An artificial intelligence approach to model nonlinear continua by intelligent meta‐elements
Authors:
Open Access
- 25 January 2021
- journal article
- section 4
- Published by Wiley in Proceedings in Applied Mathematics and Mechanics
- Vol. 20 (1) , e202000300
Abstract
A data‐driven “intelligent” meta‐element that reduces the dimensionality and accelerates nonlinear finite element computations is demonstrated on an elastoplastic continuum frame.Keywords
This publication has 9 references indexed in Scilit:
- A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading pathsComputer Methods in Applied Mechanics and Engineering, 2020
- An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new Time-distributed Residual U-Net architectureComputer Methods in Applied Mechanics and Engineering, 2020
- SO(3)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materialsComputer Methods in Applied Mechanics and Engineering, 2020
- Mechanik 4.0. Künstliche Intelligenz zur Analyse mechanischer Systeme2019
- An efficient Monte Carlo strategy for elasto-plastic structures based on recurrent neural networksActa Mechanica, 2019
- Smart finite elements: A novel machine learning applicationComputer Methods in Applied Mechanics and Engineering, 2019
- An intelligent meta‐element for linear elastic continuaProceedings in Applied Mathematics and Mechanics, 2018
- Efficient numerical modeling of 3D-printed lattice-cell structures using neural networksManufacturing Letters, 2018
- An efficient Monte Carlo simulation strategy based on model order reduction and artificial neural networksProceedings in Applied Mathematics and Mechanics, 2017