The Study On Water Level Control Of Marine Boiler Based On Fuzzy Neural Network

On the ship controlling boiler water level within the permissible range is great significance for safe and economic operation of the boiler as well as vessel.But the boiler water level controlling is a nonlinear,multivariable complex control process,and now the boiler develops to the large evaporation and relatively small steam drum volume direction,so the traditional PID control can not meet the control requirements well.Take tanker auxiliary boiler level as the research object,and based on the development of intelligent control,apply fuzzy logic control and neural network to the boiler water level control system of oil tanker auxiliary boiler to solve problems and difficulties in the traditional PID control system in tanker auxiliary boiler water level.Fuzzy neural network is a kind of control algorithm which does not need to establish accurate mathematical model and has strong robustness.It is suitable for boiler water level control system with nonlinear characteristics with large inertia and large time delay.In this paper,firstly,build the mathematic model according to the dynamic change of boiler water level.On the basis of certain simplification,the dynamic equation of boiler water level is obtained by studying the law of conservation of boiler water level according to the law of conservation of energy and the law of conservation of mass.Based on this,the boiler water level model is simplified according to the actual operation condition of the boiler,ignoring the secondary factors that affect the boiler water level,obtain and the transfer function of the boiler drum water level.Based on the obtained dynamic equation and transfer function,design the boiler water level controller,and introduce the traditional control mode and strategy briefly.Then this paper introduces the fuzzy control theory and the basic characteristics and principles of the neural network theory.On this basis,design the fuzzy-PID controller and the fuzzy neural network controller.The effect of the new controller is tested by simulation,and the control effect is compared with the traditional PID controller.The results show that the new controller solves the shortcomings of conventional PID control and has strong adaptability and robustness.The new control algorithm in this paper obtains the ideal control effect.