Unsupervised anomaly detection in railway catenary condition monitoring using autoencoders

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
9 Downloads (Pure)


The condition monitoring of railway infrastructures is collecting big data for intelligent asset management. Making the most of the big data is a critical challenge facing the railway industry. This study focuses on one of the main railway infrastructures, namely the catenary (overhead line) system that transmits power to trains. To facilitate the effective usage of catenary condition monitoring data, this study proposes an unsupervised anomaly detection approach as a pre-processing measure. The approach trains autoencoders to reduce the dimensionality of multisensor data and generate discriminative features between healthy and anomalous data. By testing the reconstruction errors using the trained autoencoders, anomalous data that indicate potential defects of catenary can be identified without prior information and human intervention. A case study on a section of high-speed railway catenary in China shows that the approach can automatically distinguish between healthy and anomalous data. The output anomalous data can save a considerable amount of computation time and manpower in further interpretations aiming to pinpoint defects.
Original languageEnglish
Title of host publicationProceedings - IECON 2020
Subtitle of host publication46th Annual Conference of the IEEE Industrial Electronics Society
Place of PublicationPiscataway
Pages2636 - 2641
Number of pages6
ISBN (Electronic)978-1-7281-5414-5
ISBN (Print)978-1-7281-5415-2
Publication statusPublished - 2020
EventThe 46th Annual Conference of the IEEE Industrial Electronics Society : IECON 2020 - Singapore, Singapore
Duration: 18 Oct 202021 Oct 2020

Publication series

NameIECON Proceedings (Industrial Electronics Conference)


ConferenceThe 46th Annual Conference of the IEEE Industrial Electronics Society
Internet address

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • anomaly detection
  • autoencoders
  • condition monitoring
  • railway catenary
  • unsupervised learning


Dive into the research topics of 'Unsupervised anomaly detection in railway catenary condition monitoring using autoencoders'. Together they form a unique fingerprint.

Cite this