Aero-Nef: Neural Fields for Rapid Aircraft Aerodynamics Simulations

TL;DR

Aero-Nef introduces neural field models that rapidly and accurately simulate steady-state aircraft aerodynamics on complex, unstructured meshes, outperforming existing methods in speed and generalization.

Contribution

The paper presents a novel implicit neural representation approach for surrogate modeling of aerodynamics, capable of handling unstructured domains and geometric variations with improved efficiency.

Findings

Achieves over three times lower test error than state-of-the-art GNNs.

Significantly improves generalization to unseen geometries.

Performs inference five orders of magnitude faster than high-fidelity solvers.

Abstract

This paper presents a methodology to learn surrogate models of steady state fluid dynamics simulations on meshed domains, based on Implicit Neural Representations (INRs). The proposed models can be applied directly to unstructured domains for different flow conditions, handle non-parametric 3D geometric variations, and generalize to unseen shapes at test time. The coordinate-based formulation naturally leads to robustness with respect to discretization, allowing an excellent trade-off between computational cost (memory footprint and training time) and accuracy. The method is demonstrated on two industrially relevant applications: a RANS dataset of the two-dimensional compressible flow over a transonic airfoil and a dataset of the surface pressure distribution over 3D wings, including shape, inflow condition, and control surface deflection variations. On the considered test cases, our approach achieves a more than three times lower test error and significantly improves generalization error on unseen geometries compared to state-of-the-art Graph Neural Network architectures. Remarkably, the method can perform inference five order of magnitude faster than the high fidelity solver on the RANS transonic airfoil dataset. Code is available at https://gitlab.isae-supaero.fr/gi.catalani/aero-nepf