Sinter product rate forecasting based on T-S fuzzy model

Through the analysis of sintering process and the relationship between sintering thermal state and sinter product rate, this paper determines the key factors influencing the sinter product rate, and proposes a method of sinter product rate forecasting based on T-S fuzzy model. Based on the extraction of the characteristic parameters of the thermal state of sintering process, the input of the model is determined. Then, the antecedent and the consequent parameters of the forecasting model are identified by the fuzzy c-means (FCM) clustering algorithm and the recursive least squares method (RLS). Finally, the T-S fuzzy model for sinter product rate forecasting is obtained. The proposed forecasting method is of value through the analysis of the forecasting results. The forecasting results are also compared with the support vector machine (SVM) and the back propagation neural network (BPNN) methods. The results show that the proposed T-S fuzzy model can effectively improve the precision of the sinter product rate forecasting.