Difference between revisions of "Publications:Towards a Machine Learning Algorithm for Predicting Truck Compressor Failures Using Logged Vehicle Data"
From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson, Stefan Byttner |P...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson, Stefan Byttner | {{PublicationSetupTemplate|Author=Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson, Stefan Byttner | ||
|PID=682966 | |PID=682966 | ||
| − | |Name=Nowaczyk, Sławomir [slanow] (Högskolan i Halmstad [2804], | + | |Name=Nowaczyk, Sławomir [slanow] [0000-0002-7796-5201] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Prytz, Rune [runpry] [0000-0001-8255-1276] (Volvo Group Trucks Technology, Advanced Technology & Research, Göteborg, Sweden);Rögnvaldsson, Thorsteinn [denni] [0000-0001-5163-2997] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Byttner, Stefan [stefan] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]) |
|Title=Towards a Machine Learning Algorithm for Predicting Truck Compressor Failures Using Logged Vehicle Data | |Title=Towards a Machine Learning Algorithm for Predicting Truck Compressor Failures Using Logged Vehicle Data | ||
|PublicationType=Conference Paper | |PublicationType=Conference Paper | ||
| Line 31: | Line 31: | ||
|ISI= | |ISI= | ||
|PMID= | |PMID= | ||
| − | |ScopusId= | + | |ScopusId=2-s2.0-84894677920 |
|NBN=urn:nbn:se:hh:diva-24249 | |NBN=urn:nbn:se:hh:diva-24249 | ||
|LocalId= | |LocalId= | ||
| Line 55: | Line 55: | ||
|CreatedDate=2013-12-31 | |CreatedDate=2013-12-31 | ||
|PublicationDate=2013-12-31 | |PublicationDate=2013-12-31 | ||
| − | |LastUpdated= | + | |LastUpdated=2015-02-12 |
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:682966}} | |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:682966}} | ||
<div style='display: none'> | <div style='display: none'> | ||
Revision as of 21:47, 30 September 2016
| Title | Towards a Machine Learning Algorithm for Predicting Truck Compressor Failures Using Logged Vehicle Data |
|---|---|
| Author | Sławomir Nowaczyk and Rune Prytz and Thorsteinn Rögnvaldsson and Stefan Byttner |
| Year | 2013 |
| PublicationType | Conference Paper |
| Journal | |
| HostPublication | Twelfth Scandinavian Conference on Artificial Intelligence |
| Conference | 12th Scandinavian Conference on Artificial Intelligence, Aalborg, Denmark, November 20–22, 2013 |
| DOI | http://dx.doi.org/10.3233/978-1-61499-330-8-205 |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:682966 |
| Abstract | Predictive maintenance is becoming more and more important for the commercial vehicle manufactures, as focus shifts from product- to service-based operation. The idea is to provide a dynamic maintenance schedule, fulfilling specific needs of individual vehicles. Luckily, the same shift of focus, as well as technological advancements in the telecommunication area, make long-term data collection more widespread, delivering the necessary data.We have found, however, that the standard attribute-value knowledge representation is not rich enough to capture important dependencies in this domain. Therefore, we are proposing a new rule induction algorithm, inspired by Michalski's classical AQ approach. Our method is aware that data concerning each vehicle consists of time-ordered sequences of readouts. When evaluating candidate rules, it takes into account the composite performance for each truck, instead of considering individual readouts in separation. This allows us more flexibility, in particular in defining desired prediction horizon in a fuzzy, instead of crisp, manner. |
