Toward Low-Cost Digital Twins for Urban Transportation Systems

This study introduces an advanced Digital Twin (DT) framework for trams, transforming public transport maintenance through intelligent analytics and real-time data monitoring. Our approach includes developing the DT concept, identifying essential tram components for monitoring, such as the drive train, transmission, electric motor, inverter, suspension, and brakes, and determining the appropriate methods and metrics for their Predictive Maintenance (PM). Employing low-cost sensors coupled with advanced analytics, our system efficiently gathers accurate data and feeds it into PM models. A set of comprehensive rules is formulated to assess the tram’s maintenance status, enabling early detection of potential issues. Significantly, this system was successfully implemented on a real tram, contributing to the early detection and prevention of a major transmission failure. Beyond trams, our approach extends to assessing infrastructure like railway conditions and plays a significant role in enhancing passenger satisfaction. This application not only demonstrates the system’s practical efficacy but also underscores its role in enhancing the safety and reliability of urban tram services.