IEEE Transactions on Power Delivery · 2001 · 107 citations · 12 references
ComputingComputer ScienceElectrical EngineeringMachine LearningPower ElectronicsTime Series AnalysisClassificationElectrical System DiagnosticsFault DetectionFault DiagnosisNeural NetworksPattern RecognitionElectrical Fault DiagnosisFault ClassificationFault Detection Using Machine LearningMachine Learning For Fault DetectionNeural Network ClassificationNeural Network-based DiagnosisRadial Basis Function NetworksRelay Protection
This paper presents a new approach to identify fault types and phases. A transmission line fault classification method based on a radial basis function (RBF) neural network with orthogonal-least-square (OLS) learning procedure was used to identify various patterns of associated voltages and currents. The RBF neural network was also compared with the back-propagation (BP) neural network in this paper. It is shown that the RBF approach can provide a fast and precise operation for various faults. The simulation results also show that the proposed approach can be used as an effective tool for high speed relaying.
12