| The technology of circulated fluidized bed for flue gas desulfurization (CFB-FGD) has low investment cost, high desulfurization efficiency, reliable operating condition, convenient maintenance and other advantages. 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 this thesis emphasizes on the modeling based on T-S fuzzy neural network model to solve above problems.Firstly, the run course regulation of CFB-FGD is analyzed in great depth and the mechanism model is established. Then we discuss the influencing factor of sulfur dioxide removal.Secondly, we research on fuzzy neural network modeling method based on fuzzy C-means clustering (FCM) algorithm under the fuzzy neural network modeling theory. The identification method of pre-and post-incident network parameter of T-S fuzzy neural network model is discussed emphatically. And due to the selection of types of fuzzy partition c based on experience will affect the clustering results, this paper presents a new concept of the effectiveness function for determining the optimal number c of fuzzy sets into categories, that is, to improve the FCM algorithm.Lastly, according to the influencing factor of sulfur dioxide removal confirmed in the mechanism model we have had, and due to how much contribution of the factor effect on the sulfur dioxide removal, we got the input variables and set up the T-S fuzzy neural network model of the CFB-FGD system. Then the premise and consequent parameters are identified based on the improved Fuzzy C-means clustering algorithm and least-square estimator algorithm.The results of simulations and experiments show that proposed methods can build a fuzzy neural network model from the data and expert knowledge and the T-S fuzzy neural network model can simulate and predict the desulfurization efficiency perfectly which better than the mechanism model. |
PDF Full Text Request