Enhancing output in open-pit coal mining: The influence of front loading geometry on machinery functionality.

This study focuses on optimizing the productivity of excavation and haulage equipment in overburden removal operations at the Borneo Indobara site, emphasizing front-loading geometry, material flow, and equipment performance. It integrates machine learning algorithms—specifically Gradient Boosting Regression—and metaheuristic optimization methods like Particle Swarm Optimization to predict productivity, improve bucket fill factors, reduce cycle times, and optimize resource allocation. Field data from four mining fleets revealed that wider and taller front-loading geometries aligned with company standards significantly enhance productivity, with optimized configurations increasing output by up to 25% and reducing operational costs by over 10%. The research also highlights the role of IoT-enabled real-time monitoring and dynamic simulations in addressing operational inefficiencies caused by factors such as operator delays and weather conditions, supporting data-driven decision-making for sustainable and efficient open-pit mining operations.