schliessen

Filtern

 

Bibliotheken

Online Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application

In order to improve one-class support vector machine (OCSVM)'s performance, that is OCSVM's training efficiency and decision precision, a double threshold OCSVM online detection (DTOOD) algorithm is proposed. In DTOOD, the OCSVM detection model with two-layer thresholds can separate outliers into no... Full description

Journal Title: Ji xie gong cheng xue bao 2009, Vol.45 (3), p.169-173
Main Author: HU, Lei
Format: Electronic Article Electronic Article
Language: eng ; chi
ID: ISSN: 0577-6686
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_crossref_primary_10_3901_JME_2009_03_169
title: Online Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application
format: Article
creator:
  • HU, Lei
ispartof: Ji xie gong cheng xue bao, 2009, Vol.45 (3), p.169-173
description: In order to improve one-class support vector machine (OCSVM)'s performance, that is OCSVM's training efficiency and decision precision, a double threshold OCSVM online detection (DTOOD) algorithm is proposed. In DTOOD, the OCSVM detection model with two-layer thresholds can separate outliers into non-margin support vectors and real abnormal samples. And the detection model can be updated online adaptively without real abnormal samples as they are omitted in future training sets. Meanwhile, sequential minimal optimization algorithm for OCSVM is introduced to improve the training efficiency. DTOOD is applied to the analysis of a liquid rocket engine turbopump historical vibration data, and the results show that DTOOD can detect the faults of the turbopump very well without any false alarm. And the computation is fast enough to assure DTOOD's ability of real time fault detection.
language: eng ; chi
source:
identifier: ISSN: 0577-6686
fulltext: no_fulltext
issn:
  • 0577-6686
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.0389848
LOCALfalse
PrimoNMBib
record
control
sourceidproquest_cross
recordidTN_cdi_crossref_primary_10_3901_JME_2009_03_169
sourceformatXML
sourcesystemPC
sourcerecordid34641729
originalsourceidFETCH-LOGICAL-c1782-72b61561e5d7f0f1b9d332a15ed88692dd693afc45b7a474a582bc45ed7bc6d0
addsrcrecordideNp1kDtPwzAURj2ARHnMrJ7YkvqR2PFY-oCiVh2oWC3HdqiRmwTbGfj3pJQJienqu_rOle4B4B6jnAqEpy_bZU4QEjmiOWbiAkxQyXnGWMWuwHWMHwhRwQmegP2u9a61cKUGn-DCJquT61o48-9dcOlwhI8qWgPH1aIbam-zdAg2Hjpv4G7--raFqjVwnSKc9b13Wp3oW3DZKB_t3e-8AfvVcj9_zja7p_V8tsk05hXJOKkZLhm2peENanAtDKVE4dKaqmKCGMMEVY0uypqrgheqrEg9Jmt4rZlBN-DhfLYP3edgY5JHF7X1XrW2G6KkBSswJ2IsTs9FHboYg21kH9xRhS-JkTwJk6MweRImEZWjsJEo_xDapZ_fUlDO_8t9AyffcTI
sourcetypeAggregation Database
isCDItrue
recordtypearticle
pqid34641729
display
typearticle
titleOnline Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application
creatorHU, Lei
creatorcontribHU, Lei
descriptionIn order to improve one-class support vector machine (OCSVM)'s performance, that is OCSVM's training efficiency and decision precision, a double threshold OCSVM online detection (DTOOD) algorithm is proposed. In DTOOD, the OCSVM detection model with two-layer thresholds can separate outliers into non-margin support vectors and real abnormal samples. And the detection model can be updated online adaptively without real abnormal samples as they are omitted in future training sets. Meanwhile, sequential minimal optimization algorithm for OCSVM is introduced to improve the training efficiency. DTOOD is applied to the analysis of a liquid rocket engine turbopump historical vibration data, and the results show that DTOOD can detect the faults of the turbopump very well without any false alarm. And the computation is fast enough to assure DTOOD's ability of real time fault detection.
identifier
