.png){kind=icon}
返回
Reinforcement-learning-based actuator selection method for active flow control
.png){kind=icon}
OA
AI
DOI：10.1017/jfm.2022.1043.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper addresses the issue of actuator selection for active flow control by proposing a novel method built on top of a reinforcement learning agent. Starting from a pre-trained agent using numerous actuators, the algorithm estimates the impact of a potential actuator removal on the value function, indicating the agent's performance. It is applied to two test cases, the one-dimensional Kuramoto-Sivashinsky equation and a laminar bidimensional flow around an airfoil at Re = 1000 for different angles of attack ranging from 12 degrees to 20 degrees, to demonstrate its capabilities and limits. The proposed actuator-sparsification method relies on a sequential elimination of the least relevant action components, starting from a fully developed layout. The relevancy of each component is evaluated using metrics based on the value function. Results show that, while still being limited by this intrinsic elimination paradigm (i.e. the sequential elimination), actuator patterns and obtained policies demonstrate relevant performances and allow us to draw an accurate approximation of the Pareto front of performances versus actuator budget.
Keyword:
drag reduction
instability control
machine learning
期刊
IF:
3.9
论文数:
2.0W
被引数:
9.4W
机构
引用论文
分享收藏Applying deep reinforcement learning to active flow control in weakly turbulent conditions.png)
PHYSICS OF FLUIDS
OAAI
PHYSICS OF FLUIDSIF4.3
OAAI分享收藏Active flow control using deep reinforcement learning with time delays in Markov decision process and autoregressive policy在马尔可夫决策过程和自回归策略中使用具有时滞的深度强化学习的主动流控制PHYSICS OF FLUIDSOAAI
PHYSICS OF FLUIDSIF4.3
OAAI分享收藏
查看更多内容