Optimization of prediction of flyrock using linear multivariate regression (LMR) and gene expression programming (GEP)—Topal Novin mine, Iran

Blast-induced flyrock is one of the most dangerous events that can be harmful to the mine personnel and equipment. Therefore, accurate prediction of this phenomenon would be essential for blasting operations. In this paper, a mathematical model was developed to predict flyrock using a statistical method. In the first step, linear multivariate regression (LMR) was used to establish the mathematical flyrock model, and then in the second step, gene expression programming (GEP) was employed to enhance statistical model appropriateness. Input parameters were considered to be burden, hole spacing, length of stemming, and powder factor, while output parameter was set to be flyrock. The required data were collected from Topal Novin limestone mine, Iran. According to the obtained results, it was observed that the performance of the developed GEP predictor model is much better than that of the LMR model. For efficiency comparison of the presented models, R square and RMSE were computed 0.86 and 13.26 and 0.91 for LMR and 10.81 for GEP, which shows superiority of the GEP technique over LMR method.