Modeling of subsonic cavity flows by neural networks

Influencing the behavior of a flow field is a core issue as its improvement can yield significant increase of the efficiency and performance of fluidic systems. On the other hand, the tools of classical control systems theory are not directly applicable to processes displaying spatial continuity as in fluid flows. The cavity flow is a good example of this and a recent research focus in aerospace science is its modeling and control. The objective is to develop a finite dimensional representative model for the system with appropriately defined inputs and outputs. Towards the goal of reconstructing the pressure fluctuations measured at the cavity floor, this paper demonstrates that given some history of inputs and outputs, a neural network based feedforward model can be developed such that the response of the neural network matches the measured response. The advantages of using such a model are the representational simplicity of the model, structural flexibility to enable controller design and the ability to store information in an interconnected structure.