A Six-Point Shock-Capturing Scheme With Neural Network

Yue Li; Lin Fu; Nikolaus A. Adams

doi:10.1063/5.0162506

A Six-Point Shock-Capturing Scheme With Neural Network

Yue Li
, Lin Fu
, Nikolaus A. Adams

Chair of Aerodynamics and Fluid mechanics

Technical University of Munich
Hong Kong University of Science and Technology

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

A recent study of low-dissipation shock-capturing scheme [Fu et al., Journal of Computational Physics 305 (2016): 333-359] proposed a nonlinear sharp selection function to remove the contributions of candidate stencils containing discontinuities from the final reconstruction. In this paper, we train a neural network to replace this empirical level nonlinear selection function in the six-order TENO6-opt scheme. The performance and robustness of the neuron-based six-point scheme are demonstrated with the advection function and 1D Euler equations.

Original language	English
Article number	450004
Journal	AIP Conference Proceedings
Volume	2849
Issue number	1
DOIs	https://doi.org/10.1063/5.0162506
State	Published - 1 Sep 2023
Event	International Conference on Numerical Analysis and Applied Mathematics 2021, ICNAAM 2021 - Rhodes, Greece Duration: 20 Sep 2021 → 26 Sep 2021

Access to Document

10.1063/5.0162506

Cite this

@article{d529bc5a09304223855edc84aab9c79b,

title = "A Six-Point Shock-Capturing Scheme With Neural Network",

abstract = "A recent study of low-dissipation shock-capturing scheme [Fu et al., Journal of Computational Physics 305 (2016): 333-359] proposed a nonlinear sharp selection function to remove the contributions of candidate stencils containing discontinuities from the final reconstruction. In this paper, we train a neural network to replace this empirical level nonlinear selection function in the six-order TENO6-opt scheme. The performance and robustness of the neuron-based six-point scheme are demonstrated with the advection function and 1D Euler equations.",

author = "Yue Li and Lin Fu and Adams, \{Nikolaus A.\}",

note = "Publisher Copyright: {\textcopyright} 2023 American Institute of Physics Inc.. All rights reserved.; International Conference on Numerical Analysis and Applied Mathematics 2021, ICNAAM 2021 ; Conference date: 20-09-2021 Through 26-09-2021",

year = "2023",

month = sep,

day = "1",

doi = "10.1063/5.0162506",

language = "English",

volume = "2849",

journal = "AIP Conference Proceedings",

issn = "0094-243X",

publisher = "American Institute of Physics",

number = "1",

}

TY - JOUR

T1 - A Six-Point Shock-Capturing Scheme With Neural Network

AU - Li, Yue

AU - Fu, Lin

AU - Adams, Nikolaus A.

PY - 2023/9/1

Y1 - 2023/9/1

N2 - A recent study of low-dissipation shock-capturing scheme [Fu et al., Journal of Computational Physics 305 (2016): 333-359] proposed a nonlinear sharp selection function to remove the contributions of candidate stencils containing discontinuities from the final reconstruction. In this paper, we train a neural network to replace this empirical level nonlinear selection function in the six-order TENO6-opt scheme. The performance and robustness of the neuron-based six-point scheme are demonstrated with the advection function and 1D Euler equations.

AB - A recent study of low-dissipation shock-capturing scheme [Fu et al., Journal of Computational Physics 305 (2016): 333-359] proposed a nonlinear sharp selection function to remove the contributions of candidate stencils containing discontinuities from the final reconstruction. In this paper, we train a neural network to replace this empirical level nonlinear selection function in the six-order TENO6-opt scheme. The performance and robustness of the neuron-based six-point scheme are demonstrated with the advection function and 1D Euler equations.

UR - https://www.scopus.com/pages/publications/85176797231

U2 - 10.1063/5.0162506

DO - 10.1063/5.0162506

M3 - Conference article

AN - SCOPUS:85176797231

SN - 0094-243X

VL - 2849

JO - AIP Conference Proceedings

JF - AIP Conference Proceedings

IS - 1

M1 - 450004

T2 - International Conference on Numerical Analysis and Applied Mathematics 2021, ICNAAM 2021

Y2 - 20 September 2021 through 26 September 2021

ER -

A Six-Point Shock-Capturing Scheme With Neural Network

Abstract

Access to Document

Other files and links

Fingerprint

Cite this