Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Statistical Anomaly Detection for Train Fleets
RISE - Research Institutes of Sweden (2017-2019), ICT, SICS.ORCID-id: 0000-0003-1597-6738
RISE., Swedish ICT, SICS, Decisions, Networks and Analytics lab.ORCID-id: 0000-0001-8577-6745
RISE., Swedish ICT, SICS, Decisions, Networks and Analytics lab.ORCID-id: 0000-0002-7181-8411
Bombardier Transportation, Sweden.
Visa övriga samt affilieringar
2012 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

We have developed a method for statistical anomaly detection which has been deployed in a tool for condition monitoring of train fleets. The tool is currently used by several railway operators over the world to inspect and visualize the occurrence of "event messages" generated on the trains. The anomaly detection component helps the operators to quickly find significant deviations from normal behavior and to detect early indications for possible problems. The savings in maintenance costs comes mainly from avoiding costly breakdowns, and have been estimated to several million Euros per year for the tool. In the long run, it is expected that maintenance costs can be reduced with between 5 and 10 % by using the tool.

Ort, förlag, år, upplaga, sidor
Toronto, Canada, 2012, 9. Vol. 3, s. 2217-2223
Nyckelord [en]
Anomaly detection, Maintenance cost, Normal behavior, Railway operators, Statistical anomaly detection, Train fleets
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:ri:diva-24031Scopus ID: 2-s2.0-84868290884ISBN: 9781577355687 (tryckt)OAI: oai:DiVA.org:ri-24031DiVA, id: diva2:1043110
Konferens
Proceedings of the 21st Innovative Applications of Artificial Intelligence Conference
Projekt
DUST
Anmärkning

Accepted for publication.

Tillgänglig från: 2016-10-31 Skapad: 2016-10-31 Senast uppdaterad: 2023-05-09Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Scopus

Person

Bohlin, MarkusHolst, AndersEkman, Jan

Sök vidare i DiVA

Av författaren/redaktören
Bohlin, MarkusHolst, AndersEkman, Jan
Av organisationen
SICSDecisions, Networks and Analytics lab
Data- och informationsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 108 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf