3D and AI for predictive maintenance of rolling stock

Joint development of a complex inspection system for negative collector shoe

3D and AI for predictive maintenance of rolling stock

All industries are now turning to digitalisation and AI, and the French public transport group RATP has followed this trend by innovating to improve the quality of its services (customer offerings, predictive maintenance, etc.).

Given that R&D Vision operates in various areas to design dedicated optical measurement systems, the company is regularly contacted to design digital predictive maintenance assistance systems for non-destructive testing (NDT), 3D terahertz reconstruction, infrared thermography and so on.

RATP and R&D Vision have just signed a research agreement to jointly develop a complex inspection system for negative and earth collector shoes on the automated underground systems on Paris Metro Line 1. This equipment, which is installed in the operating track, will enable continuous inspection of the various underground trains when they go past.

Several measurements will be taken to validate the conformity of the parts: presence/absence, 3D position, wear level, impacts and crack detection. The introduction of a predictive model will improve rail safety, as will optimised maintenance operations to ensure better availability of trains.

The optical system will ensure very high-quality, repeatable imaging, despite the speed of trains and the vibrations generated. It will guarantee outstanding robustness in image processing algorithms and Artificial Intelligence specially designed for this project.

The parties signed the research agreement at the beginning of September 2020, with the putting into service of a prototype set for 2022.