0ISSN: 0577-6686
1DOI: 10.3901/JME.2009.03.169
languageeng ; chi
ispartofJi xie gong cheng xue bao, 2009, Vol.45 (3), p.169-173
lds50peer_reviewed
citedbyFETCH-LOGICAL-c1782-72b61561e5d7f0f1b9d332a15ed88692dd693afc45b7a474a582bc45ed7bc6d0
links
openurl$$Topenurl_article
thumbnail$$Usyndetics_thumb_exl
search
creatorcontribHU, Lei
title
0Online Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application
1Ji xie gong cheng xue bao
descriptionIn order to improve one-class support vector machine (OCSVM)'s performance, that is OCSVM's training efficiency and decision precision, a double threshold OCSVM online detection (DTOOD) algorithm is proposed. In DTOOD, the OCSVM detection model with two-layer thresholds can separate outliers into non-margin support vectors and real abnormal samples. And the detection model can be updated online adaptively without real abnormal samples as they are omitted in future training sets. Meanwhile, sequential minimal optimization algorithm for OCSVM is introduced to improve the training efficiency. DTOOD is applied to the analysis of a liquid rocket engine turbopump historical vibration data, and the results show that DTOOD can detect the faults of the turbopump very well without any false alarm. And the computation is fast enough to assure DTOOD's ability of real time fault detection.
issn0577-6686
fulltextfalse
rsrctypearticle
creationdate2009
recordtypearticle
recordideNp1kDtPwzAURj2ARHnMrJ7YkvqR2PFY-oCiVh2oWC3HdqiRmwTbGfj3pJQJienqu_rOle4B4B6jnAqEpy_bZU4QEjmiOWbiAkxQyXnGWMWuwHWMHwhRwQmegP2u9a61cKUGn-DCJquT61o48-9dcOlwhI8qWgPH1aIbam-zdAg2Hjpv4G7--raFqjVwnSKc9b13Wp3oW3DZKB_t3e-8AfvVcj9_zja7p_V8tsk05hXJOKkZLhm2peENanAtDKVE4dKaqmKCGMMEVY0uypqrgheqrEg9Jmt4rZlBN-DhfLYP3edgY5JHF7X1XrW2G6KkBSswJ2IsTs9FHboYg21kH9xRhS-JkTwJk6MweRImEZWjsJEo_xDapZ_fUlDO_8t9AyffcTI
startdate2009
enddate2009
creatorHU, Lei
scope
0AAYXX
1CITATION
27TB
38FD
4FR3
5H8D
6L7M
sort
creationdate2009
titleOnline Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application
authorHU, Lei
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c1782-72b61561e5d7f0f1b9d332a15ed88692dd693afc45b7a474a582bc45ed7bc6d0
rsrctypearticles
prefilterarticles
languageeng ; chi
creationdate2009
toplevelpeer_reviewed
creatorcontribHU, Lei
collection
0CrossRef
1Mechanical & Transportation Engineering Abstracts
2Technology Research Database
3Engineering Research Database
4Aerospace Database
5Advanced Technologies Database with Aerospace
jtitleJi xie gong cheng xue bao
delivery
delcategoryRemote Search Resource
fulltextno_fulltext
addata
auHU, Lei
formatjournal
genrearticle
ristypeJOUR
atitleOnline Fault Detection Algorithm Based on Double-threshold OCSVM and Its Application
jtitleJi xie gong cheng xue bao
date2009
risdate2009
volume45
issue3
spage169
epage173
pages169-173
issn0577-6686
abstractIn order to improve one-class support vector machine (OCSVM)'s performance, that is OCSVM's training efficiency and decision precision, a double threshold OCSVM online detection (DTOOD) algorithm is proposed. In DTOOD, the OCSVM detection model with two-layer thresholds can separate outliers into non-margin support vectors and real abnormal samples. And the detection model can be updated online adaptively without real abnormal samples as they are omitted in future training sets. Meanwhile, sequential minimal optimization algorithm for OCSVM is introduced to improve the training efficiency. DTOOD is applied to the analysis of a liquid rocket engine turbopump historical vibration data, and the results show that DTOOD can detect the faults of the turbopump very well without any false alarm. And the computation is fast enough to assure DTOOD's ability of real time fault detection.
doi10.3901/JME.2009.03.169