论文标题
强化学习控制策略以减少皮肤摩擦阻力的控制策略，以完全发达的通道流动
Reinforcement Learning of Control Strategies for Reducing Skin Friction Drag in a Fully Developed Channel Flow
论文作者
论文摘要
加强学习应用于控制策略的发展，以减少在较低的雷诺数下完全发达的湍流通道流中的皮肤摩擦阻力。 Motivated by the so-called opposition control (Choi et al. 1993), in which a control input is applied so as to cancel the wall-normal velocity fluctuation on a detection plane at a certain distance from the wall, we consider wall blowing and suction as a control input, and its spatial distribution is determined by the instantaneous streamwise and wall-normal velocity fluctuations at the distance of 15 wall units above the wall.深度神经网络用于表达感应信息与控制输入之间的复杂关系，并经过训练，以最大程度地提高预期的长期奖励，即减少阻力。当仅测量壁正常速度波动并使用线性网络时，目前的框架成功地重现了先前研究中报道的反对派控制的最佳线性重量（Chung＆Talha 2011）。相比之下，当使用非线性网络时，基于瞬时流向和壁正常速度波动的更复杂的控制策略将获得。具体而言，所获得的控制策略突然在强壁吹和吸入之间切换，以使高速流体向下倾斜朝壁和低速流体的上升流向墙壁上升。获得的控制策略导致降低率高达37％，高于常规反对派控制在同一雷诺数上获得的23％。目前的结果表明，强化学习可能是通过大量试验通过系统学习制定有效控制策略的新框架。
Reinforcement learning is applied to the development of control strategies in order to reduce skin friction drag in a fully developed turbulent channel flow at a low Reynolds number. Motivated by the so-called opposition control (Choi et al. 1993), in which a control input is applied so as to cancel the wall-normal velocity fluctuation on a detection plane at a certain distance from the wall, we consider wall blowing and suction as a control input, and its spatial distribution is determined by the instantaneous streamwise and wall-normal velocity fluctuations at the distance of 15 wall units above the wall. Deep neural network is used to express the complex relationship between the sensing information and the control input, and it is trained so as to maximize the expected long-term reward, i.e., drag reduction. When only the wall-normal velocity fluctuation is measured and a linear network is used, the present framework successfully reproduces the optimal linear weight for the opposition control reported in the previous study (Chung & Talha 2011). In contrast, when a non-linear network is used, more complex control strategies based on the instantaneous streamwise and wall-normal velocity fluctuations are obtained. Specifically, the obtained control strategies abruptly switch between strong wall blowing and suction for downwelling of a high-speed fluid toward the wall and upwelling of a low-speed fluid away from the wall, respectively. The obtained control policies lead to drag reduction rates as high as 37 %, which is higher than 23 % achieved by the conventional opposition control at the same Reynolds number. The present results indicate that reinforcement learning can be a novel framework for the development of effective control strategies through systematic learning based on a large number of trials.
