Nonlinear multivariable supervisory predictive control

The process of combined cycle power plant(CCPP) is characterized by nonlinearity and uncertainty. While model predictive control has been widely used in CCPP, incorporating of constraints is a major problem. Considering a supervisory control structure, this work presents nonlinear constraint predictive control by introducing of neuro-fuzzy networks(NFNs) representing a nonlinear dynamical process. Power and velocity control of gas turbine in CCPP is presented to illustrate the implementation and the performance of the proposed method. Comparative control studies suggest an improvement over conventional controller.