Physics informed neural networks for Triple Deck

Abderrahmane, Belkallouche, Rezoug, Tahar, Dala, Laurent and Tan, Kian (2022) Physics informed neural networks for Triple Deck. Aircraft Engineering and Aerospace Technology, 94 (8). pp. 1422-1432. ISSN 1748-8842

[img]
Preview
Text
PDF_Proof.PDF - Accepted Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1108/AEAT-10-2021-0309

Abstract

Purpose – This paper introduces physics-informed neural networks (PINN) applied to the two dimensional steady-state laminar Navier-Stokes equations over a flat plate with roughness elements and specified local heating. The method bridges the gap between asymptotics theory and three dimensional turbulent flow analyses, characterised by high costs in analysis setups and prohibitive computing times. The results indicate the possibility of using surface heating or wavy surface to control the incoming flow field.

Design/methodology/approach – The understanding of the flow control mechanism is normally caused by the unsteady interactions between the aircraft structure and the turbulent flows as well as some studies have shown, surface roughness can significantly influence the fluid dynamics by inducing perturbations in the velocity profile.

Findings – The description of the boundary-layer flow, based upon a Triple-Deck structure, shows how a wavy surface and a local surface heating generate an interaction between the inviscid region and the viscous region near the flat plate.

Originality/value–The presented approach is especially original in relation to the innovative concept of physics-informed neural networks as a solver of the asymptotic triple deck method apply to the viscous-inviscid boundary layer interaction.

Item Type: Article
Uncontrolled Keywords: PINN's, Triple Deck, Asymptotic, Flow control
Subjects: F300 Physics
Department: Faculties > Engineering and Environment > Mechanical and Construction Engineering
Depositing User: John Coen
Date Deposited: 17 Mar 2022 11:31
Last Modified: 16 Sep 2022 08:45
URI: https://nrl.northumbria.ac.uk/id/eprint/48683

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics