A new adaptive hybrid neural network and fuzzy logic based fault classification approach for transmission lines protection

In this paper, an adaptive hybrid neural networks and fuzzy logic based algorithm is proposed to classify fault types in transmission lines. The proposed method is able to identify all ten shunt faults in transmission lines with high level of robustness against variable conditions such as measured amplitudes and fault resistance. In this approach, a two-end unsynchronized measurement of the signals is used. For real-time estimation of unknown synchronization angle and three phase phasors a two-layer adaptive linear neural (ADALINE) network is used. The estimated parameters are fed to a fuzzy logic system to classify fault types. This method is feasible to be used in digital distance relays which are able to be programmed, to share and discourse data with all protective and monitoring devices. The proposed method is evaluated by a number of simulations conducted in PSCAD/EMTDC and MATLAB software.