Two-degree-of-freedom control using recurrent fuzzy neural networks for a class of nonlinear discrete-time time-delay systems

This paper presents a novel two-degrees-of-freedom control for a class of nonlinear discrete-time time-delay systems. The controller combines a TSK-type recurrent fuzzy neural network (TRFNN) adaptive inverse model feedforward controller with a stochastic adaptive model reference predictive controller (SAMRPC). The former is used to provide command-feedforward control and to improve transient performance, while the SAMRPC controller is employed to eliminate any error caused by disturbances or uncertainties. Numerical simulations for controlling a highly nonlinear process reveal disturbance rejection and set-point tracking performance of the proposed control method. The results clearly indicate effectiveness and merit of the proposed method.