A machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problems-Reference-Cited by-同舟云学术

A machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problems

Published:2022 Issue:2 Volume:5 Page:1-26
ISSN:2640-3501
Container-title:Mathematics in Engineering
language:
Short-container-title:MINE

Author:

Tassi Tommaso¹,Zingaro Alberto²,Dede' Luca²

Affiliation:

1. Oliver Wyman Srl, Via Broletto 16, 20121, Milano, Italy

2. MOX, Laboratory of Scientific Computing, Dipartimento di Matematica, Politecnico di Milano, Piazza Leonardo da Vinci, 32, 20133, Milano, Italy

Abstract

<abstract><p>We propose using machine learning and artificial neural networks (ANNs) to enhance residual-based stabilization methods for advection-dominated differential problems. Specifically, in the context of the finite element method, we consider the streamline upwind Petrov-Galerkin (SUPG) stabilization method and we employ ANNs to optimally choose the stabilization parameter on which the method relies. We generate our dataset by solving optimization problems to find the optimal stabilization parameters that minimize the distances among the numerical and the exact solutions for different data of differential problem and the numerical settings of the finite element method, e.g., mesh size and polynomial degree. The dataset generated is used to train the ANN, and we used the latter "online" to predict the optimal stabilization parameter to be used in the SUPG method for any given numerical setting and problem data. We show, by means of 1D and 2D numerical tests for the advection-dominated differential problem, that our ANN approach yields more accurate solution than using the conventional stabilization parameter for the SUPG method.</p></abstract>

Publisher

American Institute of Mathematical Sciences (AIMS)

Subject

Applied Mathematics,Mathematical Physics,Analysis

Reference54 articles.

1. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro. et al., TensorFlow: Large-scale machine learning on heterogeneous systems, arXiv: 1603.04467.

2. M. S. Alnæs, J. Blechta, J. Hake, A. Johansson, B. Kehlet, A. Logg, et al., The fenics project version 1.5, Archive of Numerical Software, 3 (2015), 9–23. https://doi.org/10.11588/ans.2015.100.20553

3. Y. Bazilevs, V. M. Calo, J. A. Cottrell, T. J. R. Hughes, A. Reali, G. Scovazzi, Variational multiscale residual-based turbulence modeling for large eddy simulation of incompressible flows, Comput. Method. Appl. Mech. Eng., 197 (2007), 173–201. https://doi.org/10.1016/j.cma.2007.07.016

4. N. Bénard, J. Pons-Prats, J. Périaux, G. Bugeda, P. Braud, J. P. Bonnet, et al., Turbulent separated shear flow control by surface plasma actuator: experimental optimization by genetic algorithm approach, Exp. Fluids, 57 (2016), 22. https://doi.org/10.1007/s00348-015-2107-3

5. P. B. Bochev, C. R. Dohrmann, M. D. Gunzburger, Stabilization of low-order mixed finite elements for the Stokes equations, SIAM J. Numer. Anal., 44 (2016), 82–101. https://doi.org/10.1137/S0036142905444482

Cited by 9 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Learning quantities of interest from parametric PDEs: An efficient neural-weighted Minimal Residual approach;Computers & Mathematics with Applications;2024-06

2. A multiscale stabilized physics informed neural networks with weakly imposed boundary conditions transfer learning method for modeling advection dominated flow;Engineering with Computers;2024-05-06

3. Learning mesh motion techniques with application to fluid–structure interaction;Computer Methods in Applied Mechanics and Engineering;2024-05

4. Artificial neural network-augmented stabilized finite element method;Journal of Computational Physics;2024-02

5. Learning adaptive coarse basis functions of FETI-DP;Journal of Computational Physics;2024-01