Investigations on Physics-Informed Neural Networks for Aerodynamics

TL;DR

This paper explores the application of Physics-Informed Neural Networks (PINNs) in aerodynamics, demonstrating their effectiveness in creating surrogate models, handling multiphysics, and inferring turbulence, while analyzing their robustness and challenges.

Contribution

It provides a comprehensive investigation into PINNs for aerodynamics, highlighting their capabilities and discussing current issues and challenges in the field.

Findings

PINNs can effectively construct parametric surrogate models.

PINNs enable multiphysics couplings in aerodynamics.

PINNs can infer turbulence characteristics from data.

Abstract

Physics-Informed Neural Networks (PINNs) have recently emerged as a novel approach to simulate complex physical systems on the basis of both data observations and physical models. In this work, we investigate the use of PINNs for various applications in aerodynamics and we explain how to leverage their specific formulation to perform some tasks effectively. In particular, we demonstrate the ability of PINNs to construct parametric surrogate models, to achieve multiphysic couplings and to infer turbulence characteristics via data assimilation. The robustness and accuracy of the PINNs approach are analysed, then current issues and challenges are discussed.