Adaptive neuro-fuzzy control of dynamical systems

In this paper, the an adaptive neuro-fuzzy control that combines the features of fuzzy sets and neural networks have been implemented and applied for the control of SISO and MIMO systems. Duffing forced oscillation system was considered as the SISO plant while the Twin Rotor laboratory set up that closely mimics helicopter dynamics was considered as the MIMO plant. The tracking performance of the controller has been demonstrated for time varying inputs. Robust performance of the controller was demonstrated by applying a pulse disturbance when the controlled plant had reached a steady state. Real time implementation of the controller has been demonstrated on the Twin Rotor system.