The flow dynamics around tandem cylinders are complex, with significant engineering implications, especially in applications like high-rise buildings. This study presents a jet flow control framework for two tandem cylinders with a Reynolds number (Re) of 100, based on deep reinforcement learning. We compare two control strategies: (1) a single-agent strategy, where one controller manages the jet flow for two cylinders and (2) a dual-agent strategy, where separate controllers regulate each cylinder independently. The effectiveness of both strategies is evaluated under varying cylinder radii and inter-cylinder spacing. The results show that the single-agent strategy achieves drag reductions of approximately 28% and 40% for the front and rear cylinders, respectively, while the dual-agent strategy results in reductions of about 32% and 31%. While the single-agent strategy is more effective at reducing drag on the rear cylinder, the dual-agent strategy provides superior drag reduction for the larger cylinder and exhibits smaller fluctuations in drag across all conditions.
Skip Nav Destination
Deep reinforcement learning-based jet control for tandem cylinders
Article navigation
January 2025
Research Article|
January 08 2025
Deep reinforcement learning-based jet control for tandem cylinders
Special Collection:
Flow and Civil Structures
Xian-Jun He (何贤军)
;
Xian-Jun He (何贤军)
(Writing – original draft)
1
School of Energy and Power Engineering, Nanjing University of Science and Technology
, Nanjing 210094, China
Search for other works by this author on:
Jiang-Liu Huang (黄江流);
Jiang-Liu Huang (黄江流)
(Investigation)
2
Shanghai Space Propulsion Technology Research Institute
, Shanghai 201108, China
Search for other works by this author on:
Ming-Yu Wu (吴明雨)
;
Ming-Yu Wu (吴明雨)
(Formal analysis)
1
School of Energy and Power Engineering, Nanjing University of Science and Technology
, Nanjing 210094, China
Search for other works by this author on:
Chun Zheng (郑纯)
;
Chun Zheng (郑纯)
(Resources)
1
School of Energy and Power Engineering, Nanjing University of Science and Technology
, Nanjing 210094, China
Search for other works by this author on:
Zhi-Hua Chen (陈志华)
Zhi-Hua Chen (陈志华)
a)
(Supervision)
3
Key Laboratory of Transient Physics, Nanjing University of Science and Technology
, Nanjing 210094, China
a)Author to whom correspondence should be addressed: [email protected]
Search for other works by this author on:
a)Author to whom correspondence should be addressed: [email protected]
Physics of Fluids 37, 013616 (2025)
Article history
Received:
October 08 2024
Accepted:
December 13 2024
Citation
Xian-Jun He, Jiang-Liu Huang, Ming-Yu Wu, Chun Zheng, Zhi-Hua Chen; Deep reinforcement learning-based jet control for tandem cylinders. Physics of Fluids 1 January 2025; 37 (1): 013616. https://doi.org/10.1063/5.0242918
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
74
Views
Citing articles via
On Oreology, the fracture and flow of “milk's favorite cookie®”
Crystal E. Owens, Max R. Fan (范瑞), et al.
Physics-informed neural networks for solving Reynolds-averaged Navier–Stokes equations
Hamidreza Eivazi, Mojtaba Tahani, et al.
Chinese Academy of Science Journal Ranking System (2015–2023)
Cruz Y. Li (李雨桐), 李雨桐, et al.
Related Content
Aerodynamic interference effect and flow field mechanism of two tandem rectangular columns with a small width–thickness ratio at a high Reynolds number
Physics of Fluids (November 2024)
Aerodynamic force characteristics and flow field mechanism of multiple square cylinders in a tandem arrangement
Physics of Fluids (July 2024)
Vortex structure manipulation and drag reduction of tandem circular cylinders using a pitching splitter plate
Physics of Fluids (December 2024)
Onset of vortex shedding and hysteresis in flow over tandem sharp-edged cylinders of diverse cross sections
Physics of Fluids (January 2024)
Active control of wake-induced vibration using deep reinforcement learning
Physics of Fluids (December 2024)