Gas turbine fault diagnosis from fast response data using probabilistic methods and information fusion

Kyriazis, A; Aretakis, N; Mathioudakis, K

dc.contributor.author	Kyriazis, A	en
dc.contributor.author	Aretakis, N	en
dc.contributor.author	Mathioudakis, K	en
dc.date.accessioned	2014-03-01T02:50:23Z
dc.date.available	2014-03-01T02:50:23Z
dc.date.issued	2006	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35103
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-33750805499&partnerID=40&md5=8258b283d49ef77e5072dafd936b2414	en
dc.subject.other	Compressors	en
dc.subject.other	Failure analysis	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Probabilistic logics	en
dc.subject.other	Vibrations (mechanical)	en
dc.subject.other	Bayesian Belief Networks	en
dc.subject.other	Probabilistic Neural Networks	en
dc.subject.other	Radial compressors	en
dc.subject.other	Spectral fault signatures	en
dc.subject.other	Gas turbines	en
dc.title	Gas turbine fault diagnosis from fast response data using probabilistic methods and information fusion	en
heal.type	conferenceItem	en
heal.publicationDate	2006	en
heal.abstract	The paper covers firstly the use of probabilistic neural networks for the classification of spectral fault signatures obtained from fast response data (sound, vibration, unsteady pressure). The method is compared to other alternatives, such as geometrical and statistical pattern recognition. The effectiveness of the method is demonstrated by presenting the results from application to data from a radial compressor and an industrial gas turbine. Further, probabilistic methods are used to perform information fusion. The outcomes of different diagnostic methods are used as a first level of diagnostic inference, and are fed to two different fusion processes which are based on ^Probabilistic Neural Networks and ii)Bayesian Belief Networks. It is demonstrated that these fusion processes provide powerful tools for effective fault classification. Copyright © 2006 by ASME.	en
heal.journalName	Proceedings of the ASME Turbo Expo	en
dc.identifier.volume	2	en
dc.identifier.spage	571	en
dc.identifier.epage	579	en