Abstract

In today’s highly competitive global manufacturing environments, the continuous and reliable operation of industrial facilities is critically important. Electrical panels, which form the foundation of the production infrastructure by integrating energy distribution, control, and protection functions within a single structure, hold a special significance in maintenance processes. However, maintenance and troubleshooting activities performed on these panels are largely carried out using conventional methods that rely heavily on outdated printed documentation, static labeling, and experience-based approaches. This traditional approach leads to unnecessary time loss during repair and maintenance processes, occupational safety risks resulting from misdiagnosis, and protracted orientation costs for new personnel. This study aims to directly address core issues such as the time loss, high risk of error, and increased cognitive load caused by conventional maintenance procedures. The primary goal is to enhance the efficiency, accuracy, and operational reliability of both planned and unplanned maintenance activities conducted in factory settings. To this end, a mobile device-based maintenance assistant, integrated with Augmented Reality (AR), has been designed and developed. The developed system identifies electrical equipment on the panel in real-time, visually presenting essential technical specifications and instantaneous electrical measurements of the components to the technician. This approach is intended to simplify maintenance processes, shorten the Mean Time to Repair (MTTR), and reduce the margin for operational error. Scenario-based simulations quantify this gain by showing that intermediate information-access steps can be reduced from five to three (~40%); assuming that information search and interpretation account for 40-60% of MTTR, this corresponds to a projected MTTR reduction of approximately 16-24%. In addition, prior AR worker-assistance and AR procedural guidance studies report time savings on the order of ~25% and error-rate reductions reaching ~68.6%, supporting the feasibility of measurable reductions in operational error rate with the proposed approach [1].

Keywords:Augmented reality-assisted maintenance; Hall-effect current sensors; Sensor fusion-based tracking; Mobile maintenance systems; Human-machine interaction