A weighted dissimilarity index to isolate faults during alarm floods

A fault-isolation method based on pattern matching using the alarm lists raised by the SCADA system during an alarm flood is proposed. A training set composed of faults is used to create fault templates. Alarm vectors generated by unknown faults are classified by comparing them with the fault templa...

Descripción completa

Detalles Bibliográficos
Autores principales: Charbonnier, S, Bouchair, N, Gayet, P
Lenguaje:eng
Publicado: 2015
Materias:
Other Subjects
Acceso en línea:https://dx.doi.org/10.1016/j.conengprac.2015.09.004
http://cds.cern.ch/record/2161128
_version_ 1780950925890813952
author Charbonnier, S
Bouchair, N
Gayet, P
author_facet Charbonnier, S
Bouchair, N
Gayet, P
author_sort Charbonnier, S
collection CERN
description A fault-isolation method based on pattern matching using the alarm lists raised by the SCADA system during an alarm flood is proposed. A training set composed of faults is used to create fault templates. Alarm vectors generated by unknown faults are classified by comparing them with the fault templates using an original weighted dissimilarity index that increases the influence of the few alarms relevant to diagnose the fault. Different decision strategies are proposed to support the operator in his decision making. The performances are evaluated on two sets of data: an artificial set and a set obtained from a highly realistic simulator of the CERN Large Hadron Collider process connected to the real CERN SCADA system.
id cern-2161128
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2015
record_format invenio
spelling cern-21611282019-09-30T06:29:59Zdoi:10.1016/j.conengprac.2015.09.004http://cds.cern.ch/record/2161128engCharbonnier, SBouchair, NGayet, PA weighted dissimilarity index to isolate faults during alarm floodsOther SubjectsA fault-isolation method based on pattern matching using the alarm lists raised by the SCADA system during an alarm flood is proposed. A training set composed of faults is used to create fault templates. Alarm vectors generated by unknown faults are classified by comparing them with the fault templates using an original weighted dissimilarity index that increases the influence of the few alarms relevant to diagnose the fault. Different decision strategies are proposed to support the operator in his decision making. The performances are evaluated on two sets of data: an artificial set and a set obtained from a highly realistic simulator of the CERN Large Hadron Collider process connected to the real CERN SCADA system.oai:cds.cern.ch:21611282015
spellingShingle Other Subjects
Charbonnier, S
Bouchair, N
Gayet, P
A weighted dissimilarity index to isolate faults during alarm floods
title A weighted dissimilarity index to isolate faults during alarm floods
title_full A weighted dissimilarity index to isolate faults during alarm floods
title_fullStr A weighted dissimilarity index to isolate faults during alarm floods
title_full_unstemmed A weighted dissimilarity index to isolate faults during alarm floods
title_short A weighted dissimilarity index to isolate faults during alarm floods
title_sort weighted dissimilarity index to isolate faults during alarm floods
topic Other Subjects
url https://dx.doi.org/10.1016/j.conengprac.2015.09.004
http://cds.cern.ch/record/2161128
work_keys_str_mv AT charbonniers aweighteddissimilarityindextoisolatefaultsduringalarmfloods
AT bouchairn aweighteddissimilarityindextoisolatefaultsduringalarmfloods
AT gayetp aweighteddissimilarityindextoisolatefaultsduringalarmfloods
AT charbonniers weighteddissimilarityindextoisolatefaultsduringalarmfloods
AT bouchairn weighteddissimilarityindextoisolatefaultsduringalarmfloods
AT gayetp weighteddissimilarityindextoisolatefaultsduringalarmfloods

Ejemplares similares