Publication:
Fault detection and diagnosis using an art-based neural network

Simple item page
dc.citedby0
dc.contributor.authorYap K.S.en_US
dc.contributor.authorAu M.T.en_US
dc.contributor.authorLim C.P.en_US
dc.contributor.authorSaleh J.M.en_US
dc.contributor.authorid24448864400en_US
dc.contributor.authorid9742020600en_US
dc.contributor.authorid55666579300en_US
dc.contributor.authorid6505808410en_US
dc.date.accessioned2023-12-29T07:51:30Z
dc.date.available2023-12-29T07:51:30Z
dc.date.issued2010
dc.description.abstractThe Generalized Adaptive Resonance Theory (GART) network is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. It is capable of online learning, and is effective in tackling classification as well as regression tasks, as demonstrated in our previous work. In this paper, we further enhance the capability of the GART network with the Laplacian functions and with new vigilance and match-tracking mechanisms. In addition, a rule extraction procedure is incorporated into its dynamics, and its applicability to fault detection and diagnosis tasks is assessed. IF-THEN rules can be extracted from the weights of the trained GART network after a pruning process. The classification and rule extraction capability of GART are evaluated using one benchmark data set from medical application, and one real data set collected from a power generation plant. These results are then compared with those reported by other methods. The outcomes demonstrate that GART is able to produce high classification rates with quality rules for tackling fault detection and diagnosis problems.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.2316/p.2010.674-102
dc.identifier.epage125
dc.identifier.scopus2-s2.0-77954581394
dc.identifier.spage118
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-77954581394&doi=10.2316%2fp.2010.674-102&partnerID=40&md5=2176ea73f290265c751508c98a1d0ee5
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/30697
dc.pagecount7
dc.publisherActa Pressen_US
dc.sourceScopus
dc.sourcetitleProceedings of the 10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010
dc.subjectAdaptive resonance theory
dc.subjectFault detection and diagnosis
dc.subjectNetwork pruning
dc.subjectRule extraction
dc.titleFault detection and diagnosis using an art-based neural networken_US
dc.typeConference paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS