A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites

DOI10.1007/s00466-018-1643-0zbMath1464.74404OpenAlexW2897923334WikidataQ113327187 ScholiaQ113327187MaRDI QIDQ2319390

Xiaoxin Lu, Julien Yvonnet, Dimitris G. Giovanis, Jinbo Bai, Fabrice Detrez, Vissarion Papadopoulos

Publication date: 19 August 2019

Published in: Computational Mechanics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00466-018-1643-0

zbMATH Keywords

multiscale analysisartificial neural networkdata-driven analysiselectric effective conduction

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Effective constitutive equations in solid mechanics (74Q15) Composite and mixture properties (74E30) Electromagnetic effects in solid mechanics (74F15) Numerical and other methods in solid mechanics (74S99)

Related Items (40)

Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning ⋮ A multiscale, data-driven approach to identifying thermo-mechanically coupled laws -- bottom-up with artificial neural networks ⋮ NTFA-enabled goal-oriented adaptive space-time finite elements for micro-heterogeneous elastoplasticity problems ⋮ Accelerating the distance-minimizing method for data-driven elasticity with adaptive hyperparameters ⋮ Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network ⋮ A machine learning based plasticity model using proper orthogonal decomposition ⋮ 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 ⋮ Micromechanics-based surrogate models for the response of composites: a critical comparison between a classical mesoscale constitutive model, hyper-reduction and neural networks ⋮ Recurrent and convolutional neural networks in structural dynamics: a modified attention steered encoder-decoder architecture versus LSTM versus GRU versus TCN topologies to predict the response of shock wave-loaded plates ⋮ Intelligent stiffness computation for plate and beam structures by neural network enhanced finite element analysis ⋮ \(\mathrm{FE^{ANN}}\): an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining ⋮ Estimating permeability of 3D micro-CT images by physics-informed CNNs based on DNS ⋮ A monolithic hyper ROM \(\mathrm{FE}^2\) method with clustered training at finite deformations ⋮ Extended tensor decomposition model reduction methods: training, prediction, and design under uncertainty ⋮ Neural network-based multiscale modeling of finite strain magneto-elasticity with relaxed convexity criteria ⋮ Concurrent multiscale simulations of nonlinear random materials using probabilistic learning ⋮ Review of solution methodologies for structural analysis of composites ⋮ A micromechanical mean‐field homogenization surrogate for the stochastic multiscale analysis of composite materials failure ⋮ Deep learning framework for multiscale finite element analysis based on data-driven mechanics and data augmentation ⋮ On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning ⋮ A mechanics-informed deep learning framework for data-driven nonlinear viscoelasticity ⋮ Data-driven Whitney forms for structure-preserving control volume analysis ⋮ Model-data-driven constitutive responses: application to a multiscale computational framework ⋮ Prediction and identification of physical systems by means of physically-guided neural networks with meaningful internal layers ⋮ Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition ⋮ Bayesian neural networks for uncertainty quantification in data-driven materials modeling ⋮ Smart constitutive laws: inelastic homogenization through machine learning ⋮ Machine learning materials physics: multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures ⋮ Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity ⋮ A kernel method for learning constitutive relation in data-driven computational elasticity ⋮ Neural network constitutive model for crystal structures ⋮ Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter ⋮ Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks ⋮ Data-driven multiscale finite element method: from concurrence to separation ⋮ Application of deep learning neural network to identify collision load conditions based on permanent plastic deformation of shell structures ⋮ Inverse design of shell-based mechanical metamaterial with customized loading curves based on machine learning and genetic algorithm ⋮ Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response ⋮ Efficiency of Micro-Macro Models for Reactive Two-Mineral Systems ⋮ Material Modeling via Thermodynamics-Based Artificial Neural Networks

Cites Work

• Unnamed Item
• Interfacial discontinuity relations for coupled multifield phenomena and their application to the modeling of thin interphases as imperfect interfaces
• Numerically explicit potentials for the homogenization of nonlinear elastic heterogeneous materials
• The reduced model multiscale method (R3M) for the nonlinear homogenization of hyperelastic media at finite strains
• Multi-scale computational homogenization: trends and challenges
• Strong coupling methods in multi-phase and multi-scale modeling of inelastic behavior of heterogeneous structures.
• Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
• \(FE^2\) multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials
• A manifold learning approach to data-driven computational elasticity and inelasticity
• High-performance model reduction techniques in computational multiscale homogenization
• Dynamic data-driven reduced-order models
• Two-stage data-driven homogenization for nonlinear solids using a reduced order model
• Computational homogenization analysis in finite plasticity. Simulation of texture development in polycrystalline materials
• Prediction of the mechanical behavior of nonlinear heterogeneous systems by multi-level finite element modeling
• Self-consistent clustering analysis: an efficient multi-scale scheme for inelastic heterogeneous materials
• Data driven modeling of plastic deformation
• A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality
• Data driven computing with noisy material data sets
• Data-driven computational mechanics
• Multiscale modeling of nonlinear electric conductivity in graphene-reinforced nanocomposites taking into account tunnelling effect
• Computational homogenization of nonlinear elastic materials using neural networks
• A new neural network-based model for hysteretic behavior of materials
• Electric Tunnel Effect between Dissimilar Electrodes Separated by a Thin Insulating Film
• Approximation by superpositions of a sigmoidal function
• An approach to micro-macro modeling of heterogeneous materials
• A multi-level computational model for multi-scale damage analysis in composite and porous materials
• A class of general algorithms for multi-scale analyses of heterogeneous media

This page was built for publication: A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites