Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition

DOI10.1016/j.cma.2021.114030zbMath1502.74017MaRDI QIDQ2237770

Sunyoung Im, Maenghyo Cho, Jonggeon Lee

Publication date: 28 October 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.2021.114030

zbMATH Keywords

elasto-plasticity; surrogate model; proper orthogonal decomposition (POD); long short-term memory (LSTM); nonlinear model order reduction (MOR)

Mathematics Subject Classification ID

74C05: Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials)

65N30: Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs

Uses Software

• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An effective computational tool for parametric studies and identification problems in materials mechanics
• Model reduction in elastoplasticity: proper orthogonal decomposition combined with adaptive sub-structuring
• Multi-level a priori hyper-reduction of mechanical models involving internal variables
• Equivalent model construction for a non-linear dynamic system based on an element-wise stiffness evaluation procedure and reduced analysis of the equivalent system
• Kriging metamodeling in simulation: a review
• Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation
• Metamodeling: Radial basis functions, versus polynomials
• Model order reduction and domain decomposition strategies for the solution of the dynamic elastic-plastic structural problem
• Machine learning aided stochastic elastoplastic analysis
• Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
• An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new time-distributed residual U-net architecture
• An artificial neural network framework for reduced order modeling of transient flows
• Physics-informed multi-LSTM networks for metamodeling of nonlinear structures
• A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths
• Reduction process based on proper orthogonal decomposition for dual formulation of dynamic substructures
• An interpolation-based parametric reduced order model combined with component mode synthesis
• A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites
• Derivation of heterogeneous material laws via data-driven principal component expansions
• Two-level scheme for selection of primary degrees of freedom and semi-analytic sensitivity based on the reduced system
• Characterizing rate-dependent material behaviors in self-learning simulation
• Model order reduction for nonlinear dynamical systems based on trajectory piecewise-linear approximations
• PHYSICAL INTERPRETATION OF THE PROPER ORTHOGONAL MODES USING THE SINGULAR VALUE DECOMPOSITION
• Nonlinear model order reduction based on local reduced-order bases
• Computational homogenization of nonlinear elastic materials using neural networks
• Introduction to Nonlinear Finite Element Analysis
• An acceleration method in elasto-plastic finite element computation
• Construction of reduced-order models for fluid flows using deep feedforward neural networks
• Coupling of substructures for dynamic analyses.
• Metamodels for computer-based engineering design: Survey and recommendations