A Model Coupling CFD and DRL: Investigation on Wave Dissipation by Actively Controlled Flat Plate

In order to protect structures along the offshore and off coast, breakwaters are commonly applied reduce influence of waves. Flat plate breakwater is studied frequently due its great performance near water surface, however, traditional passive methods such as fixed floating flat usually fail give full play effective wave dissipation when encountering variable unknown incoming Therefore, this paper develops an interdisciplinary model coupling computational fluid dynamics (CFD) deep reinforcement learning (DRL) study a submerged movable against regular An in-house numerical tank (NWT) built simulate fluid-structure interaction between The domain in NWT regarded environment while agent. addition, strategy learned by artificial neural network (ANN) through continuous wave-plate interaction. It excited find that able learn control strategies automatically exhibits good adaptability changes environment.