Predicting Ground Vibration Caused by Blasting Operations in Sarcheshmeh Copper Mine Considering the Charge Type by Adaptive Neuro-Fuzzy Inference System (ANFIS)

摘要

Ground vibration is an inevitable effect of blasting operations. The propagated wave generated, can cause serious damage to the surrounding environment and nearby structures. The type of charge used in each blast is one of the important parameters affecting this vibration. In order to study the effect of charge type, ground vibrations from 11 blasts with two different charges (ANFO and Emolan) were recorded in Sarcheshmeh copper mine by PDAS-100 digital seismographs. Seismometers were installed in three vertical, tangential and radial directions and 46 data were obtained. Data processing was carried out with the DADISP software. In this paper, using Active Neuro-Fuzzy Inference System (ANFIS) and dividing data into ANFO and Emolan sets (charge types), the sensitivity of Peak Particle Velocity (PPV) with respect to the amount of charge weight per delay and the distance from the center of the blast site was analyzed. The correlation coefficient of the estimated and the measured data in both cases is about 0.97 and the Mean Square Error (MSE) in the network testing process for ANFO and Emolan data sets are equal to 0.52 and 0.7 respectively. The amount of PPV caused by ANFO and Emolan blasting for the critical cases was predicted by ANFIS. The critical cases have the maximum charge weights for ANFO and Emolan equal to 5200 kg and 7111 kg respectively and the nearest distance to blast site equals 740 m. The PPVs estimated by ANFIS are equal to 7.42 and 7.47 mm/s for blasting by Emolan and ANFO, respectively. This study shows that the amount of ground vibration caused by high-pressure explosives has more dependence on weight of charge used.