Guaranteed tracking and regulatory performance of nonlinear dynamic systems using fuzzy neural networks

A new technique for the design of stable tracking and regulatory control sy stems for nonlinear systems using fuzzy neural networks is described. A cla ss of nonlinear systems is considered where a few of the input variables ca ll be manipulated (controlled) while the rest are considered as disturbance s. System dynamics are modelled using a fuzzy neural network where each fuz zy operating region is associated with a series-parallel linear model. Two new control strategies are proposed using the LyaFunov synthesis approach. In one, a disturbance invariant control scheme is proposed where the sensit ivity of the system response with respect to the control variable is estima ted using a fuzzy neural model. In the other strategy a model predictive sc heme is developed in which disturbances are predicted online and the fuzzy neural model is used to predict the control action for a desired setpoint. The proposed controllers have been implemented for a nonlinear pH reactor t hrough simulation. In a pH control problem the acid and buffer flow rate ar e considered to be disturbances, while the base flow rate is controlled to maintain a constant pH. Simulation results show that the proposed scheme pr ovides guaranteed tracking and regulatory performance.