Recent advances in applying deep reinforcement learning for flow control: Perspectives and future directions
Deep reinforcement learning (DRL) has been applied to a variety of problems during the
past decade and has provided effective control strategies in high-dimensional and non …
past decade and has provided effective control strategies in high-dimensional and non …
DRLinFluids: An open-source Python platform of coupling deep reinforcement learning and OpenFOAM
We propose an open-source Python platform for applications of deep reinforcement learning
(DRL) in fluid mechanics. DRL has been widely used in optimizing decision making in …
(DRL) in fluid mechanics. DRL has been widely used in optimizing decision making in …
[HTML][HTML] Deep reinforcement learning: A new beacon for intelligent active flow control
The ability to manipulate fluids has always been one of the focuses of scientific research and
engineering application. The rapid development of machine learning technology provides a …
engineering application. The rapid development of machine learning technology provides a …
Data-efficient deep reinforcement learning with expert demonstration for active flow control
Deep reinforcement learning (RL) is capable of identifying and modifying strategies for
active flow control. However, the classic active formulation of deep RL requires lengthy …
active flow control. However, the classic active formulation of deep RL requires lengthy …
Intelligent controller for unmanned surface vehicles by deep reinforcement learning
With the development of the applications of unmanned surface vehicles (USVs), USV
automation technologies are attracting increasing attention. In the industry, through the …
automation technologies are attracting increasing attention. In the industry, through the …
Active control of flow past an elliptic cylinder using an artificial neural network trained by deep reinforcement learning
B Wang, Q Wang, Q Zhou, Y Liu - Applied Mathematics and Mechanics, 2022 - Springer
The active control of flow past an elliptical cylinder using the deep reinforcement learning
(DRL) method is conducted. The axis ratio of the elliptical cylinder Γ varies from 1.2 to 2.0 …
(DRL) method is conducted. The axis ratio of the elliptical cylinder Γ varies from 1.2 to 2.0 …
[HTML][HTML] 人工智能控制湍流进展: 系统, 算法, 成就, 数据分析方法
吴智， 范德威， 周裕 - 力学进展, 2023 - lxjz.cstam.org.cn
湍流控制涉及流体力学和控制理论, 对航空航天, 运载工具, 风力发电等众多领域具有重要的科学
意义和应用价值. 由于湍流的复杂性, 传统控制方法在湍流控制领域面临很多瓶颈 …
意义和应用价值. 由于湍流的复杂性, 传统控制方法在湍流控制领域面临很多瓶颈 …
Optimisation of initial velocity distribution of jets for entrainment and diffusion control using deep reinforcement learning
Y Ito, Y Hayashi, K Iwano, T Katagiri - … Journal of Heat and Mass Transfer, 2024 - Elsevier
The control of the entrainment and diffusion of the heat and mass ejected along the jet flow
requires the control of fluid motion. In the present study, optimal initial velocity distributions …
requires the control of fluid motion. In the present study, optimal initial velocity distributions …
Open-loop flow control design guided by the amplitude-frequency characteristics of the reduced-order model
Unsteady separated flow is a common flow condition causing many detrimental effects in
aerospace and other fields. Open-loop control is a potential means to eliminate these …
aerospace and other fields. Open-loop control is a potential means to eliminate these …
Reinforcement-learning-based parameter optimization of a splitter plate downstream in cylinder wake with stability analyses
C Wang, P Yu, H Huang - Physical Review Fluids, 2023 - APS
In this research, we apply the single-step deep reinforcement learning (DRL) algorithm to
optimize the spatial location and length of a downstream splitter plate in order to suppress …
optimize the spatial location and length of a downstream splitter plate in order to suppress …