MODEL TO IMPROVE THE AVAILABILITY OF SUBWAY LOADERS IN A MINING COMPANY BY APPLYING RCM METHODOLOGY WITH INDUSTRY 4.0

Availability is a widely used and important indicator of machine status. To improve availability, it is crucial to reduce breakdowns and have adequate maintenance plans. In addition, current maintenance needs demand the ability to predict failures to keep the machines in good condition. This study evaluates the subway loaders of a company in the mining sector. This sector is a fundamental part of the growth of the world economy, especially in Latin American countries such as Peru. A crucial part of the growth of the sector is the optimal operation of heavy machines since productivity depends mainly on their good performance. In that sense, this study proposes a predictive maintenance plan for subway loaders based on Industry 4.0 (IoT and Machine Learning) with the RCM methodology, additionally, it is planned to apply the EOQ method to ensure that the loader spare parts are available and does not extend maintenance times. To validate the effectiveness of the model, the simulation by Weibull statistical distribution and Arena software are suggested, since they are adequate to treat data and variables corresponding to maintenance plans and inventory management, respectively. With this, it is expected to increase availability by 8% to reach the industry-recommended 85%.