Abstract

An artificial intelligence (AI) open-loop control system is developed to manipulate a turbulent boundary layer (TBL) over a flat plate, with a view to reducing friction drag. The system comprises six synthetic jets, two wall-wire sensors, and genetic algorithm (GA) for the unsupervised learning of optimal control law. Each of the synthetic jets through rectangular streamwise slits can be independently controlled in terms of its exit velocity, frequency and actuation phase.

Experiments are conducted at a momentum-thickness-based Reynolds number Reθ of 1450. The local drag reduction downstream of the synthetic jets may reach 48% under conventional open-loop control (COC). This local drag reduction rises to 60%, with an extended effective drag reduction area, under the AI control that finds optimized non-uniform forcing. The results point to the significant potential of AI in the control of a TBL given distributed actuation.