Fuzzy logic model-based predictive control of aircraft dynamics using ANFIS

In this paper, a fuzzy model-based predictive control strategy for dynamical systems is presented. The objective is to stabilize the wing-rock behavior of an aircraft by the control action obtained by an optimization procedure in which a performance index representing the deviation error between the setpoint and the predicted output from the model is minimized. Due to its capability of characterizing the dynamic functional relationships and its feedback processing structure, the hybrid scheme known as the adaptive network-based fuzzy inference is employed as an adaptive predictor for future state values. This paper discusses the use of differential evolution to find a better optimization solution at each time instant. Simulation results show that the predictive control algorithm is very effective for compensating unpredictable changes in the aircraft dynamics over a wide range of flight conditions and other uncertainties.