Prediction and minimization of blast-induced flyrock using gene expression programming and cuckoo optimization algorithm

Abstract

Flyrock is one of the most dangerous adverse environmental effects of the blast, which can cause serious damage to the nearby buildings and people and even lead to the death in some cases. Therefore, it is very essential to correctly predict the flyrock distance to control and reduce the flyrock and also to determine the safety area. Due to the multiplicity of the parameters influencing the flyrock and the complexity of interacting parameters, the performance of empirical equations for predicting the flyrock distance is not satisfied and they cannot guaranty safety for the surrounding environment. In this research, in the first step, the predictor equation for the blast-induced flyrock was obtained using the gene expression programming. To achieve this goal, the data from 318 blast blocks in the Sungun copper mine was recorded and the amount of flyrock resulting from each blast was accurately measured. Burden, spacing, stemming, charge length and powder factor were used as the input parameters in gene expression programming (GEP) model. Among the gathered datasets, 268 datasets were intended for the model training and 50 datasets for the model testing. Then, the obtained equation from GEP was used as cost function for minimizing flyrock by cuckoo optimization algorithm. For this purpose, five strategies were defined and some optimal blast designs were provided for each strategy. The results showed that the gene expression programming model with the correlation coefficient of 0.91 and the root mean square error of 5.85 m has a good performance in predicting the blast-induced flyrock using the blast design parameters. Also, the maximum flyrock value of blast designs provided by the cuckoo algorithm was reduced by 43.6% relative to the maximum flyrock value of the initial blast designs. Input parameters sensitivity analysis showed that the powder factor is the most effective parameter on the flyrock phenomenon.