Difference between revisions of "Publications:A field test with self-organized modeling for knowledge discovery in a fleet of city buses"

From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Stefan Byttner, Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson |P...")
 
 
Line 4: Line 4:
 
{{PublicationSetupTemplate|Author=Stefan Byttner, Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson
 
{{PublicationSetupTemplate|Author=Stefan Byttner, Sławomir Nowaczyk, Rune Prytz, Thorsteinn Rögnvaldsson
 
|PID=641644
 
|PID=641644
|Name=Byttner, Stefan [stefan] (Högskolan i Halmstad [2804], Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) [3905], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Nowaczyk, Sławomir [slanow] (Högskolan i Halmstad [2804], Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) [3905], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Prytz, Rune [runpry] (Högskolan i Halmstad [2804], Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) [3905], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]) (Volvo Group Trucks Technology);Rögnvaldsson, Thorsteinn [denni] (Högskolan i Halmstad [2804], Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) [3905], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650])
+
|Name=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));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, Gothenburg, 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))
 
|Title=A field test with self-organized modeling for knowledge discovery in a fleet of city buses
 
|Title=A field test with self-organized modeling for knowledge discovery in a fleet of city buses
 
|PublicationType=Conference Paper
 
|PublicationType=Conference Paper
Line 14: Line 14:
 
|Volume=
 
|Volume=
 
|Issue=
 
|Issue=
|HostPublication=
+
|HostPublication=2013 IEEE International Conference on Mechatronics and Automation (ICMA 2013)
|Conference=IEEE International conference on Mechatronics and Automation
+
|Conference=10th IEEE International Conference on Mechatronics and Automation, IEEE ICMA 2013, Takamastu, Japan, 4-7 August, 2013
|StartPage=
+
|StartPage=896
|EndPage=
+
|EndPage=901
 
|Year=2013
 
|Year=2013
 
|Edition=
 
|Edition=
 
|Pages=
 
|Pages=
|City=
+
|City=Piscataway, NJ
|Publisher=
+
|Publisher=IEEE Press
 
|Series=
 
|Series=
 
|SeriesISSN=
 
|SeriesISSN=
|ISBN=
+
|ISBN=978-1-4673-5558-2
 
|Urls=
 
|Urls=
 
|ISRN=
 
|ISRN=
|DOI=
+
|DOI=http://dx.doi.org/10.1109/ICMA.2013.6618034
|ISI=
+
|ISI=000335375900151
 
|PMID=
 
|PMID=
|ScopusId=
+
|ScopusId=2-s2.0-84887900171
 
|NBN=urn:nbn:se:hh:diva-23370
 
|NBN=urn:nbn:se:hh:diva-23370
 
|LocalId=
 
|LocalId=
 
|ArchiveNumber=
 
|ArchiveNumber=
|Keywords=
+
|Keywords=Controller area network;Data collection;Diagnostic knowledge;Electronic control units;Information sources;Relevant components;Remote diagnostics;Self-organized models
 
|Categories=Signalbehandling (20205)
 
|Categories=Signalbehandling (20205)
 
|ResearchSubjects=
 
|ResearchSubjects=
 
|Projects=
 
|Projects=
|Notes=
+
|Notes=<p>Article number 6618034, Category number CFP13839-CDR, Code 100781</p>
|Abstract=<p>Fleets of commercial vehicles represent an excellent real life setting for ubiquitous knowledge discovery. There are many electronic control units onboard a modern bus or truck, with hundreds of signals being transmitted between them on the controller area network. The growing complexity of the vehicles has lead to a significant desire to have systems for fault detection, remote diagnostics and maintenance prediction. This paper aims to show that it is possible to discover useful diagnostic knowledge by a self-organized algorithm in the scenario of a fleet of city buses. The approach is demonstrated as a process consisting of two parts; Unsupervised modeling (where interesting features are discovered) and Guided search (where the previously found features are coupled to additional information sources). The modeling part searches for simple linear models in a group of vehicles, where interesting features are selected based on both non-randomness in relations and variability in the group. It is shown in an eight months long data collection study that this approach was able to discover features related to broken wheelspeed sensors. Strikingly, deviations in these features (for the vehicles with broken sensors) can be observed up to several months before a breakdown occur. This potentially allows for sufficient time to schedule the vehicle for maintenance and prepare the workshop with relevant components.</p>
+
|Abstract=<p>Fleets of commercial vehicles represent an excellent real life setting for ubiquitous knowledge discovery. There are many electronic control units onboard a modern bus or truck, with hundreds of signals being transmitted between them on the controller area network. The growing complexity of the vehicles has lead to a significant desire to have systems for fault detection, remote diagnostics and maintenance prediction. This paper aims to show that it is possible to discover useful diagnostic knowledge by a self-organized algorithm in the scenario of a fleet of city buses. The approach is demonstrated as a process consisting of two parts; Unsupervised modeling (where interesting features are discovered) and Guided search (where the previously found features are coupled to additional information sources). The modeling part searches for simple linear models in a group of vehicles, where interesting features are selected based on both non-randomness in relations and variability in the group. It is shown in an eight months long data collection study that this approach was able to discover features related to broken wheelspeed sensors. Strikingly, deviations in these features (for the vehicles with broken sensors) can be observed up to several months before a breakdown occur. This potentially allows for sufficient time to schedule the vehicle for maintenance and prepare the workshop with relevant components. © 2013 IEEE.</p>
 
|Opponents=
 
|Opponents=
 
|Supervisors=
 
|Supervisors=
Line 55: Line 55:
 
|CreatedDate=2013-08-19
 
|CreatedDate=2013-08-19
 
|PublicationDate=2013-08-19
 
|PublicationDate=2013-08-19
|LastUpdated=2013-10-15
+
|LastUpdated=2015-02-12
 
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:641644}}
 
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:641644}}
 
<div style='display: none'>
 
<div style='display: none'>

Latest revision as of 21:41, 30 September 2016

Do not edit this section

Keep all hand-made modifications below

Title A field test with self-organized modeling for knowledge discovery in a fleet of city buses
Author Stefan Byttner and Sławomir Nowaczyk and Rune Prytz and Thorsteinn Rögnvaldsson
Year 2013
PublicationType Conference Paper
Journal
HostPublication 2013 IEEE International Conference on Mechatronics and Automation (ICMA 2013)
Conference 10th IEEE International Conference on Mechatronics and Automation, IEEE ICMA 2013, Takamastu, Japan, 4-7 August, 2013
DOI http://dx.doi.org/10.1109/ICMA.2013.6618034
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:641644
Abstract Fleets of commercial vehicles represent an excellent real life setting for ubiquitous knowledge discovery. There are many electronic control units onboard a modern bus or truck, with hundreds of signals being transmitted between them on the controller area network. The growing complexity of the vehicles has lead to a significant desire to have systems for fault detection, remote diagnostics and maintenance prediction. This paper aims to show that it is possible to discover useful diagnostic knowledge by a self-organized algorithm in the scenario of a fleet of city buses. The approach is demonstrated as a process consisting of two parts; Unsupervised modeling (where interesting features are discovered) and Guided search (where the previously found features are coupled to additional information sources). The modeling part searches for simple linear models in a group of vehicles, where interesting features are selected based on both non-randomness in relations and variability in the group. It is shown in an eight months long data collection study that this approach was able to discover features related to broken wheelspeed sensors. Strikingly, deviations in these features (for the vehicles with broken sensors) can be observed up to several months before a breakdown occur. This potentially allows for sufficient time to schedule the vehicle for maintenance and prepare the workshop with relevant components. © 2013 IEEE.