Change search
ReferencesLink to record
Permanent link

Direct link
Statistical anomaly detection for train fleets
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB. Swedish Institute of Computer Science, Sweden.ORCID iD: 0000-0001-8577-6745
Show others and affiliations
2013 (English)In: The AI Magazine, ISSN 0738-4602, Vol. 34, no 1, 33-42 p.Article in journal (Refereed) Published
Abstract [en]

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

Place, publisher, year, edition, pages
2013. Vol. 34, no 1, 33-42 p.
Keyword [en]
Anomaly detection, Bayesian, Bayesian statistics, Maintenance cost, Normal behavior, Railway operators, Statistical anomaly detection, Train fleets, Condition monitoring, Maintenance
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-127174ISI: 000336891700004ScopusID: 2-s2.0-84876175602OAI: diva2:643833

QC 20130828

Available from: 2013-08-28 Created: 2013-08-28 Last updated: 2015-06-26Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Holst, Anders
By organisation
Computational Biology, CB
In the same journal
The AI Magazine
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 52 hits
ReferencesLink to record
Permanent link

Direct link