Developing an Advanced Soft Computational Model for Estimating Blast-Induced Ground Vibration in Nui Beo Open-pit Coal Mine (Vietnam) Using Artificial Neural Network

Abstract

The principal object of this study is blast-induced groundvibration (PPV), which is one of the dangerous side effects of blastingoperations in an open-pit mine. In this study, nine artificial neuralnetworks (ANN) models were developed to predict blast-induced PPV inNui Beo open-pit coal mine, Vietnam. Multiple linear regression and theUnited States Bureau of Mines (USBM) empirical techniques are alsoconducted to compare with nine developed ANN models. 136 blastingoperations were recorded in many years used for this study with 85% ofthe whole datasets (116 blasting events) was used for training and the rest15% of the datasets (20 blasting events) for testing. Root Mean SquareError (RMSE), Determination Coefficient (R2), and Mean Absolute Error(MAE) are used to compare and evaluate the performance of the models.The results revealed that ANN technique is more superior to othertechniques for estimating blast-induced PPV. Of the nine developed ANNmodels, the ANN 7-10-8-5-1 model with three hidden layers (ten neuronsin the first hidden layer, eight neurons in the second layers, and fiveneurons in the third hidden layer) provides the most outstandingperformance with an RMSE of 1.061, R2 of 0.980, and MAE of 0.717 ontesting datasets. Based on the obtained results, ANN technique should beapplied in preliminary engineering for estimating blast-induced PPV inopen-pit mine.