# Active Control of Flow over Rotating Cylinder by Multiple Jets using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2307.12083 · HTML: https://mlsanity.com/paper/2307.12083/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 51 references that are in the map.
- First posted on arXiv 22 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Continuous Deep Q-Learning with Model-based Acceleration](https://mlsanity.com/paper/1603.00748/) (2016)
- [Efficient collective swimming by harnessing vortices through deep reinforcement learning](https://mlsanity.com/paper/1802.02674/) (2018)
- [Direct shape optimization through deep reinforcement learning](https://mlsanity.com/paper/1908.09885/) (2019)
- [Single-step deep reinforcement learning for open-loop control of laminar and turbulent flows](https://mlsanity.com/paper/2006.02979/) (2020)

## Built on by (most cited first, 1 of 1)

- [Hypersonic Flow Control: Generalized Deep Reinforcement Learning for Hypersonic Intake Unstart Control under Uncertainty](https://mlsanity.com/paper/2602.02531/) (2026)

## Abstract (arXiv)

The real power of artificial intelligence appears in reinforcement learning, which is computationally and physically more sophisticated due to its dynamic nature. Rotation and injection are some of the proven ways in active flow control for drag reduction on blunt bodies. In this paper, rotation will be added to the cylinder alongside the deep reinforcement learning (DRL) algorithm, which uses multiple controlled jets to reach the maximum possible drag suppression. Characteristics of the DRL code, including controlling parameters, their limitations, and optimization of the DRL network for use with rotation will be presented. This work will focus on optimizing the number and positions of the jets, the sensors location, and the maximum allowed flow rate to jets in the form of the maximum allowed flow rate of each actuation and the total number of them per episode. It is found that combining the rotation and DRL is promising since it suppresses the vortex shedding, stabilizes the Karman vortex street, and reduces the drag coefficient by up to 49.75%. Also, it will be shown that having more sensors at more locations is not always a good choice and the sensor number and location should be determined based on the need of the user and corresponding configuration. Also, allowing the agent to have access to higher flow rates, mostly reduces the performance, except when the cylinder rotates. In all cases, the agent can keep the lift coefficient at a value near zero, or stabilize it at a smaller number.