DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Analysis of Railway Track Irregularities with Convolutional Autoencoders and Clustering Algorithms

Niebling, Julia and Baasch, Benjamin and Kruspe, Anna (2020) Analysis of Railway Track Irregularities with Convolutional Autoencoders and Clustering Algorithms. In: Communications in Computer and Information Science, 1279, pp. 78-89. Springer. AI4RAILS 2020, 07. Sept. 2020, Munich. doi: 10.1007/978-3-030-58462-7_7. ISBN 978-303032422-3. ISSN 1865-0929.

[img] PDF

Official URL: https://link.springer.com/chapter/10.1007/978-3-030-58462-7_7


Modern maintenance strategies for railway tracks rely more and more on data acquired with low-cost sensors installed on in-service trains. This quasi-continuous condition monitoring produces huge amounts of data, which require appropriate processing strategies. Deep learning has become a promising tool in analyzing large volumes of sensory data. In this work, we demonstrate the potential of artificial intelligence to analyze railway track defects. We combine traditional signal processing methods with deep convolutional autoencoders and clustering algorithms to find anomalies and their patterns. The methods are applied to real world data gathered with a multi-sensor prototype measurement system on a shunter locomotive operating on the industrial railway network of the inland harbor of Braunschweig (Germany). This work shows that deep learning methods can be applied to find patterns in railway track irregularities and opens a wide area of further improvements and developments.

Item URL in elib:https://elib.dlr.de/136375/
Document Type:Conference or Workshop Item (Speech)
Title:Analysis of Railway Track Irregularities with Convolutional Autoencoders and Clustering Algorithms
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Niebling, JuliaJulia.Niebling (at) dlr.dehttps://orcid.org/0000-0001-5413-2234
Baasch, BenjaminBenjamin.Baasch (at) dlr.dehttps://orcid.org/0000-0003-1970-3964
Kruspe, AnnaAnna.Kruspe (at) dlr.dehttps://orcid.org/0000-0002-2041-9453
Date:7 September 2020
Journal or Publication Title:Communications in Computer and Information Science
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 78-89
EditorsEmailEditor's ORCID iD
Bernardi, SimonaUniversity of Zaragozahttps://orcid.org/0000-0002-2605-6243
Vittorini, ValeriaUnivesity of Naples Federico IIUNSPECIFIED
Flammini, FrancescoLinnaeus Universityhttps://orcid.org/0000-0002-2833-7196
Nardone, RobertoUniversity of Reggio CalabriaUNSPECIFIED
Marrone, StefanoUnivesity of Naples Federico IIhttps://orcid.org/0000-0001-6852-0377
Adler, RasmusFraunhofer IESEUNSPECIFIED
Schneider, DanielFraunhofer IESEhttps://orcid.org/0000-0003-3465-9738
Schleiß, PhilippFraunhofer IKSUNSPECIFIED
Nostro, NicolaResiltech s.r.lhttps://orcid.org/0000-0001-6295-3622
Løvenstein Olsen, RasmusAalborg UniversityUNSPECIFIED
Di Salle, AmletoUniversity of L'Aquilahttps://orcid.org/0000-0002-0163-9784
Masci, PaoloNational Institute of Aerospace, Langley Research Centerhttps://orcid.org/0000-0002-0667-7763
Series Name:Dependable Computing - EDCC 2020 Workshops
Keywords:Defect Detection, Deep Learning, Convolutional Autoencoder, Clustering
Event Title:AI4RAILS 2020
Event Location:Munich
Event Type:Workshop
Event Dates:07. Sept. 2020
Organizer:Shift2Rail project RAILS
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:other
DLR - Research area:Raumfahrt
DLR - Program:R - no assignment
DLR - Research theme (Project):R - no assignment, V - Digitalisierung und Automatisierung des Bahnsystems
Location: Jena
Institutes and Institutions:Institute of Data Science
Institute of Transportation Systems
Deposited By: Niebling, Julia
Deposited On:01 Oct 2020 08:59
Last Modified:01 Oct 2020 08:59

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.