Abstract:
Blasting is an intrinsic component of mining cycle of operation. However, it is usually associated with negative environmental effects such as blast-induced ground vibration (BIGV) which require accurate prediction and control. Therefore in this study, Gaussian process regression (GPR) and artificial neural netwrok (ANN) have been developed for the prediction of BIGV in term of peak particle velocity (PPV) while Grey-Wolf optimization algorithm has been used to optimize the blast-design parameters for the control of BIGV in Obajana limestone quarry. The blast-design parameters such as burden (B), spacing (S), hole depth (Hd), stemming length (T) and number of hole (Nh) were obtained from the quarry. The distance from the blasting point to the measuring point (D) was measured while the charge per delay (Cd) was also determined for each of the blasting operations. The PPV was also measured for each blasting operations using the SLAM
STICK X triaxial accelerometer. These seven parameters were used as the input to the proposed GPR and ANN models while the PPV was the targeted output. All the models were implemented in MATLAB software. The performance of the proposed model was evaluated using some statistical indices such as coefficient of determination (R²), mean-squared error (MSE), and variance accounted for (VAF). The output of the GPR model was compared with the ANN model. The R2 and VAF values obtained for the GPR model is about 0.999 and 100%, respectively while that of ANN was 0.884 and 88.33%, respectively. The GPR model proved to be more accurate than the ANN model. The GWO was also developed using the ANN model for the generation of objective function. The output of the GWO revealed that if the number of holes (Nh) can be reduced by 45% and Cd by 8%, the PPV will be reduced to about 94%. Hence, the proposed models
are both suitable for prediction of PPV and optimization of blast-design parameter
