Latent Representation of Computational Fluid Dynamics Meshes and Application to Airfoil Aerodynamics
Authors:
- Zhen WeiZWZhen Wei
- Benoît GuillardBGBenoît Guillard
- Pascal FuaPFPascal Fua
- Vincent ChapinVCVincent Chapin
- Michaël BauerheimMBMichaël Bauerheim
- 1 August 2023
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 61 (8) , 3507-3525
Abstract
Mesh manipulation is central to computational fluid dynamics. However, creating appropriate computational meshes often involves substantial manual intervention that has to be repeated each time the target shape changes. To address this problem, we propose an autodecoder-based latent representation approach. Human prior knowledge is embedded into learned geometric patterns, which eliminates the need for further handcrafting. Furthermore, the resulting computational meshes are differentiable with respect to the model parameters, which makes it suitable for inclusion in end-to-end trainable pipelines. We apply the model on two-dimensional airfoils to demonstrate its ability to handle various tasks.Keywords
Funding Information
- Agence de l’Innovation de Défense DECAP project
- Programme d’Investissements d’Avenir (ANR-17-EURE-0005)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
This publication has 31 references indexed in Scilit:
- Dimension Reduction for Aerodynamic Design OptimizationAIAA Journal, 2011
- Geometric Filtration Using Proper Orthogonal Decomposition for Aerodynamic Design OptimizationAIAA Journal, 2010
- Gmsh: A 3‐D finite element mesh generator with built‐in pre‐ and post‐processing facilitiesInternational Journal for Numerical Methods in Engineering, 2009
- Universal Parametric Geometry Representation MethodJournal of Aircraft, 2008
- Mesh deformation based on radial basis function interpolationComputers & Structures, 2007
- Surrogate-based analysis and optimizationProgress in Aerospace Sciences, 2005
- Concise Orthogonal Representation of Supercritical AirfoilsJournal of Aircraft, 2001
- Reducing data dimensionality through optimizing neural network inputsAIChE Journal, 1995
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- An optimal Poincaré inequality for convex domainsArchive for Rational Mechanics and Analysis, 1960