Semi-autogenous mill power model development using gene expression programming

Abstract

Predicting the performance of the semi-autogenous (SAG) mill is necessary for the best circuit design which is possible by suitable modeling and simulation. Numerous models of the SAG mill are studied in the literature, but the majority of them do not evaluate the predicted model for full-scale mill performance. Mill powers of the semi-autogenous mill have an effective influence on the mill performance. In this regard, a new predictive model based on gene expression programming (GEP) was developed to predict the mill power of the SAG mill. To achieve this purpose, a total number of 186 full-scale SAG mill works were investigated and the most effective parameters on SAG mill power, i.e., feed moisture, mass flowrate, mill load cell weight, SAG mill solid percentage, inlet and outlet water to the SAG mill and work index were measured and utilized to develop the GEP model. In order to determine the relationship between the input and output parameters, the GEP model was developed and the results were compared with non-linear multiple regression (NLMR) method. The results show the capability of the GEP model in predicting the mill power. It shows that the mill power is more sensitive to mass flowrate and work index than other input parameters.