XG Boost Algorithm to Simultaneous Prediction of Rock Fragmentation and Induced Ground Vibration Using Unique Blast Data

The two most frequently heard terms in the mining industry are safety and production. These put a lot of pressure on blasting engineers crew to give more while consuming less. key achieving optimum results is sophisticated bench analysis, which must be combined with design blast parameters for good fragmentation safe ground vibration. Thus, unique solution forecasting both reduced vibration using rock mass joint angle will aid operations cost savings. To arrive at proper understanding solution, 152 blasts were carried out various mines by adjusting concerning measured angle. XG Boost, K-Nearest Neighbor, Random Forest algorithms evaluated, Boost outputs shown superior Mean Absolute Percentage Error (MAPE), Root Squared (RMSE), Co-efficient determination (R2) values. Using decision-tree-based ensemble Machine Learning algorithm that uses gradient-boosting framework simultaneous formula was developed predict same set parameters.