Modelling the Prioritisation of Technical Objects Using the EPN Indicator

Abstract

The objective of this article is to analyse and evaluate the effectiveness of predictive maintenance for machines performing key functions within a production structure. This article presents a methodology for determining the Equipment Priority Number (EPN), calculated based on parameters such as energy consumption, the criticality of machines in the value stream, and their impact on the continuity of the supply chain. The experimental implementation of a system for monitoring operational parameters—including current consumption, vibrations, and torque moments—enabled the prediction of potential failures and the planning of maintenance actions, which contributed to improving operational stability and reducing the risk of unplanned downtime. The obtained results confirm the effectiveness of the proposed methodology and demonstrate that a predictive maintenance system supported by the EPN indicator enables accurate prioritisation of maintenance activities in an actual production system. The findings also show that implementing the EPN algorithm allows for more precise prioritisation in highly customised production environments. Furthermore, the analysis of the collected data suggests the potential for further optimisation through the integration of data-driven diagnostics and artificial intelligence methods, which could enhance the efficiency and competitiveness of the system. This study’s conclusions provide a foundation for advancing predictive maintenance methods in industrial production.