FEA-Net: a physics-guided data-driven model for efficient mechanical response prediction
From MaRDI portal
Publication:2309378
DOI10.1016/j.cma.2020.112892zbMath1436.74078arXiv2002.01893OpenAlexW3007593704MaRDI QIDQ2309378
Houpu Yao, Yi Gao, Yong-Ming Liu
Publication date: 31 March 2020
Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2002.01893
Finite element methods applied to problems in solid mechanics (74S05) Theory of constitutive functions in solid mechanics (74A20)
Related Items
DeLISA: deep learning based iteration scheme approximation for solving PDEs, Learning topology optimization process via convolutional long‐short‐term memory autoencoder‐decoder, On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method, Locally assembled stiffness matrix: a novel method to obtain global stiffness matrix, HiDeNN-FEM: a seamless machine learning approach to nonlinear finite element analysis, Embedding physical knowledge in deep neural networks for predicting the phonon dispersion curves of cellular metamaterials, Bayesian synergistic metamodeling (BSM) for physical information infused data-driven metamodeling, A complete physics-informed neural network-based framework for structural topology optimization, TONR: an exploration for a novel way combining neural network with topology optimization, Physics-informed graph neural Galerkin networks: a unified framework for solving PDE-governed forward and inverse problems
Uses Software
Cites Work
- Acceleration of the Jacobi iterative method by factors exceeding 100 using scheduled relaxation
- Global flexibility simulation and element stiffness simulation in finite element analysis with neural network
- High efficient load paths analysis with U* index generated by deep learning
- Smart finite elements: a novel machine learning application
- A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
- Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning
- Neural networks for topology optimization
- A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality
- Computational mechanics enhanced by deep learning