A DATA-DRIVEN APPROACH TO BLASTING EFFICIENCY OPTIMIZATION IN OPENCAST MINES

Abstract

Blasting operations in opencast mines significantly influence downstream activities such as loading, hauling, and crushing. Inefficient blast designs can lead to poor fragmentation, safety concerns, and increased operational costs. This study presents a datadriven approach to optimize blasting parameters in opencast mining by analyzing historical blast performance data, rock mass characteristics, and explosive properties. Using statistical modeling and machine learning techniques, the study identifies key parameter combinations that yield optimal fragmentation and cost-efficiency. Field validation indicates that data-informed optimization can reduce secondary breakage, minimize environmental impact, and enhance overall mine productivity. The approach offers a scalable framework for mine operators to systematically improve blast outcomes based on site-specific data