A Framework for Enablement of Augmented Reality in Railway Maintenance
Railway maintenance relies on effective assessment of asset health to ensure safety and reliability. It requires appropriate technologies, methodologies, and tools for monitoring the condition of railway assets. These technologies and tools often utilize advanced sensor technology for data acquisition, distributed computing for data processing, enhanced analytics for knowledge extraction, and visualization technologies for data representation. While significant progress has been made in data acquisition, processing, and analytics, data visualization has not received sufficient attention. In parallel, the emerging Industry 5.0 concept emphasizes human-centricity, resilience, and sustainability in industrial systems, highlighting the need for enhanced human-system interaction (HSI) in maintenance processes. HSI can be enhanced by using perception-enhancing technology such as Augmented Reality (AR). However, the effective integration of AR into railway maintenance requires structured frameworks that address the challenges of task workflow, interaction, and information presentation. Hence, the purpose of this paper is to propose a framework for enabling AR-based assistance in railway maintenance. Following a Design Science Research (DSR) methodology, the framework defines functional elements and information flows to support the execution of inspection tasks and is realized through an AR-based system that integrates procedural guidance, flexible workflow navigation, multimodal interaction, contextual information access, and automated inspection log generation. A controlled user study compares the AR-assisted inspection approach with a traditional inspection method using standardized usability measures. The results indicate that both approaches scored within the marginal usability range. These findings indicate the feasibility of AR-based assistance as a human-centric complement to existing railway maintenance practices, while motivating further refinement and evaluation in operational settings.