Search

During the last two decades, industrial applications of augmented reality (AR) have been incorporated in sectors such as automotive or aeronautics in tasks including manufacturing, maintenance, and assembly. However, AR’s potential has yet to be demonstrated in the railway sector due to its complexity and difficulties in automating tasks. This work aims to present an AR system based on HoloLens 2 to assist the assembly process of insulation panels in the railway sector significantly decreasing the time required to perform the assembly. Along with the technical description of the system, an exhaustive validation process is provided where the assembly using the developed system is compared to the traditional assembly method as used by a company that has facilitated a case study. The results obtained show that the system presented outperforms the traditional solution by 78% in the time spent in the localization subtask, which means a 47% decrease in the global assembly time. Additionally, it decreases the number of errors in 88% of the cases, obtaining a more precise and almost error-free assembly process. Finally, it is also proven that using AR removes the dependence on users’ prior knowledge of the system to facilitate assembly.