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
Mining Big Data For Vehicle Maintenance
KTH, School of Information and Communication Technology (ICT).
2016 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Optimizing maintenance of capital intensive products is getting increasingly important in todays data driven world. Advancement in the telecommunication services allows to gather data from vehicles making it possible to apply data mining techniques for predicting the remaining useful life and/or failure of a component. Failures in heavy trucks and buses can cause immobilization on the road, damage to the cargo, disruption of operations and can also be a potential source of road accidents. Predictive replacement of their components results both in increased reliability of vehicles and in significant cost savings from unplanned maintenance events giving Scania a competitive advantage.In this thesis, methods and results have been presented for applying wellknown data driven techniques, classification and survival analysis, to the task of predicting the need for repairs of APS (Air Processing System), a critical component in Scania’s heavy vehicles. Prediction models have been developed based on logged data regarding the current state of the vehicle, communicated wirelessly, in conjunction with data from the workshops related to the repair history. Stacked classifiers and a novel approach for predicting the health status, based on the combined results of classification and survival analysis, have been proposed. Overall, the results strongly support the idea that data mining techniques can be used to optimize maintenance schedules.

Place, publisher, year, edition, pages
2016. , p. 55
Series
TRITA-ICT-EX ; 2016:204
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-206151OAI: oai:DiVA.org:kth-206151DiVA, id: diva2:1091389
External cooperation
Scania
Subject / course
Information and Communication Technology
Educational program
Master of Science in Engineering - Information and Communication Technology
Examiners
Available from: 2017-04-26 Created: 2017-04-26 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Information and Communication Technology (ICT)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 169 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