Soft sensor for apparent degree of calcination in NSP cement production line

Abstract

Because it is difficult to measure the on-line apparent degree of calcination in New Suspension Preheater Dry Process (NSP) cement production line, a soft sensor model is established by using soft sensor technique and Least Squares Support Vector Machine (LS-SVM) with RBF kernel. The furnace temperature and pressure of the calciner, the outlet temperature and pressure of the calciner, the temperature of the tertiary air and the lay off quantity of cement raw are used as the inputs of soft sensor model. The apparent degree of calcination is the output. A realization scheme programmed by VC ++ based on DCS and OPC technique is presented. The results of the experiment show that the prediction accuracy of this soft sensor model for the apparent degree of calcination in NSP cement production line based on LS-SVM can reach 98.8%. So the on-line measurement of the apparent degree of calcination in NSP cement production line can be realized by this soft sensor model.