Shocks Under Control: Taming Transonic Compressible Flow over an RAE2822 Airfoil with Deep Reinforcement Learning
Authors:
Preprint
Abstract
Active flow control of compressible transonic shock-boundary layer interactions over a two-dimensional RAE2822 airfoil at Re = 50,000 is investigated using deep reinforcement learning (DRL). The flow field exhibits highly unsteady dynamics, including complex shock-boundary layer interactions, shock oscillations, and the generation of Kutta waves from the trailing edge. A high-fidelity CFD solver, employing a fifth-order spectral discontinuous Galerkin scheme in space and a strong-stability-preserving Runge-Kutta (5,4) method in time, together with adaptive mesh refinement capability, is used to obtain the accurate flow field. Synthetic jet actuation is employed to manipulate these unsteady flow features, while the DRL agent autonomously discovers effective control strategies through direct interaction with high-fidelity compressible flow simulations. The trained controllers effectively mitigate shock-induced separation, suppress unsteady oscillations, and manipulate aerodynamic forces under transonic conditions. In the first set of experiments, aimed at both drag reduction and lift enhancement, the DRL-based control reduces the average drag coefficient by 13.78% and increases lift by 131.18%, thereby improving the lift-to-drag ratio by 121.52%, which underscores its potential for managing complex flow dynamics. In the second set, targeting drag reduction while maintaining lift, the DRL-based control achieves a 25.62% reduction in drag and a substantial 196.30% increase in lift, accompanied by markedly diminished oscillations. In this case, the lift-to-drag ratio improves by 220.26%.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Deep reinforcement cross-domain transfer learning of active flow control for three-dimensional bluff body flowJournal of Computational Physics, 2025
- Deep reinforcement learning for active flow control in a turbulent separation bubbleNature Communications, 2025
- Dynamic feature-based deep reinforcement learning for flow control of circular cylinder with sparse surface pressure sensingJournal of Fluid Mechanics, 2024
- Review of active control of circular cylinder flowOcean Engineering, 2022
- Adaptive activation functions accelerate convergence in deep and physics-informed neural networksJournal of Computational Physics, 2020
- Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow controlJournal of Fluid Mechanics, 2019
- From 2D to 3D in fluid turbulence: unexpected critical transitionsJournal of Fluid Mechanics, 2017
- The dominant wave-capturing flux: A finite-volume scheme without decomposition for systems of hyperbolic conservation lawsJournal of Computational Physics, 2006
- A High-Order Accurate Discontinuous Finite Element Method for the Numerical Solution of the Compressible Navier–Stokes EquationsJournal of Computational Physics, 1997
- An adaptive finite element scheme for transient problems in CFDComputer Methods in Applied Mechanics and Engineering, 1987