Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations
From MaRDI portal
Publication:6107091
Abstract: We propose to accelerate a high order discontinuous Galerkin solver using neural networks. We include a corrective forcing to a low polynomial order simulation to enhance its accuracy. The forcing is obtained by training a deep fully connected neural network, using a high polynomial order simulation but only for a short time frame. With this corrective forcing, we can run the low polynomial order simulation faster (with large time steps and low cost per time step) while improving its accuracy. We explored this idea for a 1D Burgers' equation in (Marique and Ferrer, CAF 2022), and we have extended this work to the 3D Navier-Stokes equations, with and without a Large Eddy Simulation closure model. We test the methodology with the turbulent Taylor Green Vortex case and for various Reynolds numbers (30, 200 and 1600). In addition, the Taylor Green Vortex evolves with time and covers laminar, transitional, and turbulent regimes, as time progresses. The proposed methodology proves to be applicable to a variety of flows and regimes. The results show that the corrective forcing is effective in all Reynolds numbers and time frames (excluding the initial flow development). We can train the corrective forcing with a polynomial order of 8, to increase the accuracy of simulations from a polynomial order 3 to 6, when correcting outside the training time frame. The low order correct solution is 4 to 5 times faster than a simulation with comparable accuracy (polynomial order 6). Additionally, we explore changes in the hyperparameters and use transfer learning to speed up the training. We observe that it is not useful to train a corrective forcing using a different flow condition. However, an already trained corrective forcing can be used to initialise a new training (at the correct flow conditions) to obtain an effective forcing with only a few training iterations.
Recommendations
- Accelerating high order discontinuous Galerkin solvers using neural networks: 1D Burgers' equation
- A neural network multigrid solver for the Navier-Stokes equations
- DNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equations
- Controlling oscillations in high-order discontinuous Galerkin schemes using artificial viscosity tuned by neural networks
- NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
Cites work
- \texttt{HORSES3D}: a high-order discontinuous Galerkin solver for flow simulations and multi-physics applications
- A functional oriented truncation error adaptation method
- A high order Discontinuous Galerkin Finite Element solver for the incompressible Navier-Stokes equations
- A high-order accurate discontinuous finite element method for the numerical solution of the compressible Navier-Stokes equations
- A p-multigrid strategy with anisotropic p-adaptation based on truncation errors for high-order discontinuous Galerkin methods
- A review on deep reinforcement learning for fluid mechanics
- A statically condensed discontinuous Galerkin spectral element method on Gauss-Lobatto nodes for the compressible Navier-Stokes equations
- A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers
- Accelerating high order discontinuous Galerkin solvers using neural networks: 1D Burgers' equation
- Adaptation strategies for high order discontinuous Galerkin methods based on tau-estimation
- An interior penalty stabilised incompressible discontinuous Galerkin-Fourier solver for implicit large eddy simulations
- Approximate Riemann solvers, parameter vectors, and difference schemes
- Comparisons of p-adaptation strategies based on truncation- and discretisation-errors for high order discontinuous Galerkin methods
- Data-driven science and engineering. Machine learning, dynamical systems, and control
- Design of a Smagorinsky spectral vanishing viscosity turbulence model for discontinuous Galerkin methods
- Finite element approximation of wave problems with correcting terms based on training artificial neural networks with fine solutions
- Implementing Spectral Methods for Partial Differential Equations
- Learning data-driven discretizations for partial differential equations
- Small-scale structure of the Taylor–Green vortex
Cited in
(5)- Discretizationnet: a machine-learning based solver for Navier-Stokes equations using finite volume discretization
- A neural network multigrid solver for the Navier-Stokes equations
- DNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equations
- A novel paradigm for solving PDEs: multi-scale neural computing
- Learning high-accuracy numerical schemes for hyperbolic equations on coarse meshes
This page was built for publication: Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6107091)
