Feasibility of the indirect determination of blast-induced rock movement based on three new hybrid intelligent models

The indirect and accurate determination of blast-induced rock movement has important significance in the reduction of ore loss and dilution and in the protection of environment. The present paper aims to predict blast-induced rock movement resulting from the Husab Uranium Mine, Namibia, the Coeur Rochester Mine, USA, and the Phoenix Mine, USA, and three new hybrid models using a genetic algorithm (GA), an artificial bee colony algorithm (ABC), a cuckoo search algorithm (CS) and support vector regression (SVR), namely the GA-SVR, ABC-SVR and CS-SVR models, are proposed. Eight typical blasting parameters rock type, number of free faces, first centerline distance, hole diameter, power factor, spacing, subdrill and initial depth of monitoring were chosen as the input variables to establish the intelligent model, and horizontal blast-induced rock movement (M-H) was the output variable after conducting the available analyses of the database. Three performance metrics, including the correlation coefficient (R-2), mean square error and variance account for, were used to assess the predictive performances of the aforementioned models. Based on the obtained results, the performance metrics show that the GA-SVR, ABC-SVR and CS-SVR model can provide satisfactory performance in estimating blast-induced rock movement, and GA-SVR model can achieve better results than the GWO-SVR, CS-SVR and ANN models when considering both predictive performance and calculation speed.

Automated summary

The study aimed to predict blast-induced rock movement using different algorithms, and found that the GA-SVR, ABC-SVR, and CS-SVR models provided satisfactory predictive performance, with the GA-SVR model outperforming the GWO-SVR, CS-SVR, and ANN models in terms of both predictive performance and calculation speed.