Hwi Jin Kwon

In railway maintenance, the precision of complex mechanical–electronic subsystems such as door systems is directly related to operational safety, as small positional deviations can lead to functional failures or unsafe conditions. However, conventional training methods based on paper manuals and static diagrams provide limited support for understanding three-dimensional structures, fine adjustment criteria, and judgment processes required in actual maintenance tasks. This paper presents an augmented reality (AR) based maintenance training framework for railway vehicle door systems that supports precision-oriented and decision-based learning through real-time position feedback. The proposed framework enables users to directly manipulate virtual components within a scenario-driven workflow derived from actual maintenance procedures. During interaction, the system provides visual and numerical feedback within predefined mechanical tolerance ranges, allowing users to determine whether adjustments satisfy operational criteria. A core element is a real-time position feedback algorithm that converts user-driven component movements into numerical position values relative to reference ranges. This mechanism supports delicate adjustment tasks, such as Door Close Limit Switch (DCS) trigger alignment, by enabling users to recognize positional deviations within millimeter-level tolerances. In addition to adjustment feedback, the framework presents representative acceptable and faulty maintenance cases, allowing trainees to compare outcomes and develop practical maintenance judgment under tolerance constraints. The system was implemented on a mobile AR platform using high-fidelity three-dimensional models that preserve structural relationships, motion constraints, and interference conditions observed in real maintenance environments. User experience evaluation with 60 professional railway maintenance technicians using the System Usability Scale (SUS) and the Single Ease Question (SEQ) yielded mean scores of 73.42 and 6.25, respectively, indicating high usability and task-level clarity. These results demonstrate that the proposed framework effectively supports both precise adjustment training and maintenance decision-making beyond conventional visualization-based AR approaches.

The axle box of a railway vehicle is a critical component, and its maintenance involves complex procedures that are difficult to convey with traditional, document-based manuals. To address these challenges, augmented reality (AR)-based educational content was developed to digitize maintenance training and enhance its effectiveness. The content’s implementation was guided by a systematic storyboard, which was based on interviews with skilled staff. It also utilized specialized algorithms to improve the accuracy of mechanical measurement work and the efficiency of User Interface (UI) generation. The user experience of the developed content was comprehensively evaluated using a combination of two methods: a formative evaluation through direct observation of work performance and a post-survey administered to 40 participants. As a result of the evaluation, the mean work success rate was 62.5%, demonstrating the content’s high efficiency as a training tool. The overall mean score from the post-survey was 4.11, indicating high user satisfaction and perceived usefulness. A one-way ANOVA was performed and revealed a statistically significant difference in post-survey scores among the four age groups. The developed content was found to be more effective for younger participants. The results confirm the high potential of AR as a digital educational method for complex maintenance work.

The Brake operating unit (BOU) of a railway vehicle is one of the important systems for controlling the braking of the train. Because this system uses compressed air, it is difficult to understand and train the system. The existing education method involves learning the pneumatic flow of various control air in a 2D pneumatic circuit diagram based on a maintenance manual. However, in the actual braking system, it was difficult to learn effectively because the air flows in 3D. In order to solve these problems, the improvement of the training technique using the new 3D augmented reality (AR) was performed. In this study, to increase the learning effect of air brake flow, a technique for simultaneously displaying the pneumatic flow in 2D circuit diagram and 3D model was proposed. First, the distance ratio for simultaneous display can be determined using the proposed streamline matching variable calculation algorithm (SLMVC) that uses position and animation duration as input variables. Second, to avoid the complexity of using the 24 variables of the Particle System module in Unity, an existing universal 3D platform, a continuously emission property correction algorithm (CEPC) that can output particle objects as a streamline using only 4 properties (e.g., start lifetime, start speed, emission rate over time, start delay). As a result, the following 6 different types of BOU air pressure could be simultaneously displayed in 2D and 3D (e.g., AC, BC, SR, SBR, AS1, AS2). Therefore, maintenance staff can effectively learn complex pneumatic flow. To verify the usability of the developed content, a survey using the NASA-TLX technique was conducted targeting 60 maintenance staff. As a result of the comparison between Group A using the existing maintenance manual and Group B using the developed AR content, the perceived workload decreased by 28%. In particular, the frustration part decreased by 64% and the performance part decreased by 62%, indicating that the usability of AR content was very good.