Abstract
Advection-dominated diffusion is a challenging computational problem that requires special stabilization efforts. Unfortunately, the numerical solution obtained with the commonly used Galerkin method delivers unexpected oscillation resulting in an inaccurate numerical solution. The theoretical background resulting from the famous inf-sup condition tells us that the finite-dimensional test space employed by the Galerkin method does not allow us to reach the supremum necessary for problem stability. We enlarge the test space to overcome this problem. We do it for a fixed trial space. The method that allows us to do so is the residual minimization method. This method, however, requires the solution to a much larger system of linear equations than the standard Galerkin method. We represent the larger test space by its set of optimal test functions, forming a basis of the same dimension as the trial space in the Galerkin method. The resulting Petrov-Galerkin method stabilizes our challenging advection-dominated problem. We train the optimal test functions offline with the neural network to speed up the computations. We also observe that the optimal test functions, usually global, can be approximated with local support functions, resulting in a low computational cost for the solver and a stable numerical solution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bazilevs, Y., Calo, V.M., Cottrell, J.A., Hughes, T.J.R., Reali, A., Scovazzi, G.: Variational multiscale residual-based turbulence modeling for large eddy simulation of incompressible flows. Comput. Methods Appl. Mech. Eng. 197(1), 173–201 (2007)
Berg, J., Nystrom, K.: Data-driven discovery of PDEs in complex datasets. J. Comput. Phys. 384, 239–252 (2019)
Brevis, I., Muga, I., van der Zee, K.: Data-driven finite elements methods: machine learning acceleration of goal-oriented computations (2020). Arxiv arXiv:2003.04485:1–24
Cottrell, J.A., Hughes, T.J.R., Bazilevs, Y.: Isogeometric analysis: toward integration of CAD and FEA. John Wiley & Sons (2009)
Demkowicz, L.: 2D \(hp\)-adaptive finite element package (2Dhp90) version 2.0. Ticam Report, 2:06 (2002)
Demkowicz, L., Rachowicz, W., Devloo, P.: A fully automatic \(hp\)-adaptivity. J. Sci. Comput. 17(1–4), 117–142 (2002)
Hackbusch, W., Grasedyck, L., Börm, S.: An introduction to hierarchical matrices. Math. Bohem. 127, 229–241 (2002)
Higham, C.F.: Deep learning: an introduction for applied mathematicians. SIAM Rev. 61(4), 860–891 (2019)
Hughes, T.J.R., Cottrell, J.A., Bazilevs, Y.: Isogeometric analysis: CAD, finite elements, NURBS, exact geometry and mesh refinement. Comput. Methods Appl. Mech. Eng. 194(39), 4135–4195 (2005)
Hughes, T.J.R., Franca, L., Mallet, M.: A new finite element formulation for computational fluid dynamics: vi. convergence analysis of the generalized supg formulation for linear time-dependent multidimensional advective-diffusive systems. Comput. Methods Appl. Mech. Eng. 63(1), 97–112 (1987)
Łoś, M., Deng, Q., Muga, I., Paszyński, M., Calo., V.: Isogeometric residual minimization method (iGRM) with direction splitting preconditoner for stationary advection-diffusion problems. Comput. Methods Appl. Mech. Eng. (in press.) (2020). arXiv:1906.06727
Łoś, M., Munoz-Matute, J., Muga, I., Paszyński, M.: Isogeometric residual minimization method (iGRM) with direction splitting for non-stationary advection-diffusion problems. Comput. Math. Appl. 79(2), 213–229 (2019)
Łoś, M., Munoz-Matute, J., Muga, I., Paszyński, M.: Isogeometric residual minimization for time-dependent stokes and navier-stokes problems. Comput. Math. Appl. (in press.) (2020). arXiv:2001.00178
Łoś, M., Rojas, S., Paszyński, M., Muga, I., Calo, V.: Discontinuous galerkin based isogeometric residual minimization for the stokes problem (DGIRM). In: Invited to the Special Issue of Journal of Computational Science on 20th Anniversary of ICCS Conference (2020)
Opschoor, J.A.A., Petersen, P.C., Schwab, C.: Deep ReLU networks and high-order finite element methods. Anal. Appl. 18(5), 715–770 (2020)
Paszyński, M., Służalec, T.: Petrov-galerkin formulation equivallent to the residual minimization method for finding an optimal test functions. ECCOMAS Congress, 5–9 June 2022, Oslo, Norway (2022)
Pietro, D., Ern, A.: Mathematical Aspects of Discontinuous Galerkin Methods. Springer (2011). https://doi.org/10.1007/978-3-642-22980-0
Schmitz, P., Ying, L.: A fast nested dissection solver for cartesian 3D elliptic problems using hierarchical matrices. J. Comput. Phys., 258:227–245 (2014)
Służalec, T., Dobija, M., Paszyńska, A., Muga, I., Paszyński, M.: Automatic stabilization of finite-element simulations using neural networks and hierarchical matrices (2022). arxiv.org/abs/2212.12695
Tsihrintzis, G., Sotiropoulos, D.N., Jain, L.C.: Machine learning paradigms: advances in data analytics. Springer (2019). https://doi.org/10.1007/978-3-319-94030-4
Jinchao, X.: Finite neuron method and convergence analysis. Commun. Comput. Phys. 28, 1707–1745 (2020)
Acknowledgement
The Authors are thankful for support from the funds assigned to AGH University of Science and Technology by the Polish Ministry of Science and Higher Education. Research project partly supported by program “Excellence initiative – research university” for the AGH University of Science and Technology.
The publication has been supported by a grant from the Faculty of Management and Social Communication under the Strategic Programme Excellence Initiative at Jagiellonian University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Służalec, T., Paszyński, M. (2023). Fast Solver for Advection Dominated Diffusion Using Residual Minimization and Neural Networks. In: Mikyška, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14074. Springer, Cham. https://doi.org/10.1007/978-3-031-36021-3_52
Download citation
DOI: https://doi.org/10.1007/978-3-031-36021-3_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36020-6
Online ISBN: 978-3-031-36021-3
eBook Packages: Computer ScienceComputer Science (R0)