Neural Network-Based Intelligent Integrated Modeling For The CFB-FGD Processes

The technology of circulated fluidized bed for flue gas desulfurization(CFB-FGD) is based on the theory of circulated fluidizing bed. It augments the material concentration and lengthens the reacting time by recycling the reaction product and desulfurizer, thus increase the desulfurizer utilization ratio and the desulfurization efficiency. The CFB-FGD technology is suitable for the current condition of China because of its low investment cost, high desulfurization efficiency, reliable operating condition, convenient maintenance and other advantages.The coal-fired electricity accounts for dominant position of the total power generation, about 80%. Combustion of abundant coal for power generation comes into being the sulfur dioxide excessive discharge and serious environment pollution. How to reduce pollutant emission is one of important issues we faced to be solved urgently in our country. For excogitating of control technology about CFB-FGD which has the trait of technique viable, high standard, low project alteration and working period, reliable investment and self-determination knowledge property right, the thesis based on "Research and development of the CFB-FGD automation control technology", which is one of key subjects in "tenth five-year plan", set up the CFB-FGD mechanism model. Because of the CFB-FGD is a nonlinear, multi-variable and complicate system; its mechanism has not been completely mastered even now. The mathematics model doesn't satisfy the actual need, so the zoom out design and the operative process guidance is mainly based on the experience. The establishment and maintenance of the mechanism model of the CFB-FGD is complicated, and numerous iterations have been made when calculating the desulfurization efficiency. This thesis emphasizes on the intelligent integrated modeling based on neural network to solve above problems.Firstly, the integration of NN and conventional modeling is discussed emphatically under the intelligent integrated modeling theory. The input weighted feed-forward NN integration modeling is proposed, which has not only high accuracy and fast convergence but also adaptability to the industrial process with strong non-linearity, especially many input variables.