Modeling method of carbon efficiency in iron ore sintering process

Iron ore sintering is one of the most energy-consuming processes in steelmaking. The main source of energy for it is the combustion of carbon. To find ways of reducing the energy consumption, it is necessary to predict the carbon efficiency. In this study, a modeling method that is based on the characteristics of the sintering process was developed to do that. It employs the comprehensive carbon ratio (CCR) as a measure of carbon efficiency. The method uses a back-propagation neural network (BPNN) to build a predictive model that consists of two submodels, the state-parameters submodel and the CCR submodel. An mechanism, partial correlation coefficient (PCC), and Spearman's rank correlation coefficient (SRCC) analyses of process data are used to determine the most appropriate inputs for the two submodels. Finally, verification of the modeling method based on actual process data shows the efficient of the model in predicting carbon efficiency of iron ore sintering.