Impact factor improvement and maintenance schedule optimisation of mining shovels by remaining useful life and linear programming

The mining industry is slow in adopting digitisation compared to other industry segments. The companies are coping with operation cost pressures due to demand fluctuations and increased operations costs. The equipment maintenance costs aggregate around 10% to 30% of the direct mining operations costs due to different operating conditions. This article leverages the Cox regression machine learning (ML) model to determine the survival days of shovels. Subsequently, to increase the availability, a mathematical model is formulated to optimise the maintenance schedules of shovels to increase their availability. Finally, decision optimisation (DO) ILOG CPLEX and remaining useful life (RUL) is deployed to combine maintenance schedules of preventive maintenance (PM) and predictive maintenance (PdM). This ML led innovative model optimises maintenance schedule drives the data-driven actions to demonstrate the metrics of overall equipment effectiveness (OEE), overall throughput effectiveness (OTE) and impact factor (IF) computation. furthermore, the IF improvement is demonstrated through a case study of mining shovels. The IF improvement is also aligned with the productivity improvement of equipment as per the United Nations (UN) sustainable development goals (SDGs).