Defective assets on the rail track represent a significant cause of hold ups on most rail and tram networks, causing one third of delays and sometimes rail trams’ suspensions, thus impacting citizens’ expectations and the normal operation of cities. Therefore, the early detection of symptoms associated with possible rail track wear is fundamental in order to resolve such problems as soon as possible, and even completely prevent them if possible.

The predictive maintenance application will monitor the rail track status and profile in real-time, enabling the identification of changes in equipment behavior that foreshadow failure. Furthermore, through offline analytics, potential correlations between unexpected detected obstacles (obtained through the NGAP/ADAS application) and rail track damages will be examined. The application will also provide recommendations, enabling maintenance teams to carry out remedial work before the asset starts to fail. Finally, the power consumption profile will also be monitored in real-time, in order to potentially minimize consumption and have an environmentally positive impact.