction-based material network: a general framework for (porous) microstructured materials ⋮ Recurrent neural networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step ⋮ Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response ⋮ Data-driven approach for dynamic homogenization using meta learning ⋮ A robust unsupervised neural network framework for geometrically nonlinear analysis of inelastic truss structures ⋮ A data-driven approach for modeling tension-compression asymmetric material behavior: numerical simulation and experiment

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Cavitation in elastomeric solids. I: A defect-growth theory
• Numerically explicit potentials for the homogenization of nonlinear elastic heterogeneous materials
• Inelastic deformation and energy dissipation in ceramics: a mechanism-based constitutive model
• A variational approach to the theory of the elastic behaviour of multiphase materials
• New variational principles in plasticity and their application to composite materials
• The variational multiscale method -- a paradigm for computational mechanics
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• The nonlinear elastic response of suspensions of rigid inclusions in rubber. I: An exact result for dilute suspensions
• Smart finite elements: a novel machine learning application
• Exploring the 3D architectures of deep material network in data-driven multiscale mechanics
• Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
• A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
• A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites
• A geometric multiscale finite element method for the dynamic analysis of heterogeneous solids
• Elastic properties of reinforced solids: Some theoretical principles
• Hierarchically parallel coupled finite strain multiscale solver for modeling heterogeneous layers
• Computational homogenization of nonlinear elastic materials using neural networks
• A Theorem on the Conductivity of a Composite Medium

This page was built for publication: Smart constitutive laws: inelastic homogenization through machine learning