Improving Payload Efficiency in Open-Pit Mining: An Integrated Model Using Six Sigma and Artificial Intelligence

Abstract The mining sector is a very important part of Peru's economy, but open-pit operations are still losing productivity because of problems with the way materials are loaded. This study suggests a mixed model that combines Six Sigma methods with Artificial Intelligence (AI) to make loading the payload more efficient in a copper mining company. The research seeks to diminish operational variability, enhance payload compliance across truck models, and elevate equipment reliability through a systematic DMAIC and PDCA methodology. The methodology consists of calibration protocols, maintenance cycles, operator training, and AI-driven capacity analysis to assess performance through Pp and Ppk indicators. A case study conducted in a Peruvian mining company demonstrated substantial enhancements: loading efficiency achieved 100% across all truck models, null reading rates diminished by up to 13.82%, and equipment availability rose by 7%. Also, Six Sigma capacity indices showed that the Ppk for the CAT 797F model went up by 94% and that it went up by more than 50% for other models. These results show that the proposed model works to improve operational efficiency and can be used on a larger scale in the mining industry.