A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials

DOI10.1016/j.cma.2018.09.020zbMath1440.74340arXiv1807.09829OpenAlexW2884529566WikidataQ129201848 ScholiaQ129201848MaRDI QIDQ1986850

Yanyan Li

Publication date: 9 April 2020

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

Full work available at URL: https://arxiv.org/abs/1807.09829

zbMATH Keywords

large deformations machine learning building blocks nonlinear plasticity material network

Mathematics Subject Classification ID

Homogenization in equilibrium problems of solid mechanics (74Q05)

Related Items

Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning, Learning constitutive relations using symmetric positive definite neural networks, An FE-DMN method for the multiscale analysis of thermomechanical composites, RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors, Data-driven prognostic model for temperature field in additive manufacturing based on the high-fidelity thermal-fluid flow simulation, A mixed FFT-Galerkin approach for incompressible or slightly compressible hyperelastic solids under finite deformation, Microstructure-guided deep material network for rapid nonlinear material modeling and uncertainty quantification, Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling, 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, A machine learning based plasticity model using proper orthogonal decomposition, Superaccurate effective elastic moduli via postprocessing in computational homogenization, Machine learning-enabled self-consistent parametrically-upscaled crystal plasticity model for Ni-based superalloys, Micromechanics-based surrogate models for the response of composites: a critical comparison between a classical mesoscale constitutive model, hyper-reduction and neural networks, Deep CNNs as universal predictors of elasticity tensors in homogenization, A comparative study on different neural network architectures to model inelasticity, Physically enhanced training for modeling rate-independent plasticity with feedforward neural networks, Reduced order mathematical homogenization method for polycrystalline microstructure with microstructurally small cracks, Automatic generation of interpretable hyperelastic material models by symbolic regression, Two-stage 2D-to-3d reconstruction of realistic microstructures: implementation and numerical validation by effective properties, \(\mathrm{FE^{ANN}}\): an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining, Incompressible rubber thermoelasticity: a neural network approach, Learning Markovian Homogenized Models in Viscoelasticity, On the micromechanics of deep material networks, 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, Micromechanics-informed parametric deep material network for physics behavior prediction of heterogeneous materials with a varying morphology, Self-optimization wavelet-learning method for predicting nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations, Transfer learning of recurrent neural network‐based plasticity models, A micromechanical mean‐field homogenization surrogate for the stochastic multiscale analysis of composite materials failure, Cooperative data-driven modeling, Optimal parameters selection of back propagation algorithm in the feedforward neural network, Deep learning framework for multiscale finite element analysis based on data-driven mechanics and data augmentation, Multiscale Modeling of Metal-Ceramic Spatially Tailored Materials via Gaussian Process Regression and Peridynamics, On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning, Model-free data-driven identification algorithm enhanced by local manifold learning, Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate, Poroelastic model parameter identification using artificial neural networks: on the effects of heterogeneous porosity and solid matrix Poisson ratio, 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, Efficient prediction of the effective nonlinear properties of porous material by FEM-cluster based analysis (FCA), Cell division in deep material networks applied to multiscale strain localization modeling, An FE-DMN method for the multiscale analysis of short fiber reinforced plastic components, Deep autoencoders for physics-constrained data-driven nonlinear materials modeling, On the mathematical foundations of the self-consistent clustering analysis for non-linear materials at small strains, Large-deformation reduced order homogenization of polycrystalline materials, A computational multi-scale model for the stiffness degradation of short-fiber reinforced plastics subjected to fatigue loading, Geometric deep learning for computational mechanics. I: Anisotropic hyperelasticity, A GFEM-based reduced-order homogenization model for heterogeneous materials under volumetric and interfacial damage, Machine learning for metal additive manufacturing: predicting temperature and melt pool fluid dynamics using physics-informed neural networks, A multiscale high-cycle fatigue-damage model for the stiffness degradation of fiber-reinforced materials based on a mixed variational framework, \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials, FEA-Net: a physics-guided data-driven model for efficient mechanical response prediction, Deep material network with cohesive layers: multi-stage training and interfacial failure analysis, Exploring the 3D architectures of deep material network in data-driven multiscale mechanics, Interaction-based material network: a general framework for (porous) microstructured materials, Clustering discretization methods for generation of material performance databases in machine learning and design optimization, Transfer learning of deep material network for seamless structure-property predictions, A representative volume element network (RVE-net) for accelerating RVE analysis, microscale material identification, and defect characterization, A dynamical view of nonlinear conjugate gradient methods with applications to FFT-based computational micromechanics, Material Modeling via Thermodynamics-Based Artificial Neural Networks, Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks

Cites Work