Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Cleansing Railway Track Measurement Data for Better Maintenance Decision
Luleå University of Technology, Department of Business Administration, Technology and Social Sciences, Business Administration and Industrial Engineering. (Kvalitetsteknik och logistik)
Luleå University of Technology, Department of Business Administration, Technology and Social Sciences, Business Administration and Industrial Engineering. Trafikverket. (Kvalitetsteknik och logistik)
University of Oulu.
Luleå University of Technology, Department of Business Administration, Technology and Social Sciences, Business Administration and Industrial Engineering. (Kvalitetsteknik och logistik)
2019 (English)Conference paper, Published paper (Refereed)
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.

Place, publisher, year, edition, pages
2019.
National Category
Reliability and Maintenance
Research subject
Quality technology and logistics
Identifiers
URN: urn:nbn:se:ltu:diva-75427OAI: oai:DiVA.org:ltu-75427DiVA, id: diva2:1341155
Conference
The 5th eMaintenance conference (2019)
Funder
VinnovaAvailable from: 2019-08-07 Created: 2019-08-07 Last updated: 2019-08-27

Open Access in DiVA

No full text in DiVA

Other links

https://www.ltu.se/research/subjects/Drift-och-underhall/Konferenser/eMaintenance-Conference-2019
By organisation
Business Administration and Industrial Engineering
Reliability and Maintenance

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 18 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf