Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
This work provides a method for accelerating computational fluid dynamics simulations for aerospace engineering, though it is incremental as it applies an existing neural network architecture to a specific physics problem.
The study investigated the accuracy of deep learning models, specifically a modernized U-net architecture, for predicting Reynolds-Averaged Navier-Stokes solutions in airfoil flows, achieving mean relative pressure and velocity errors of less than 3% on unseen airfoil shapes.
With this study we investigate the accuracy of deep learning models for the inference of Reynolds-Averaged Navier-Stokes solutions. We focus on a modernized U-net architecture, and evaluate a large number of trained neural networks with respect to their accuracy for the calculation of pressure and velocity distributions. In particular, we illustrate how training data size and the number of weights influence the accuracy of the solutions. With our best models we arrive at a mean relative pressure and velocity error of less than 3% across a range of previously unseen airfoil shapes. In addition all source code is publicly available in order to ensure reproducibility and to provide a starting point for researchers interested in deep learning methods for physics problems. While this work focuses on RANS solutions, the neural network architecture and learning setup are very generic, and applicable to a wide range of PDE boundary value problems on Cartesian grids.