Investigation of Numerical Diffusion in Aerodynamic Flow Simulations with Physics Informed Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911337833037824 |
|---|---|
| author | Warey, Alok Han, Taeyoung Kaushik, Shailendra |
| author_facet | Warey, Alok Han, Taeyoung Kaushik, Shailendra |
| contents | Computational Fluid Dynamics (CFD) simulations are used for many air flow simulations including road vehicle aerodynamics. Numerical diffusion occurs when local flow direction is not aligned with the mesh lines and when there is a non-zero gradient of the dependent variable in the direction normal to the streamline direction. It has been observed that typical numerical discretization schemes for the Navier-Stokes equations such as first order upwinding produce very accurate solutions without numerical diffusion when the mesh is aligned with the streamline directions. On the other hand, numerical diffusion is maximized when the streamline direction is at an angle of 45° relative to the mesh line. The amount of numerical diffusion can be reduced by mesh refinements such as aligning mesh lines along the local flow direction or by introducing higher order numerical schemes which may introduce potential numerical instability or additional computational cost. Couple test cases of a simple steady-state incompressible and inviscid air flow convection problem were used to investigate whether numerical diffusion occurs when using Physics Informed Neural Networks (PINNs) that rely on automatic differentiation as opposed to numerical techniques used in traditional Computational Fluid Dynamics (CFD) solvers. Numerical diffusion was not observed when PINNs were used to solve the Partial Differential Equation (PDE) for the simple convection problem irrespective of flow angle. The PINN correctly simulated the streamwise upwinding, which has great potential to improve the accuracy of Navier-Stokes solvers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2103_03115 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Investigation of Numerical Diffusion in Aerodynamic Flow Simulations with Physics Informed Neural Networks Warey, Alok Han, Taeyoung Kaushik, Shailendra Fluid Dynamics Computational Fluid Dynamics (CFD) simulations are used for many air flow simulations including road vehicle aerodynamics. Numerical diffusion occurs when local flow direction is not aligned with the mesh lines and when there is a non-zero gradient of the dependent variable in the direction normal to the streamline direction. It has been observed that typical numerical discretization schemes for the Navier-Stokes equations such as first order upwinding produce very accurate solutions without numerical diffusion when the mesh is aligned with the streamline directions. On the other hand, numerical diffusion is maximized when the streamline direction is at an angle of 45° relative to the mesh line. The amount of numerical diffusion can be reduced by mesh refinements such as aligning mesh lines along the local flow direction or by introducing higher order numerical schemes which may introduce potential numerical instability or additional computational cost. Couple test cases of a simple steady-state incompressible and inviscid air flow convection problem were used to investigate whether numerical diffusion occurs when using Physics Informed Neural Networks (PINNs) that rely on automatic differentiation as opposed to numerical techniques used in traditional Computational Fluid Dynamics (CFD) solvers. Numerical diffusion was not observed when PINNs were used to solve the Partial Differential Equation (PDE) for the simple convection problem irrespective of flow angle. The PINN correctly simulated the streamwise upwinding, which has great potential to improve the accuracy of Navier-Stokes solvers. |
| title | Investigation of Numerical Diffusion in Aerodynamic Flow Simulations with Physics Informed Neural Networks |
| topic | Fluid Dynamics |
| url | https://arxiv.org/abs/2103.03115 |