Rotary Kiln Intelligent Control Based on T-S Fuzzy Neural Network and Rough Sets

Abstract

Based on the idea of the knowledge reduction of the rough sets (RS) theory and the nonlinearity mapping of Takagi-Sugeno fuzzy neural network (FNN), a kind of RS-FNN intelligent control method is presented and applied in the rotary kiln sintering process due to its nonlinearities in the dynamics and the large dimensionality of the problem. Firstly, fuzzy c-means (FCM) clustering method based on a new cluster validity index is used to obtain the optimal discrete values of the continuous attributes. Then, RS theory is adopted to obtain the reductive rules using industrial history datum and corresponding FNN model has better topology configuration. Finally, the structure parameters of T-S fuzzy model are fine-tuned by a hybrid algorithm integrating the gradient descent method with least-squares estimation. The results of simulation as well as temperature control for an industrial rotary kiln furnace of iron ore oxidized pellets sintering process were performed to demonstrate the feasibility and effectiveness of the proposed scheme.