Year: 2020
Author: Zheng Sun, Shuyi Wang, Lo-Bin Chang, Yulong Xing, Dongbin Xiu
Communications in Computational Physics, Vol. 28 (2020), Iss. 5 : pp. 2075–2108
Abstract
We propose a universal discontinuity detector using convolution neural network (CNN) and apply it in conjunction of solving nonlinear conservation laws in both 1D and 2D. The CNN detector is trained offline with synthetic data. The training data are generated using randomly constructed piecewise functions, which are then processed using randomized linear advection solver to count for the cases of numerical errors in practice. The detector is then paired with high-order numerical solvers. In particular, we combined high-order WENO in troubled cells with high-order central difference in smooth region. Extensive numerical examples are presented. We observe that the proposed method produces notably sharper and cleaner signals near the discontinuities, when compared to other well known troubled cell detector methods.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/cicp.OA-2020-0199
Communications in Computational Physics, Vol. 28 (2020), Iss. 5 : pp. 2075–2108
Published online: 2020-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 34
Keywords: Deep neural network convolution neural network discontinuity detection troubled cell hybrid method hyperbolic conservation laws.
Author Details
-
Troubled-Cell Indication Using K-means Clustering with Unified Parameters
Zhu, Hongqiang | Wang, Zhihuan | Wang, Haiyun | Zhang, Qiang | Gao, ZhenJournal of Scientific Computing, Vol. 93 (2022), Iss. 1
https://doi.org/10.1007/s10915-022-01987-5 [Citations: 0] -
A neural network enhanced weighted essentially non-oscillatory method for nonlinear degenerate parabolic equations
Kossaczká, T. | Ehrhardt, M. | Günther, M.Physics of Fluids, Vol. 34 (2022), Iss. 2
https://doi.org/10.1063/5.0078397 [Citations: 10] -
A data-driven high order sub-cell artificial viscosity for the discontinuous Galerkin spectral element method
Zeifang, Jonas | Beck, AndreaJournal of Computational Physics, Vol. 441 (2021), Iss. P.110475
https://doi.org/10.1016/j.jcp.2021.110475 [Citations: 15] -
A hybrid WENO scheme for steady-state simulations of Euler equations
Wan, Yifei | Xia, YinhuaJournal of Computational Physics, Vol. 463 (2022), Iss. P.111292
https://doi.org/10.1016/j.jcp.2022.111292 [Citations: 4] -
Artificial intelligence and machine learning in aerodynamics
Kou, Jiaqing | Xiao, TianbaiMetascience in Aerospace, Vol. 1 (2024), Iss. 2 P.190
https://doi.org/10.3934/mina.2024009 [Citations: 0] -
Multi-layer Perceptron Estimator for the Total Variation Bounded Constant in Limiters for Discontinuous Galerkin Methods
Yu, Xinyue | Shu, Chi-WangLa Matematica, Vol. 1 (2022), Iss. 1 P.53
https://doi.org/10.1007/s44007-021-00004-9 [Citations: 6] -
A simplified multilayer perceptron detector for the hybrid WENO scheme
Xue, Zhengyang | Xia, Yinhua | Li, Chen | Yuan, XianxuComputers & Fluids, Vol. 244 (2022), Iss. P.105584
https://doi.org/10.1016/j.compfluid.2022.105584 [Citations: 2] -
A new scale-invariant hybrid WENO scheme for steady Euler and Navier-Stokes equations
Wan, Yifei
Applied Numerical Mathematics, Vol. 210 (2025), Iss. P.177
https://doi.org/10.1016/j.apnum.2024.12.012 [Citations: 0] -
Mastering the Cahn–Hilliard equation and Camassa–Holm equation with cell-average-based neural network method
Zhou, Xiaofang | Qiu, Changxin | Yan, Wenjing | Li, BiaoNonlinear Dynamics, Vol. 111 (2023), Iss. 5 P.4823
https://doi.org/10.1007/s11071-022-08088-w [Citations: 4] -
A New Hybrid WENO Scheme with the High-Frequency Region for Hyperbolic Conservation Laws
Wan, Yifei | Xia, YinhuaCommunications on Applied Mathematics and Computation, Vol. 5 (2023), Iss. 1 P.199
https://doi.org/10.1007/s42967-021-00153-2 [Citations: 4] -
A learned conservative semi-Lagrangian finite volume scheme for transport simulations
Chen, Yongsheng | Guo, Wei | Zhong, XinghuiJournal of Computational Physics, Vol. 490 (2023), Iss. P.112329
https://doi.org/10.1016/j.jcp.2023.112329 [Citations: 0] -
Deep smoothness weighted essentially non-oscillatory method for two-dimensional hyperbolic conservation laws: A deep learning approach for learning smoothness indicators
Kossaczká, Tatiana | Jagtap, Ameya D. | Ehrhardt, MatthiasPhysics of Fluids, Vol. 36 (2024), Iss. 3
https://doi.org/10.1063/5.0199322 [Citations: 1] -
Cell-average based neural network method for third order and fifth order KdV type equations
Chen, Yongsheng | Yan, Jue | Zhong, XinghuiFrontiers in Applied Mathematics and Statistics, Vol. 8 (2022), Iss.
https://doi.org/10.3389/fams.2022.1021069 [Citations: 2]