A Novel Predictive Control and Its Application on Water Level System of Ship Boiler

Water level is an important index to ensure the safety and stable operation of the ship boiler. Because of the nonlinear and time lag of the water level system, normal PID control can´t obtain the satisfactory effect. So the improved neural network predictive control based on support vector machine (SVM) was presented. This method used SVM to identify the predictive model of the system, and used BP network based on simulated annealing (SA) algorithm to make receding optimization. Finally, this method was applied to the water level control system of ship boiler. The simulation results show that this method has high precision, and it´s also suit for the engineering application