Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network

Journal article (2019)

Authors

F. Ghavamian Applied Mechanics - CEG
A. Simone Applied Mechanics - CEG , Università degli Studi di Padova
Research Group
Applied Mechanics (CEG) (TU Delft)
Copyright: © 2019 F. Ghavamian, A. Simone
DOI: https://doi.org/10.1016/j.cma.2019.112594
Machine learning Deep learning Viscoplasticity Strain softening Recurrent neural network Multiscale modeling
More Info
expand_more

Published Date

2019

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Civil Engineering & Geosciences

Department

Materials- Mechanics- Management & Design

Research Group

Applied Mechanics

Abstract

FE2 multiscale simulations of history-dependent materials are accelerated by means of a recurrent neural network (RNN) surrogate for the history-dependent micro level response. We propose a simple strategy to efficiently collect stress–strain data from the micro model, and we modify the RNN model such that it resembles a nonlinear finite element analysis procedure during training. We then implement the trained RNN model in the FE2 scheme and employ automatic differentiation to compute the consistent tangent. The exceptional performance of the proposed model is demonstrated through a number of academic examples using strain-softening Perzyna viscoplasticity as the nonlinear material model at the micro level.