High-speed train-rails Quality Monitoring and Predictive Maintenance
Aggregating various data sources
For Vinci, the stakes are multiple: counting and identifying trains, infrastructures availability, responsibilities sharing when an issue arise (rail incident or disabled train), and Predictive Maintenance: which includes maintenance plan optimization by detecting weak early signals.
To be as simple and efficient as possible, the solution had to integrate more than 20 data sources, including:
- Data coming from communication between SNCF control center and trains
- IoT data
- Meteorological sensors
- Data from the maintenance train controlling various elements of the infrastructure
Operationalizing data processing
Although all this information already existed, it was completely fragmented between the different departments. This limited approach did not help to fully leverage and power data or to go further by developing new services based on Artificial Intelligence.
Predictive Maintenance Solution
After a thorough evaluation of different solutions, Vinci chose ForePaaS and its partner Eleven, a European strategy firm with a strong expertise on digital and data challenges, to build its predictive maintenance solution for several reasons:
- To access every component required for a data project, all in one place: collection, storage, exposition, training and run of AI models
- To leverage a platform with the capability to connect and process multiple data sources and formats, including high-frequency IoT, passive and active data
- To benefit from an agile collaboration framework with fast iteration cycles and strong support throughout each step of the process
The solution was quickly designed using the ForePaaS Platform. A first prototype was quickly deployed, in less than 6 months, to better understand the origin of unavailabilities, with a focus on train switches for which data are harder to process. A second phase was launched a few months later, focusing now on data extraction and predictive models development to move towards more predictive maintenance.