List of Journal Publications
2019
2.
Ghavamian, F., Simone, A.
Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network Journal Article
In: COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, vol. 357, 2019.
Abstract | BibTeX | Tags: Deep learning, Machine learning, Multiscale modeling, Recurrent neural network, Strain softening, Viscoplasticity | Links:
@article{Ghavamian2019,
title = {Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network},
author = {F. Ghavamian and A. Simone},
doi = {10.1016/j.cma.2019.112594},
year = {2019},
date = {2019-01-01},
journal = {COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING},
volume = {357},
publisher = {Elsevier B.V.},
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 FE 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.},
keywords = {Deep learning, Machine learning, Multiscale modeling, Recurrent neural network, Strain softening, Viscoplasticity},
pubstate = {published},
tppubtype = {article}
}
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 FE 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.
2017
1.
Ghavamian, F., Tiso, P., Simone, A.
POD-DEIM model order reduction for strain softening viscoplasticity Journal Article
In: COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, vol. 317, pp. 458–479, 2017.
Abstract | BibTeX | Tags: Discrete empirical interpolation method, k-means clustering algorithm, Machine learning, Model order reduction, Perzyna viscoplasticity, Proper orthogonal decomposition, Strain softening | Links:
@article{Ghavamian2017,
title = {POD-DEIM model order reduction for strain softening viscoplasticity},
author = {F. Ghavamian and P. Tiso and A. Simone},
doi = {10.1016/j.cma.2016.11.025},
year = {2017},
date = {2017-01-01},
journal = {COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING},
volume = {317},
pages = {458–479},
publisher = {Elsevier B.V.},
abstract = {We demonstrate a Model Order Reduction technique for a system of nonlinear equations arising from the Finite Element Method (FEM) discretization of the three-dimensional quasistatic equilibrium equation equipped with a Perzyna viscoplasticity constitutive model. The procedure employs the Proper Orthogonal Decomposition-Galerkin (POD-G) in conjunction with the Discrete Empirical Interpolation Method (DEIM). For this purpose, we collect samples from a standard full order FEM analysis in the offline phase and cluster them using a novel -means clustering algorithm. The POD and the DEIM algorithms are then employed to construct a corresponding reduced order model. In the online phase, a sample from the current state of the system is passed, at each time step, to a nearest neighbor classifier in which the cluster that best describes it is identified. The force vector and its derivative with respect to the displacement vector are approximated using DEIM, and the system of nonlinear equations is projected onto a lower dimensional subspace using the POD-G. The constructed reduced order model is applied to two typical solid mechanics problems showing strain-localization (a tensile bar and a wall under compression) and a three-dimensional square-footing problem.},
keywords = {Discrete empirical interpolation method, k-means clustering algorithm, Machine learning, Model order reduction, Perzyna viscoplasticity, Proper orthogonal decomposition, Strain softening},
pubstate = {published},
tppubtype = {article}
}
We demonstrate a Model Order Reduction technique for a system of nonlinear equations arising from the Finite Element Method (FEM) discretization of the three-dimensional quasistatic equilibrium equation equipped with a Perzyna viscoplasticity constitutive model. The procedure employs the Proper Orthogonal Decomposition-Galerkin (POD-G) in conjunction with the Discrete Empirical Interpolation Method (DEIM). For this purpose, we collect samples from a standard full order FEM analysis in the offline phase and cluster them using a novel -means clustering algorithm. The POD and the DEIM algorithms are then employed to construct a corresponding reduced order model. In the online phase, a sample from the current state of the system is passed, at each time step, to a nearest neighbor classifier in which the cluster that best describes it is identified. The force vector and its derivative with respect to the displacement vector are approximated using DEIM, and the system of nonlinear equations is projected onto a lower dimensional subspace using the POD-G. The constructed reduced order model is applied to two typical solid mechanics problems showing strain-localization (a tensile bar and a wall under compression) and a three-dimensional square-footing problem.
