Retour aux projets

14586.2 PFES-ES

Machine Learning approaches for freight train safety monitoring

Résumé

Machine Learning approaches for freight train safety monitoring

Textes supplémentaires

Abstract

The proposed project aims to provide a method for safety monitoring of trains in the SBB network. It focuses on automatically identifying wheel defects on freight trains based on the existing SBB infrastructure.|The method is expected to provide within-class and overall wheel defect rankings. This goal involves adapting and extending current machine learning methods such as multiple instance learning, semi-supervised classification and simultaneous regression and ranking.

Participants

Stefan Koller

Wirtschaftspartner

stefan.koller@sbb.ch

SBB Anlagen und Technologien Stefan Koller Güterstrasse 3 6005 Luzern LU CH

Joachim Buhmann

Kontaktperson

jbuhmann@inf.ethz.ch

ETH Zürich Joachim Buhmann Universitätsstrasse 6 8092 Zürich ZH CH

Détails du projet

Office de recherche
INNOSUISSE
Statut du projet
Abgeschlossen
Type de projet
Forschungsprojekt
Date de début
2013-02-28
Date de fin
2016-02-29
Coûts totaux approuvés
CHF 253649.00
Section
21 Förderbereich Enabling Sciences
Domaine politique NABS
Industrielle Produktivität und Technologie

Disciplines de recherche

  • T180 Telecommunication engineering 100.0%