UPCommons. Portal del coneixement obert de la UPC
Publication
Artículo científico (JournalArticle)
Deep reinforcement learning for active flow control in a turbulent separation bubble
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., This work was performed in part during the Fifth Madrid Summer Workshop, funded by the European Research Council (ERC) under the Caust grant ERC-AdG-101018287. OL has been partially funded by the European Commission’s Horizon 2020 Framework program and the European High-Performance Computing Joint Undertaking (JU) under grant agreement no. 101093393, and by MCIN/AEI/10.13039/501100011033 and the European Union NextGenerationEU/PRTR (PCI2022-134996-2), project CEEC. OL has been partially supported by a Ramon y Cajal postdoctoral contract (ref: RYC2018-025949-I). RV and FAA acknowledge financial support from ERC grant no. ‘2021-CoG-101043998, DEEPCONTROL’. The authors thank Laia Julió from the BSC support services and Dr. Andrew Shao from the SmartSim team for the help and fruitful discussions about the CFD–DRL software framework. The authors also thank the UPM Turbulence Summer School and our hosts Javier Jiménez, Miguel Pérez Encinar and Adrián Lozano-Durán for the organization of the workshop. Finally, we acknowledge the National Academic Infrastructure for Supercomputing in Sweden (NAISS) for the computational time provided at the large-GPU systems Alvis and Berzelius., Peer Reviewed