Summary

The objective of the INDIGO project (development of an intelligent device for the diagnosis and monitoring of railway systems) is to provide a solution in the field of railway stationary diagnostics, in order to prevent possible accidents caused by the occurrence of physical and mechanical problems that may occur over time.

The research is in the field of diagnostic methods and predictive maintenance of “low-value” railway systems and it is aimed at developing techniques for monitoring significant physical parameters of trains (e.g. speed, travel direction, train composition, level of wear of the wheel rims, rail temperature, etc.) and methods for an effective and efficient planning of maintenance activities.

Description

The INDIGO project aims to meet the historical need for monitoring and checking the operational status of a train, extending in an original, non-invasive and economical way, the possibility of making predictive diagnostics also on a set of “low-value” vehicles (e.g. regional, metropolitan and freight trains). At European level, railway maintenance is considerably and promptly evolving, thanks to a heightened sensitivity to safety, quality, efficiency and sustainability. This fast evolution forms the basis of this project and it is a catalyst for Research and Development in the specific field.

The idea is to develop a “stationary” diagnostic system installed on the ground and not on board the train; capable of exploiting advanced products and techniques in order to correlate the information coming from a set of sensors arranged on rails, that can be activated by train passages over an Electromagnetic Pedal. These devices will be able to identify and detect the essential parameters of the vehicles in transit and also to sample their values; in order to observe any “not regular” operating conditions. The main parameters concern the physical characteristics of a train as: the speed and the travel direction, the composition of the tractor and the wagons, the level of wear of the wheel rims in every axis, the rail temperature, etc.

With these informations it will be possible to build, for each train, a set of diagnostic data that are useful to perform predictive analyses to determine when to stop a vehicle and provide maintenance, thus ensuring the optimization of the rolling stock maintenance resources. This database will also serve as a collection of “footprints” of railway trends in order to identify trains with similar behaviours.