Ball mill coal pulverized system is a multivariable coupled nonlinear time-varying system with long time delay which is extensively applied in coal fired power plants and is difficult to be controlled by conventional PID regulating algorithm. In this paper it suggests a Fuzzy Neural Network Controller and its initial value is optimized by the modified PSO, adjusted on-line by use of BP algorithm. It has been simulated and the simulating results show the Fuzzy Neural Controller has better control characteristics. So this controller has better successful availability for engineering implementation. |