Aero-Nef: Neural Fields for Rapid Aircraft Aerodynamics Simulations
arXiv:2407.19916 · doi:10.1038/s41598-024-76983-w
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
32 pages
References in corpus (15)
- Geometric deep learning: going beyond Euclidean data
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
- Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
- Implicit Neural Representations with Periodic Activation Functions
- Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
- Data-Driven POD-Galerkin Reduced Order Model for Turbulent Flows
- Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
- An artificial neural network framework for reduced order modeling of transient flows
- Geom-DeepONet: A Point-cloud-based Deep Operator Network for Field Predictions on 3D Parameterized Geometries
- Physics-Informed Neural Networks for Parametric Compressible Euler Equations
- Operator Learning with Neural Fields: Tackling PDEs on General Geometries
- A composable machine-learning approach for steady-state simulations on high-resolution grids
- INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations