Research Of Modeling And Control In A Thermal Power Plant Desulfurization System Based On Fuzzy Neural Network

SO₂ emissions from a thermal power plant is serious harm to the environment, so it becomes an important issue in a thermal power plant about the reasonable control of sulfur dioxide emissions and improving the efficiency of desulfurization. The desulfurization process has many characteristics, such as multi variables, nonlinear, uncertainty and delay in a thermal power plant. So it is difficult to model and control.The desulfurization process of intelligent modeling and intelligent control method of research will has important theoretical and practical significance to improve the efficiency of desulfurization systtem and control of the desulfurization process and ensure smooth and efficient operation of the system. In the limestone / gypsum wet flue gas desulfurization system, the slurry PH value has a great influence on the desulfurization efficiency, so the thesis analyzes and studies the desulfurization efficiency modeling and slurry pH control. There are many factors affecting the desulfurization efficiency, so the thesis put T-S fuzzy neural network into the soft sensor modeling applied to the modeling of the desulfurization efficiency.The simulation results show that the validity of the model and the data analysis shows that the model has good performance. Due to its large inertia, delay and nonlinear characteristics in slurry pH control process, the thesis chooses the Mamdani fuzzy neural network to establish the controller and uses to control the pH value of the slurry. In order to further improve the ability of the network in the control and achieve a better control effect, so the thesis proposes fuzzy neural network of DEBP algorithm used for the optimization of the pH value of the desulfurization system controller. The simulation results show fuzzy neural network based on the algorithm has more advantages in the desulfurization control system.The thesis has certain reference revalue and engineering significance to engineering application based on fuzzy neural network.