Toward fully stabilized flow control using deep reinforcement learning
Abstract
This study enhances the performance of flow control across various synthetic jet configurations by improving deep reinforcement learning techniques. The training results based on the foundational deep reinforcement learning framework indicate that as the Reynolds number increases, the effectiveness of synthetic jet control becomes increasingly sensitive to the position of the jet. When synthetic jets are positioned near the flow separation region, the control strategy consistently exhibits excellent performance. However, when synthetic jets are located farther from the separation region, the flow control performance diminishes, and the consumption of external energy increases. By enhancing dynamic state features and reshaping the reward function, we significantly improve control performance across various Reynolds numbers and synthetic jet positions. With the optimized framework, we achieve significant drag reduction effects ranging from 8% to 34% within the Reynolds number range of 100 to 400. The flow control strategy is capable of simultaneously achieving multiple control objectives, including reducing drag, suppressing lift, eliminating vortex shedding, and decreasing energy consumption. These findings highlight the potential of optimizing deep reinforcement learning frameworks to achieve more adaptive flow control strategies for various flow scenarios.
Versions
Related
- State-augmented deep reinforcement learning for active flow control around an elliptical cylinder
- Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction
- Quantum control of solid state qubits via Reinforcement Learning
- Optimizing synthetic jet placement for control stability in increasing Reynolds number flows based on deep reinforcement learning
- Reinforcement-learning control of turbulence transition in the modified Hasegawa-Wakatani system
BibTeX
@misc{jia2026toward,
title = {{Toward fully stabilized flow control using deep reinforcement learning}},
author = {Wang Jia and Hang Xu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35676},
eprint = {2610.35676},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35676},
}
RIS
TY - UNPB
TI - Toward fully stabilized flow control using deep reinforcement learning
AU - Wang Jia
AU - Hang Xu
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35676
UR - https://arxiv.org/abs/2610.35676
AB - This study enhances the performance of flow control across various synthetic jet configurations by improving deep reinforcement learning techniques. The training results based on the foundational deep reinforcement learning framework indicate that as the Reynolds number increases, the effectiveness of synthetic jet control becomes increasingly sensitive to the position of the jet. When synthetic jets are positioned near the flow separation region, the control strategy consistently exhibits excellent performance. However, when synthetic jets are located farther from the separation region, the flow control performance diminishes, and the consumption of external energy increases. By enhancing dynamic state features and reshaping the reward function, we significantly improve control performance across various Reynolds numbers and synthetic jet positions. With the optimized framework, we achieve significant drag reduction effects ranging from 8% to 34% within the Reynolds number range of 100 to 400. The flow control strategy is capable of simultaneously achieving multiple control objectives, including reducing drag, suppressing lift, eliminating vortex shedding, and decreasing energy consumption. These findings highlight the potential of optimizing deep reinforcement learning frameworks to achieve more adaptive flow control strategies for various flow scenarios.
ER -