抄録
The wall temperature profile in the flow field of an impinging two jet array has been controlled using a neural network. The jet excitation is conducted by injection and suction through the fine slits at the nozzle exits to obtain the desired wall temperature profile. The wall temperature profile is determined uniquely by the excitation pattern; the flow field is considered as one function with the excitation pattern as an input and the wall temperature profile as an output. A neural network learns the inverse function of the flow field via on-line-learning and off-line-learning, and is then applied as a controller. As the inverse function become accurate via learning, the wall temperature profile approaches the target asymptotically.
