Setting up of a probabilistic neural network for sensor fault detection including operation with component faults

Romesis, G; Mathioudakis, K

dc.contributor.author	Romesis, G	en
dc.contributor.author	Mathioudakis, K	en
dc.date.accessioned	2014-03-01T01:19:32Z
dc.date.available	2014-03-01T01:19:32Z
dc.date.issued	2003	en
dc.identifier.issn	0742-4795	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/15551
dc.subject	Engine Performance	en
dc.subject	Fault Detection	en
dc.subject	Fault Identification	en
dc.subject	Gas Turbine	en
dc.subject	Probabilistic Neural Network	en
dc.subject.classification	Engineering, Mechanical	en
dc.subject.other	Engines	en
dc.subject.other	Gas turbines	en
dc.subject.other	Identification (control systems)	en
dc.subject.other	Mathematical models	en
dc.subject.other	Probability	en
dc.subject.other	Sensors	en
dc.subject.other	Spurious signal noise	en
dc.subject.other	Fault detection	en
dc.subject.other	Probabilistic neural network (PNN)	en
dc.subject.other	Sensor fault	en
dc.subject.other	Neural networks	en
dc.subject.other	engine	en
dc.subject.other	fault detection	en
dc.subject.other	gas turbine	en
dc.subject.other	neural network	en
dc.subject.other	performance assessment	en
dc.subject.other	sensor	en
dc.title	Setting up of a probabilistic neural network for sensor fault detection including operation with component faults	en
heal.type	journalArticle	en
heal.identifier.primary	10.1115/1.1582493	en
heal.identifier.secondary	http://dx.doi.org/10.1115/1.1582493	en
heal.language	English	en
heal.publicationDate	2003	en
heal.abstract	The diagnostic ability of probabilistic neural networks (PNN) for detecting sensor faults on gas turbines is examined. The structure and the features of a PNN, for sensor fault detection, are presented. It is shown that with the proposed formulation, a powerful tool for sensor fault identification is produced. A particular feature of the PNN produced is the ability to detect sensor faults even in the presence of engine component malfunction, as well as on deteriorated engines. In such situations, the size of bias that can be identified increases. The way to establish the limits of sensor bias that can be detected is presented along with results from application to test cases with realistic noise magnitudes. The diagnostic procedure proposed here is also supported by an engine performance model. The data used for setting up and testing the PNN are generated by such a model.	en
heal.publisher	ASME-AMER SOC MECHANICAL ENG	en
heal.journalName	Journal of Engineering for Gas Turbines and Power	en
dc.identifier.doi	10.1115/1.1582493	en
dc.identifier.isi	ISI:000185213400004	en
dc.identifier.volume	125	en
dc.identifier.issue	3	en
dc.identifier.spage	634	en
dc.identifier.epage	641	en