Predictive Maintenance in a Railway Scenario

Duration: 10/2014 - 09/2017

Partners: DB Schenker Rail AG, Telecooperation Group at TU Darmstadt

Funding: Industry collaboration

Sensor technology has been integrated in railway systems for quite a while. Rail vehicles and the infrastructure are equipped with a large amount of sensors, on which security mechanisms like traffic control as well as control mechanisms on the trains are based. In the future there will be an even greater amount of sensors because they are constantly getting cheaper. The trend leads towards using this sensor-data for different kinds of monitoring. The various possibilities may be unclear at the point of installation and only become obvious much later.

The trains are equipped with an abundance of sensors, monitoring many system parameters. Those are the variables that can lead to insights regarding maintenance necessity or system performance. In the future they shall not only be used for diagnostics, but also to predict impending failures and help prevent them from happening altogether. This is known as predictive maintenance, and the main goal of this research project is to develop methods to apply it to the train fleet and prove its feasibility. Furthermore, possibilities to automatize the various prediction processes will be researched, as well as an integration of the resulting methodology into a real-world maintenance system will be targeted.



small ke-icon

Knowledge Engineering Group

Fachbereich Informatik
TU Darmstadt

S2|02 D203
Hochschulstrasse 10

D-64289 Darmstadt

Telefon-Symbol+49 6151 16-21811
Fax-Symbol +49 6151 16-21812

A A A | Drucken | Impressum | Sitemap | Suche | Mobile Version
zum Seitenanfangzum Seitenanfang