AeroINR: meta-learning for efficient generation of aerodynamic geometries
AeroINR: meta-learning for efficient generation of aerodynamic geometries
Effective optimisation of aerodynamic shapes requires high-quality parameterisation of candidate geometries. In recent years, the increasing availability and applicability of data - through increasing computational power, GPUs, cloud storage and AI - has motivated the development of data-driven approaches to the parameterisation problem, particularly those that can process the image-based data coming from scanned design parts. In this paper a novel approach to aerodynamic shape parameterisation is proposed, which leverages meta-learning in a generative deep learning framework. The solution put forward - AeroINR - aims to learn continuous neural representations as surrogates of the discrete field data used for shape representation in image-based applications. This approach transforms the learning problem to that of the surrogate model weight distribution of candidate geometries, rather than grid-based field values directly, which can reduce the number of variables describing each geometry by an order of magnitude or more. Benchmarking is carried out against three state-of-the-art deep-learning based aerofoil parameterisations, with AeroINR shown to outperform these models in two of the three metrics considered. Ablation study results show the robustness of this approach to generative framework and choice of discrete field representation.
AI-Aided Design,, VAE, Hypernetworks, Meta-Learning, Implicit Neural Representations
Bamford, Joshua Thomas
e8cdc100-0e20-475c-8d67-01b191711526
Toal, David
dc67543d-69d2-4f27-a469-42195fa31a68
Keane, Andy
26d7fa33-5415-4910-89d8-fb3620413def
9 September 2024
Bamford, Joshua Thomas
e8cdc100-0e20-475c-8d67-01b191711526
Toal, David
dc67543d-69d2-4f27-a469-42195fa31a68
Keane, Andy
26d7fa33-5415-4910-89d8-fb3620413def
Bamford, Joshua Thomas, Toal, David and Keane, Andy
(2024)
AeroINR: meta-learning for efficient generation of aerodynamic geometries.
Bifet, Albert, Krilavičius, Tomas, Miliou, Ioanna and Nowaczyk, Slawomir
(eds.)
In Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track.
(doi:10.1007/978-3-031-70378-2_28).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Effective optimisation of aerodynamic shapes requires high-quality parameterisation of candidate geometries. In recent years, the increasing availability and applicability of data - through increasing computational power, GPUs, cloud storage and AI - has motivated the development of data-driven approaches to the parameterisation problem, particularly those that can process the image-based data coming from scanned design parts. In this paper a novel approach to aerodynamic shape parameterisation is proposed, which leverages meta-learning in a generative deep learning framework. The solution put forward - AeroINR - aims to learn continuous neural representations as surrogates of the discrete field data used for shape representation in image-based applications. This approach transforms the learning problem to that of the surrogate model weight distribution of candidate geometries, rather than grid-based field values directly, which can reduce the number of variables describing each geometry by an order of magnitude or more. Benchmarking is carried out against three state-of-the-art deep-learning based aerofoil parameterisations, with AeroINR shown to outperform these models in two of the three metrics considered. Ablation study results show the robustness of this approach to generative framework and choice of discrete field representation.
Text
AeroINR
- Accepted Manuscript
Restricted to Repository staff only until 22 August 2025.
Request a copy
More information
e-pub ahead of print date: 22 August 2024
Published date: 9 September 2024
Venue - Dates:
European Conference for Machine Learning and Knowledge Discovery in Databases, , Vilnius, Lithuania, 2024-09-09 - 2024-09-13
Keywords:
AI-Aided Design,, VAE, Hypernetworks, Meta-Learning, Implicit Neural Representations
Identifiers
Local EPrints ID: 494439
URI: http://eprints.soton.ac.uk/id/eprint/494439
PURE UUID: 03e9927f-1e3e-4a38-8500-c873969ad64d
Catalogue record
Date deposited: 08 Oct 2024 16:41
Last modified: 09 Oct 2024 02:05
Export record
Altmetrics
Contributors
Editor:
Albert Bifet
Editor:
Tomas Krilavičius
Editor:
Ioanna Miliou
Editor:
Slawomir Nowaczyk
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
