A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning

DOI10.1016/j.cma.2018.01.036zbMath1440.74130OpenAlexW2788766513MaRDI QIDQ2310917

Publication date: 7 April 2020

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.2018.01.036

zbMATH Keywords

recurrent neural network directed graph multiscale method dual-porosity data-driven modeling embedded discontinuity

Mathematics Subject Classification ID

Fluid-solid interactions (including aero- and hydro-elasticity, porosity, etc.) (74F10) Finite element methods applied to problems in solid mechanics (74S05) Soil and rock mechanics (74L10)

Related Items

Learning constitutive relations using symmetric positive definite neural networks, A data-driven approach to full-field nonlinear stress distribution and failure pattern prediction in composites using deep learning, Multiscale modeling of inelastic materials with thermodynamics-based artificial neural networks (TANN), Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties, Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling, Model-free data-driven simulation of inelastic materials using structured data sets, tangent space information and transition rules, Accelerating the distance-minimizing method for data-driven elasticity with adaptive hyperparameters, A graph theoretic framework for representation, exploration and analysis on computed states of physical systems, Constrained neural network training and its application to hyperelastic material modeling, MAP123: a data-driven approach to use 1D data for 3D nonlinear elastic materials modeling, Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network, Finite element coupled positive definite deep neural networks mechanics system for constitutive modeling of composites, A fixed point multi-scale finite volume method: application to two-phase incompressible fluid flow through highly heterogeneous porous media, Three-scale multiphysics finite element framework (FE\(^3\)) modelling fault reactivation, Multiscale modeling of thermo-mechanical responses of granular materials: a hierarchical continuum-discrete coupling approach, Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity, <scp>Data</scp>‐physics driven reduced order homogenization, Interfacing finite elements with deep neural operators for fast multiscale modeling of mechanics problems, Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials, A neural kernel method for capturing multiscale high-dimensional micromorphic plasticity of materials with internal structures, Physically enhanced training for modeling rate-independent plasticity with feedforward neural networks, A structure-preserving neural differential operator with embedded Hamiltonian constraints for modeling structural dynamics, 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, Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions, Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response, Multiscale Modeling of Metal-Ceramic Spatially Tailored Materials via Gaussian Process Regression and Peridynamics, A framework for neural network based constitutive modelling of inelastic materials, A phase field model for cohesive fracture in micropolar continua, A continuum framework for coupled solid deformation-fluid flow through anisotropic elastoplastic porous media, Physics-informed multi-LSTM networks for metamodeling of nonlinear structures, Anisotropic elastoplastic response of double-porosity media, Unsupervised discovery of interpretable hyperelastic constitutive laws, A kd-tree-accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data, Cell division in deep material networks applied to multiscale strain localization modeling, Deep autoencoders for physics-constrained data-driven nonlinear materials modeling, An updated Lagrangian LBM-DEM-FEM coupling model for dual-permeability fissured porous media with embedded discontinuities, High efficient load paths analysis with U* index generated by deep learning, A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials, Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning, A micromorphically regularized Cam-Clay model for capturing size-dependent anisotropy of geomaterials, Predicting the mechanical properties of biopolymer gels using neural networks trained on discrete fiber network data, Smart constitutive laws: inelastic homogenization through machine learning, A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks, 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, Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening, Phase field modeling of frictional slip with slip weakening/strengthening under non-isothermal conditions, A multi-stage deep learning based algorithm for multiscale model reduction, Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks, A physics-constrained data-driven approach based on locally convex reconstruction for noisy database, \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials, Deep material network with cohesive layers: multi-stage training and interfacial failure analysis, FFT-based solver for higher-order and multi-phase-field fracture models applied to strongly anisotropic brittle materials, Derivation of heterogeneous material laws via data-driven principal component expansions, A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation, A representative volume element network (RVE-net) for accelerating RVE analysis, microscale material identification, and defect characterization, Multiscale finite element calculations in Python using sfepy, Learning constitutive relations from indirect observations using deep 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, Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response, General solution and Green's function for fluid-saturated infinite and semi-infinite orthotropic poro-thermoelastic materials, Multiscale modelling and material design of woven textiles using Gaussian processes

Uses Software

Cites Work