A nonlinear data-driven reduced order model for computational homogenization with physics/pattern-guided sampling

DOI10.1016/j.cma.2019.112657zbMath1441.74297WikidataQ115063490 ScholiaQ115063490MaRDI QIDQ2175074

Satyaki Bhattacharjee, Karel Matouš

Publication date: 28 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.2019.112657

zbMATH Keywords

parallel computing; machine learning; big data; computational homogenization; reduced order model; nonlinear manifold

Mathematics Subject Classification ID

74Q05: Homogenization in equilibrium problems of solid mechanics

65Z05: Applications to the sciences

74S99: Numerical and other methods in solid mechanics

Related Items

Editorial: Special issue on uncertainty quantification, machine learning, and data-driven modeling of biological systems

Uses Software

• Neural Network Toolbox

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multiscale modeling and characterization of granular matter: from grain kinematics to continuum mechanics
• Wavelet based reduced order models for microstructural analyses
• The analytical solution of the additive constant problem
• Regression models for functional data by reproducing kernel Hilbert spaces methods
• Random geometric graph diameter in the unit ball
• A non-linear dimension reduction methodology for generating data-driven stochastic input models
• Using level sets for creating virtual random packs of non-spherical convex shapes
• Multi-scale computational homogenization: trends and challenges
• A numerical method for homogenization in nonlinear elasticity
• An adaptive method for homogenization in orthotropic nonlinear elasticity
• Computational micro-to-macro transitions for discretized micro-structures of heterogeneous materials at finite strains based on the minimization of averaged incremental energy.
• \(FE^2\) multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials
• A manifold learning approach for integrated computational materials engineering
• Multilayer feedforward networks are universal approximators
• A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials
• Model reduction via parametrized locally invariant manifolds: Some examples
• Reduced basis hybrid computational homogenization based on a mixed incremental formulation
• Surrogate modeling of multiscale models using kernel methods
• Hierarchically parallel coupled finite strain multiscale solver for modeling heterogeneous layers
• Computational homogenization of nonlinear elastic materials using neural networks
• A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
• Volumes of Generalized Unit Balls
• On the Development of Volumetric Strain Energy Functions
• Large-Eddy Simulation of Turbulent Obstacle Flow Using a Dynamic Subgrid-Scale Model
• Mercer’s Theorem, Feature Maps, and Smoothing
• MODEL REDUCTION FOR FLUIDS, USING BALANCED PROPER ORTHOGONAL DECOMPOSITION
• Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning
• On constitutive macro-variables for heterogeneous solids at finite strain
• Random heterogeneous materials. Microstructure and macroscopic properties