Real time Fault Detection and Diagnosis (FDD) is an important area of research interest in Knowledge Based Expert Systems. Neurocomputing is one of fastest growing areas of research in the fields of Artificial Intelligence and Pattern Recognition. This paper explores the suitability of pattern classification approach of neural networks for fault detection and diagnosis. Suitability of using neural network as pattern classifiers for power system fault diagnosis is described in detail. A neural network design and simulation environment for real-time FDD is presented. An Analysis of the learning, recall and generalization charecterstisc of the neural network diagnostic system is presented and discussed in detail.
h i g a l o r e-560 012 , INDIA eniail. blianu~live.iisc.eriiet.iii AICISTHAC'I' Object Orieiitecl Metliotlology (OOM) lins rcldctl a IICIV clinreesioti for tire represetitation, madelirig rntl siinul:ttion of v:irious day-to-clay applicatioIis. 'l'lic brisic prrrdigin of OOM reflects ~IIC closc~icss to ivliicli (lie nictliodology rclrtes lo tlic rcal world entities. Over a I)eriotl of tiiiic, tlie requiretiietit of tletnilecl atitl exact represoitntioti with no npp-oxiinntioii or rcal world objects tlint reflccts i t s bciitiviornl pattern is on tile rise. 'I'liis has reseltccl ia tlie terminology of 'Coiiiplex Objccts' in systeni sinidation. hi AC-MTDC systciii bas several ialcrrelatccll iiitcrcoiincctcci compoiieiits aircl pose SI complex picture. 0l)jectifying such system will render tlic systeiii design/ analysis/ identification/ perforeisiicc cvalualion and control, niore easy aiiti iicll) in better unclerstaecliiig o f (lie systeir i i i its aitirety. 111 (Inis paper, n full relwesctitntion of the various I)C syste~iis sub coliil)oticiits arc risctl fur clcvclupiiig ciassc~ of compoiients. Detrilecl representntioti nlorig with tlic various a1 tributes aiicl nictliotlologics associatecl with each o f these conipoiients arc rc~)resentetl. The case study underla kcii in this I)aper is a Four 'I'crniianl AUM'I'DC systeiii with a l l its ternii1i:il c o i i i~~o i i e~i~s. '1'11~ paper liigliligiits the various aclvniilagcs tlic OORl teclinique offers f o r I'o~vcr Systcn~ Modeliiig. This nolatiori is of iiiiinciisc Iicll) esl)ecially (luring tlic systeiii tlcsigii st;~pc wherciii the tuning of various systciii con~l~onents can be acliicvcrl without unrlcrgoiiig tlie rigor of the conventioaal niethocls. KEY W O W S : Object Oriented Mctliocls (OOM), Objcct Oriciitecl 1)esign (OOD), Objcct Or-iciitctl Analysis (OOA), IlVDC l'raasmission Systeni, Systeni Simulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.