Identification and control of aircraft dynamics using radial basis function networks

The emergence of neural networks as a promising tool for approximating complex system input-output mappings has generated a great deal of interest in the area of modeling, identification and control of nonlinear dynamical systems. One specific research area that would tremendously benefit from this approach is the area of identification and control of high performance aircraft, especially at high angles of attack. Under those flight conditions, the control task becomes extremely difficult due to added design complexity and hard nonlinearities characterizing the system. In this paper, the authors investigate one type of neural networks, namely radial basis function (RBF) networks, and apply them to the identification and control problems of an aircraft system. The RBF network is used as an on-line approximator of the aircraft pitch dynamics, combined with a nonlinear control law to improve the closed-loop system performance. The results are illustrated through simulations using a nonlinear model of the F-16 aircraft pitch dynamics