The University of Southampton
University of Southampton Institutional Repository

Graph-convolutional autoencoder frameworks for aerodynamic shape predictions of the Agard wing

Graph-convolutional autoencoder frameworks for aerodynamic shape predictions of the Agard wing
Graph-convolutional autoencoder frameworks for aerodynamic shape predictions of the Agard wing
This paper presents a novel framework for predicting aerodynamic surface fields through geometric deep learning, specifically applied to the Agard 446.5 wing test case. Leveraging a graph convolutional network within a multi-mesh autoencoder, the framework achieves efficient and accurate predictions of aerodynamic shape behavior. Two predictive methodologies are introduced, utilizing modal coordinates to represent shape variations, providing a significant improvement over traditional computational fluid dynamics by reducing dependency on extensive datasets. Initial findings demonstrate the models capability to accurately predict aerodynamic forces and flow fields across a range of deformed geometries. With rapid prediction capabilities, these models have the potential to integrate seamlessly into optimization workflows, accelerating the overall optimization process and streamlining the exploration of design space.
American Institute of Aeronautics and Astronautics
Massegur Sampietro, David
d5bc71e8-f1b8-4c9f-9537-7ff63ad19426
Immordino, Gabriele
ed9626cc-aa2b-40be-b376-0868967e5e65
Vaiuso, Andrea
510503a9-3071-4747-a346-8cd402200160
Da Ronch, Andrea
a2f36b97-b881-44e9-8a78-dd76fdf82f1a
Righi, Marcello
26caafe6-a86f-445b-82ca-9789ae4109ca
Massegur Sampietro, David
d5bc71e8-f1b8-4c9f-9537-7ff63ad19426
Immordino, Gabriele
ed9626cc-aa2b-40be-b376-0868967e5e65
Vaiuso, Andrea
510503a9-3071-4747-a346-8cd402200160
Da Ronch, Andrea
a2f36b97-b881-44e9-8a78-dd76fdf82f1a
Righi, Marcello
26caafe6-a86f-445b-82ca-9789ae4109ca

Massegur Sampietro, David, Immordino, Gabriele, Vaiuso, Andrea, Da Ronch, Andrea and Righi, Marcello (2025) Graph-convolutional autoencoder frameworks for aerodynamic shape predictions of the Agard wing. In AIAA SciTech Forum 2025. American Institute of Aeronautics and Astronautics.. (doi:10.2514/6.2025-0885).

Record type: Conference or Workshop Item (Paper)

Abstract

This paper presents a novel framework for predicting aerodynamic surface fields through geometric deep learning, specifically applied to the Agard 446.5 wing test case. Leveraging a graph convolutional network within a multi-mesh autoencoder, the framework achieves efficient and accurate predictions of aerodynamic shape behavior. Two predictive methodologies are introduced, utilizing modal coordinates to represent shape variations, providing a significant improvement over traditional computational fluid dynamics by reducing dependency on extensive datasets. Initial findings demonstrate the models capability to accurately predict aerodynamic forces and flow fields across a range of deformed geometries. With rapid prediction capabilities, these models have the potential to integrate seamlessly into optimization workflows, accelerating the overall optimization process and streamlining the exploration of design space.

This record has no associated files available for download.

More information

e-pub ahead of print date: 3 January 2025

Identifiers

Local EPrints ID: 501423
URI: http://eprints.soton.ac.uk/id/eprint/501423
PURE UUID: 4b85294d-3368-4a1f-a8d4-4ba56b97740c
ORCID for David Massegur Sampietro: ORCID iD orcid.org/0000-0001-6586-5097
ORCID for Gabriele Immordino: ORCID iD orcid.org/0000-0003-2718-0120
ORCID for Andrea Da Ronch: ORCID iD orcid.org/0000-0001-7428-6935

Catalogue record

Date deposited: 30 May 2025 16:57
Last modified: 03 Sep 2025 02:02

Export record

Altmetrics

Contributors

Author: David Massegur Sampietro ORCID iD
Author: Gabriele Immordino ORCID iD
Author: Andrea Vaiuso
Author: Andrea Da Ronch ORCID iD
Author: Marcello Righi

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×