A measurement-based fault detection approach applied to monitor robots swarm

Handle URI:
http://hdl.handle.net/10754/625670
Title:
A measurement-based fault detection approach applied to monitor robots swarm
Authors:
Khaldi, Belkacem; Harrou, Fouzi; Sun, Ying ( 0000-0001-6703-4270 ) ; Cherif, Foudil
Abstract:
Swarm robotics requires continuous monitoring to detect abnormal events and to sustain normal operations. Indeed, swarm robotics with one or more faulty robots leads to degradation of performances complying with the target requirements. This paper present an innovative data-driven fault detection method for monitoring robots swarm. The method combines the flexibility of principal component analysis (PCA) models and the greater sensitivity of the exponentially-weighted moving average control chart to incipient changes. We illustrate through simulated data collected from the ARGoS simulator that a significant improvement in fault detection can be obtained by using the proposed methods as compared to the use of the conventional PCA-based methods.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program
Citation:
Khaldi B, Harrou F, Sun Y, Cherif F (2017) A measurement-based fault detection approach applied to monitor robots swarm. 2017 6th International Conference on Systems and Control (ICSC). Available: http://dx.doi.org/10.1109/ICoSC.2017.7958703.
Publisher:
IEEE
Journal:
2017 6th International Conference on Systems and Control (ICSC)
KAUST Grant Number:
OSR-2015-CRG4-2582
Conference/Event name:
6th International Conference on Systems and Control, ICSC 2017
Issue Date:
10-Jul-2017
DOI:
10.1109/ICoSC.2017.7958703
Type:
Conference Paper
Sponsors:
This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582. The authors (Belkacem Khaldi and Foudil Cherif) would like to thank the LESIA Laboratory, Department of Computer Science, University of Mohamed Khider,Biskra, Algeria for the continued support during the research.
Additional Links:
http://ieeexplore.ieee.org/document/7958703/
Appears in Collections:
Conference Papers; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKhaldi, Belkacemen
dc.contributor.authorHarrou, Fouzien
dc.contributor.authorSun, Yingen
dc.contributor.authorCherif, Foudilen
dc.date.accessioned2017-10-03T12:49:33Z-
dc.date.available2017-10-03T12:49:33Z-
dc.date.issued2017-07-10en
dc.identifier.citationKhaldi B, Harrou F, Sun Y, Cherif F (2017) A measurement-based fault detection approach applied to monitor robots swarm. 2017 6th International Conference on Systems and Control (ICSC). Available: http://dx.doi.org/10.1109/ICoSC.2017.7958703.en
dc.identifier.doi10.1109/ICoSC.2017.7958703en
dc.identifier.urihttp://hdl.handle.net/10754/625670-
dc.description.abstractSwarm robotics requires continuous monitoring to detect abnormal events and to sustain normal operations. Indeed, swarm robotics with one or more faulty robots leads to degradation of performances complying with the target requirements. This paper present an innovative data-driven fault detection method for monitoring robots swarm. The method combines the flexibility of principal component analysis (PCA) models and the greater sensitivity of the exponentially-weighted moving average control chart to incipient changes. We illustrate through simulated data collected from the ARGoS simulator that a significant improvement in fault detection can be obtained by using the proposed methods as compared to the use of the conventional PCA-based methods.en
dc.description.sponsorshipThis publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582. The authors (Belkacem Khaldi and Foudil Cherif) would like to thank the LESIA Laboratory, Department of Computer Science, University of Mohamed Khider,Biskra, Algeria for the continued support during the research.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/7958703/en
dc.rights(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.subjectControl chartsen
dc.subjectData modelsen
dc.subjectFault detectionen
dc.subjectMonitoringen
dc.subjectPrincipal component analysisen
dc.subjectRobot sensing systemsen
dc.titleA measurement-based fault detection approach applied to monitor robots swarmen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.identifier.journal2017 6th International Conference on Systems and Control (ICSC)en
dc.conference.date2017-05-07 to 2017-05-09en
dc.conference.name6th International Conference on Systems and Control, ICSC 2017en
dc.conference.locationBatna, DZAen
dc.eprint.versionPost-printen
dc.contributor.institutionLESIA Laboratory, Department of Computer Science, University of Mohamed Khider, B.P. 145, R.P. 07000 Biskra, Algeriaen
kaust.authorHarrou, Fouzien
kaust.authorSun, Yingen
kaust.grant.numberOSR-2015-CRG4-2582en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.