Finite difference physics-informed neural networks enable improved solution accuracy of the Navier-Stokes equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Roy, Nityananda, Dürr, Robert, Bück, Andreas, Sundar, S.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916546636414976
author Roy, Nityananda
Dürr, Robert
Bück, Andreas
Sundar, S.
author_facet Roy, Nityananda
Dürr, Robert
Bück, Andreas
Sundar, S.
contents Generating an accurate solution of the Navier--Stokes equations using physics--informed neural networks (PINNs) for higher Reynolds numbers in the corners of a lid--driven cavity problem is challenging. In this paper, we improve the solution accuracy of the incompressible Navier--Stokes equations in the region near the walls significantly and generate accurate secondary vortices in the corners of the lid--driven cavity by solving the governing equations using finite difference--based PINNs (FD--PINNs) without employing the known solution. We adopt the domain decomposition method (DDM) and combine it with the FD--PINNs to solve the lid--driven cavity problem for the Reynolds numbers Re = 400 and Re=1000. A comparison of the mean square error (MSE) between the presented and standard FD--PINNs using the reference solution is exhibited, showing the accuracy and effectiveness of the new approach.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00014
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finite difference physics-informed neural networks enable improved solution accuracy of the Navier-Stokes equations
Roy, Nityananda
Dürr, Robert
Bück, Andreas
Sundar, S.
Computational Physics
Fluid Dynamics
Generating an accurate solution of the Navier--Stokes equations using physics--informed neural networks (PINNs) for higher Reynolds numbers in the corners of a lid--driven cavity problem is challenging. In this paper, we improve the solution accuracy of the incompressible Navier--Stokes equations in the region near the walls significantly and generate accurate secondary vortices in the corners of the lid--driven cavity by solving the governing equations using finite difference--based PINNs (FD--PINNs) without employing the known solution. We adopt the domain decomposition method (DDM) and combine it with the FD--PINNs to solve the lid--driven cavity problem for the Reynolds numbers Re = 400 and Re=1000. A comparison of the mean square error (MSE) between the presented and standard FD--PINNs using the reference solution is exhibited, showing the accuracy and effectiveness of the new approach.
title Finite difference physics-informed neural networks enable improved solution accuracy of the Navier-Stokes equations
topic Computational Physics
Fluid Dynamics
url https://arxiv.org/abs/2501.00014