Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • 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
Cleansing Railway Track Measurement Data for Better Maintenance Decision
Luleå tekniska universitet, Institutionen för ekonomi, teknik och samhälle, Industriell Ekonomi. (Kvalitetsteknik och logistik)
Luleå tekniska universitet, Institutionen för ekonomi, teknik och samhälle, Industriell Ekonomi. Trafikverket. (Kvalitetsteknik och logistik)
University of Oulu.
Luleå tekniska universitet, Institutionen för ekonomi, teknik och samhälle, Industriell Ekonomi. (Kvalitetsteknik och logistik)
2019 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Data of sufficient quality, quantity and validity constitute asometimes overlooked basis for eMaintenance. Missing data,heterogeneous data types, calibration problems, or non-standarddistributions are common issues of operation and maintenancedata. Railway track geometry data used for maintenance planningexhibit all the above issues. They also have unique featuresstemming from their collection by measurement cars runningalong the railway network. As the track is a linear asset, measuredgeometry data need to be precisely located to be useful. However,since the sensors on the measurement car are moving along thetrack, the observations’ geographical sampling positions comewith uncertainty. Another issue is that different seasons and othertime restrictions (e.g. related to the timetable) prohibit regularsampling. Hence, prognostics related to remaining useful life(RUL) are challenging since most forecasting methods require afixed sampling frequency.

This paper discusses methods for data cleaning, data condensationand data extraction from large datasets collected by measurementcars. We discuss missing data replacement, dealing withautocorrelation or cross-correlation, and consequences of notfulfilling methodological pre-conditions such as estimatingprobabilities of failures using data that do not follow the assumeddistributions or data that are dependent. We also discuss outlierdetection, dealing with data coming from multiple distributions,of unknown calibrations and other issues seen in railway trackgeometry data. We also discuss the consequences of notaddressing or mishandling quality issues of such data.

Ort, förlag, år, upplaga, sidor
2019.
Nationell ämneskategori
Tillförlitlighets- och kvalitetsteknik
Forskningsämne
Kvalitetsteknik och logistik
Identifikatorer
URN: urn:nbn:se:ltu:diva-75427OAI: oai:DiVA.org:ltu-75427DiVA, id: diva2:1341155
Konferens
The 5th eMaintenance conference (2019)
Forskningsfinansiär
VinnovaTillgänglig från: 2019-08-07 Skapad: 2019-08-07 Senast uppdaterad: 2019-08-27

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

https://www.ltu.se/research/subjects/Drift-och-underhall/Konferenser/eMaintenance-Conference-2019
Av organisationen
Industriell Ekonomi
Tillförlitlighets- och kvalitetsteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 71 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • 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