Assessment of Maximum Explosive Charge Used Per Delay in Surface Mines

The present paper mainly with deals the prediction of safe charge of explosive used per delay (Qmax) using artificial neural network (ANN) incorporating peak particle velocity (PPV) and distance between blast face to monitoring point (D). 120 blast vibration data sets were monitored at different vulnerable and strategic locations in and around a major coal producing opencast coal mines in India. 100 blast vibrations records were used for the training of the ANN model vis-à-vis to determine site constants of various conventional vibration predictors. Rest 20 new randomly selected data sets were used to compare the ANN prediction results with widely used conventional predictors. Results were compared based on coefficient of determination (R2) between measured and predicted values of Qmax. It was found that coefficient of determination between measured and predicted Qmax by ANN was 0.894, whereas it was ranging from 0.023 to 0.417 by different conventional predictor equations. Key-Words: Safe explosive charge used per delay; peak particle velocity; distance between blast face to monitoring point; conventional vibration predictors; artificial neural network