Bluff body uses deep-reinforcement-learning trained active flow control to achieve hydrodynamic stealth

摘要

We propose a novel active-flow-control strategy for bluff bodies to hide their hydrodynamic traces, i.e., strong shears and periodically shed vortices, from predators. A group of windward-suction-leeward-blowing (WSLB) actuators are adopted to control the wake of a circular cylinder submerged in a uniform flow. An array of velocity sensors is deployed in the near wake to provide feedback signals. Through the data-driven deep reinforcement learning, effective control strategies are trained for the WSLB actuation to mitigate the cylinder's hydrodynamic signatures. Only a 0.29% deficit in streamwise velocity is detected, which is a 99.5% reduction from the uncontrolled value. The same control strategy is found also to be effective when the cylinder undergoes transverse vortex-induced vibration. The findings from this study can shed some light on the design and operation of underwater structures and robotics to achieve hydrodynamic stealth.