Journals
Resources
About Us
Open Access

Convolution Neural Network Shock Detector for Numerical Solution of Conservation Laws

Convolution Neural Network Shock Detector for Numerical Solution of Conservation Laws

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

Zheng Sun

Shuyi Wang

Lo-Bin Chang

Yulong Xing

Dongbin Xiu

  1. Troubled-Cell Indication Using K-means Clustering with Unified Parameters

    Zhu, Hongqiang | Wang, Zhihuan | Wang, Haiyun | Zhang, Qiang | Gao, Zhen

    Journal of Scientific Computing, Vol. 93 (2022), Iss. 1

    https://doi.org/10.1007/s10915-022-01987-5 [Citations: 0]
  2. 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]
  3. A data-driven high order sub-cell artificial viscosity for the discontinuous Galerkin spectral element method

    Zeifang, Jonas | Beck, Andrea

    Journal of Computational Physics, Vol. 441 (2021), Iss. P.110475

    https://doi.org/10.1016/j.jcp.2021.110475 [Citations: 15]
  4. A hybrid WENO scheme for steady-state simulations of Euler equations

    Wan, Yifei | Xia, Yinhua

    Journal of Computational Physics, Vol. 463 (2022), Iss. P.111292

    https://doi.org/10.1016/j.jcp.2022.111292 [Citations: 4]
  5. Artificial intelligence and machine learning in aerodynamics

    Kou, Jiaqing | Xiao, Tianbai

    Metascience in Aerospace, Vol. 1 (2024), Iss. 2 P.190

    https://doi.org/10.3934/mina.2024009 [Citations: 0]
  6. Multi-layer Perceptron Estimator for the Total Variation Bounded Constant in Limiters for Discontinuous Galerkin Methods

    Yu, Xinyue | Shu, Chi-Wang

    La Matematica, Vol. 1 (2022), Iss. 1 P.53

    https://doi.org/10.1007/s44007-021-00004-9 [Citations: 6]
  7. A simplified multilayer perceptron detector for the hybrid WENO scheme

    Xue, Zhengyang | Xia, Yinhua | Li, Chen | Yuan, Xianxu

    Computers & Fluids, Vol. 244 (2022), Iss. P.105584

    https://doi.org/10.1016/j.compfluid.2022.105584 [Citations: 2]
  8. 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]
  9. Mastering the Cahn–Hilliard equation and Camassa–Holm equation with cell-average-based neural network method

    Zhou, Xiaofang | Qiu, Changxin | Yan, Wenjing | Li, Biao

    Nonlinear Dynamics, Vol. 111 (2023), Iss. 5 P.4823

    https://doi.org/10.1007/s11071-022-08088-w [Citations: 4]
  10. A New Hybrid WENO Scheme with the High-Frequency Region for Hyperbolic Conservation Laws

    Wan, Yifei | Xia, Yinhua

    Communications on Applied Mathematics and Computation, Vol. 5 (2023), Iss. 1 P.199

    https://doi.org/10.1007/s42967-021-00153-2 [Citations: 4]
  11. A learned conservative semi-Lagrangian finite volume scheme for transport simulations

    Chen, Yongsheng | Guo, Wei | Zhong, Xinghui

    Journal of Computational Physics, Vol. 490 (2023), Iss. P.112329

    https://doi.org/10.1016/j.jcp.2023.112329 [Citations: 0]
  12. 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, Matthias

    Physics of Fluids, Vol. 36 (2024), Iss. 3

    https://doi.org/10.1063/5.0199322 [Citations: 1]
  13. Cell-average based neural network method for third order and fifth order KdV type equations

    Chen, Yongsheng | Yan, Jue | Zhong, Xinghui

    Frontiers in Applied Mathematics and Statistics, Vol. 8 (2022), Iss.

    https://doi.org/10.3389/fams.2022.1021069 [Citations: 2]