Turbulent jet is one of the classical shear flows discussed in virtually every textbook. Its control finds many important industrial applications, including dilution jets in combustors, fuel injection of combustion engines, noise mitigation of sub- and supersonic jets for civil and military aircrafts, thrust augmenting ejectors, thrust vector control, etc. The key to control entrainment and mixing processes in a turbulent jet is, as in other shear layers, to manipulate the coherent motions. An artificial intelligence (AI) control system is firstly developed to maximize the mixing rate of a turbulent jet. This system comprises six independently operated unsteady minijet actuators, two hot-wire sensors placed in the jet, and genetic programming for the unsupervised learning of a near-optimal control law. It has been demonstrated that the AI control system can learn automatically how to optimize the operating parameters of the spatially distributed actuators and thus the turbulent jet for the targeted cost.

AI learning curve and its representative flow structures.