Generalized Predictive Control Algorithm Applied to Thermal Power Units Based on Fuzzy Neural Network

Abstract

Mordern electric power process is a typical complex industy course which is multivariable nonlinear,long-time delay ,time-variant and difficult to be established accurate model. So it is hard to get optimum effect when system operating with conventional control strategy.A FNN network with dynamic feature has been used to identify the coordinated control system for establishing a predictive model in Generalized predictive control strategy, and a predictive control has been achieved with online rolling optimization and real-time feedback revision in the paper. This method was compared with conventional PID control method,the simulation result shows that this method can adapt the object change characteristic.This method has a good control effect.