Prediction of blast-induced vibrations in limestone quarries using Support Vector Machine

Abstract

One of the major environmental concerns related to blasting operation in mining and civil engineering projects is ground vibration. The ground parameters should be taken into account by the prediction models, especially if the ground conditions have variable characters. In a blasting environment, this is usually possible by using an empirical method. However, in this study, the application of a novel artificial method, called a ‘Support Vector Machine’ (SVM), has been offered for the prediction of blast-induced ground vibration by taking into consideration the maximum charge per delay and the distance between the blast face and monitoring point. Two limestone quarries have been studied through this research. The results clearly show that the SVM can be used as a reliable predictor technique to predict the vibration level with a correlation coefficient of 0.944 which has been obtained by comparing measured and predicted values.