Diagnóstico de faltas em linhas de transmissão baseado em redes neurais artificiais e transformada wavelet.

Abstract

A method based on artificial neural networks and wavelet transforms for fault detection and classification in transmission lines is proposed. The analysis is accomplished in current and voltage waveforms obtained from digital fault recorders. The detection step and the fault interval are achieved by means of a set of rules obtained from the current waveform analysis in the time and wavelet domains. In this step, a fault is distinguished from power quality disturbances such as voltage sags and switching transients. In the case of fault, its classification is accomplished by a neural network, responsible for voltage and current waveforms pattern recognition in time domain. The method has been evaluated for real and simulated faults in transmission lines of CHESF's transmission system, good results were obtained in both cases.