File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Research on application of PCA and SVM to flame monitoring

TitleResearch on application of PCA and SVM to flame monitoring
Authors
KeywordsCombustion Diagnosis
Flame Image
Patterns Distinction
Principal Component Analysis
Support Vector Machine(Svm)
Issue Date2004
PublisherZhongguo Dianji Gongcheng Xuehui. The Journal's web site is located at http://www.dwjs.com.cn
Citation
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering, 2004, v. 24 n. 2, p. 185-190 How to Cite?
AbstractSeven characteristic values ,such as flame luminance, flame area, centroid offset and etc. are extracted in analysing the flame image. And then based on principal component analysis (PCA), a method for monitoring and diagnosing stability of flame is put forward. Two statistics of Hotelling T2 and Q are used to monitor time-to-time image data vectors, and check them whether they exceed their own controllable limit. As long as any one of them exceeds the limit, abnormity of combustion should be concluded. An experimental research shows that the method helps in on-line and real-time recognizing and judging the combustion status of the burning flame, and gives a visual result with figures of Q, of Hotelling T2 and PCA; at the same time, the characteristic vector and the original image data identified and sorted by using a method of support vector machine (SVM), the results show that two method, one is based on PCA and another is by support vector machine, are quite accordant.
Persistent Identifierhttp://hdl.handle.net/10722/91111
ISSN
2015 SCImago Journal Rankings: 0.881
References

 

DC FieldValueLanguage
dc.contributor.authorBai, W-Den_HK
dc.contributor.authorYan, J-Hen_HK
dc.contributor.authorChi, Yen_HK
dc.contributor.authorWang, Fen_HK
dc.contributor.authorMa, Z-Yen_HK
dc.contributor.authorLin, Ben_HK
dc.contributor.authorNi, M-Jen_HK
dc.contributor.authorCen, K-Fen_HK
dc.date.accessioned2010-09-17T10:13:12Z-
dc.date.available2010-09-17T10:13:12Z-
dc.date.issued2004en_HK
dc.identifier.citationZhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering, 2004, v. 24 n. 2, p. 185-190en_HK
dc.identifier.issn0258-8013en_HK
dc.identifier.urihttp://hdl.handle.net/10722/91111-
dc.description.abstractSeven characteristic values ,such as flame luminance, flame area, centroid offset and etc. are extracted in analysing the flame image. And then based on principal component analysis (PCA), a method for monitoring and diagnosing stability of flame is put forward. Two statistics of Hotelling T2 and Q are used to monitor time-to-time image data vectors, and check them whether they exceed their own controllable limit. As long as any one of them exceeds the limit, abnormity of combustion should be concluded. An experimental research shows that the method helps in on-line and real-time recognizing and judging the combustion status of the burning flame, and gives a visual result with figures of Q, of Hotelling T2 and PCA; at the same time, the characteristic vector and the original image data identified and sorted by using a method of support vector machine (SVM), the results show that two method, one is based on PCA and another is by support vector machine, are quite accordant.en_HK
dc.languageengen_HK
dc.publisherZhongguo Dianji Gongcheng Xuehui. The Journal's web site is located at http://www.dwjs.com.cnen_HK
dc.relation.ispartofZhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineeringen_HK
dc.subjectCombustion Diagnosisen_HK
dc.subjectFlame Imageen_HK
dc.subjectPatterns Distinctionen_HK
dc.subjectPrincipal Component Analysisen_HK
dc.subjectSupport Vector Machine(Svm)en_HK
dc.titleResearch on application of PCA and SVM to flame monitoringen_HK
dc.typeArticleen_HK
dc.identifier.emailLin, B:blin@hku.hken_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.scopuseid_2-s2.0-2342437937en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-2342437937&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume24en_HK
dc.identifier.issue2en_HK
dc.identifier.spage185en_HK
dc.identifier.epage190en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats