Deep reinforcement learning for active flow control in a turbulent separation bubble
Top Cited Papers
Open Access
- 7 February 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-13
Abstract
The control efficacy of deep reinforcement learning (DRL) compared with classical periodic forcing is numerically assessed for a turbulent separation bubble (TSB). We show that a control strategy learned on a coarse grid works on a fine grid as long as the coarse grid captures main flow features. This allows to significantly reduce the computational cost of DRL training in a turbulent-flow environment. On the fine grid, the periodic control is able to reduce the TSB area by 6.8%, while the DRL-based control achieves 9.0% reduction. Furthermore, the DRL agent provides a smoother control strategy while conserving momentum instantaneously. The physical analysis of the DRL control strategy reveals the production of large-scale counter-rotating vortices by adjacent actuator pairs. It is shown that the DRL agent acts on a wide range of frequencies to sustain these vortices in time. Last, we also introduce our computational fluid dynamics and DRL open-source framework suited for the next generation of exascale computing machines.Keywords
All Related Versions
This publication has 78 references indexed in Scilit:
- SOD2D: A GPU-enabled Spectral Finite Elements Method for compressible scale-resolving simulationsComputer Physics Communications, 2023
- Deep reinforcement learning for turbulence modeling in large eddy simulationsInternational Journal of Heat and Fluid Flow, 2022
- Active flow control with rotating cylinders by an artificial neural network trained by deep reinforcement learningJournal of Hydrodynamics, 2020
- Plasma Streamwise Vortex Generators for Flow Separation Control on TrucksFlow, Turbulence and Combustion, 2018
- Pressure-Gradient Turbulent Boundary Layers Developing Around a Wing SectionFlow, Turbulence and Combustion, 2017
- Direct numerical simulation of a self-similar adverse pressure gradient turbulent boundary layerInternational Journal of Heat and Fluid Flow, 2016
- Direct numerical simulation of the flow around a wing section at moderate Reynolds numberInternational Journal of Heat and Fluid Flow, 2016
- A parametric study of adverse pressure gradient turbulent boundary layersInternational Journal of Heat and Fluid Flow, 2011
- Large-Eddy simulations of circular synthetic jets in quiescent surroundings and in turbulent cross-flowInternational Journal of Heat and Fluid Flow, 2009
- RESONANT MODE INTERACTION IN A CANONICAL SEPARATED FLOW2006