Change search
Link to record
Permanent link

Direct link
Publications (2 of 2) Show all publications
Bergquist, B., Söderholm, P., Kauppila, O. & Vanhatalo, E. (2019). Cleaning of Railway Track Measurement Data forBetter Maintenance Decisions. In: Miguel Castano Arranz; Ramin Karim (Ed.), Proceedings of the 5th International Workshop and Congress on eMaintenance: eMaintenance: Trends in Technologies & methodologies, challenges, possibilites and applications. Paper presented at 5th International Workshop and Congress on eMaintenance, Stockholm, Sweden, 14-15 May 2019 (pp. 9-15). Luleå University of Technology
Open this publication in new window or tab >>Cleaning of Railway Track Measurement Data forBetter Maintenance Decisions
2019 (English)In: Proceedings of the 5th International Workshop and Congress on eMaintenance: eMaintenance: Trends in Technologies & methodologies, challenges, possibilites and applications / [ed] Miguel Castano Arranz; Ramin Karim, Luleå University of Technology , 2019, p. 9-15Conference paper, Published paper (Refereed)
Abstract [en]

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

This paper discusses methods for data cleaning, data condensation and data extraction from large datasets collected by measurement cars. We discuss missing data replacement, dealing with autocorrelation or cross-correlation, and consequences of not fulfilling methodological pre-conditions such as estimating probabilities of failures using data that do not follow the assumed distributions or data that are dependent. We also discuss outlier detection, dealing with data coming from multiple distributions, of unknown calibrations and other issues seen in railway track geometry data. We also discuss the consequences of not addressing or mishandling quality issues of such data. 

Place, publisher, year, edition, pages
Luleå University of Technology, 2019
Series
Trafikverkets forskningsportföljer
Keywords
Track geometry, big data, railway, data quality, diagnostics, prognostics, maintenance, Sweden
National Category
Reliability and Maintenance
Research subject
FOI-portföljer, Vidmakthålla
Identifiers
urn:nbn:se:trafikverket:diva-5620 (URN)978-91-7790-475-5 (ISBN)
Conference
5th International Workshop and Congress on eMaintenance, Stockholm, Sweden, 14-15 May 2019
Projects
Samordnad, effektiv planering av järnvägsinfrastrukturunderhåll
Funder
VinnovaSwedish Transport Administration, TRV 2017/14891
Note

ISBN för värdpublikation: 978-91-7790-475-5

Available from: 2019-08-07 Created: 2022-10-13 Last updated: 2023-02-01Bibliographically approved
Bergquist, B. & Söderholm, P. (2016). Predictive Modelling for Estimation of Railway Track Degradation. In: Uday Kumar; Alireza Ahmadu; Ajit Kumar Verma; Prabhakar Varde (Ed.), Current Trends in Reliability, Availability, Maintainability and Safety: An Industry Perspective. Paper presented at International Conference ICRESH-ARMS 2015 : 01/06/2015 - 04/06/2015 (pp. 331-347). Encyclopedia of Global Archaeology/Springer Verlag
Open this publication in new window or tab >>Predictive Modelling for Estimation of Railway Track Degradation
2016 (English)In: Current Trends in Reliability, Availability, Maintainability and Safety: An Industry Perspective / [ed] Uday Kumar; Alireza Ahmadu; Ajit Kumar Verma; Prabhakar Varde, Encyclopedia of Global Archaeology/Springer Verlag , 2016, p. 331-347Conference paper, Published paper (Refereed)
Abstract [en]

The degradation processes affecting railway track condition depends both on the resistance of the track and on the stresses subjected to it. Regarding the stresses, both their magnitudes and cycles are of importance when considering the degradation. Furthermore, the stresses have some regularity and variability in the time domain, while the degradation resistance of a track has some spatial regularity as well as variability. In addition, the condition measurements of track may be both irregular and contain measurement errors. Hence, it is challenging to model the condition of track to enable predictions and condition-based maintenance. However, wear prediction models could help to change large parts of the maintenance practice from predominantly corrective to preventive if both the deterministic and the stochastic components of the wear process can be estimated with sufficient accuracy. In this study, one-step-ahead predictions have been used for establishing prognostic models based on repeated measurements of railway track geometry to estimate track wear properties, degradation rates and stochastic behaviour including measurement errors. The prognostic models have then been used for condition assessment and state predictions. Repeated sampling allows for estimations of measurement errors, but the irregular sampling need to be accounted for by interpolation in the time series modelling approach

Place, publisher, year, edition, pages
Encyclopedia of Global Archaeology/Springer Verlag, 2016
Series
Trafikverkets forskningsportföljer
Series
Lecture Notes in Mechanical Engineering, ISSN 2195-4356
National Category
Reliability and Maintenance
Research subject
FOI-portföljer, Vidmakthålla
Identifiers
urn:nbn:se:trafikverket:diva-6062 (URN)10.1007/978-3-319-23597-4_24 (DOI)2-s2.0-85043755542 (Scopus ID)7501c3d9-b0a9-4f38-9faa-70788a5a4890 (Local ID)978-3-319-23596-7 (ISBN)978-3-319-23597-4 (ISBN)7501c3d9-b0a9-4f38-9faa-70788a5a4890 (Archive number)7501c3d9-b0a9-4f38-9faa-70788a5a4890 (OAI)
Conference
International Conference ICRESH-ARMS 2015 : 01/06/2015 - 04/06/2015
Projects
Samordnad, effektiv planering av järnvägsinfrastrukturunderhåll
Funder
Swedish Transport Administration, TRV 2017/14891
Available from: 2016-09-30 Created: 2023-03-17 Last updated: 2023-05-29Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3911-8009

Search in DiVA

Show all publications