A study of CMAC neural network generalized predictive control for generating unit

摘要

Large thermal power unit is complex, nonlinear, big lag system. Using the traditional control method is difficult to get the best running effect. And in neural network modeling based on multivariable generalized predictive control strategy, has wide range, strong robustness etc, and can effectively make up for the deficiency. Based on the Cerebellar Model Articulation Controller neural network modeling, after the online rolling optimization and feedback correction, realize the predictive control. The simulation results show its validity.