Algorithms for locating faults on series compensated lines using neural network and deterministic methods

Abstract

This paper investigates a scheme to improve the reach measurement of distance relays and fault locators for series compensated power lines. A deterministic method and a feedforward neural network method have been implemented for online calculation of the voltage across a nonlinear capacitor installation. These techniques are compared and incorporated into a new relaying scheme which is independent of the series capacitor installation, operation of the capacitor protection, and the surrounding power system elements. The proposed scheme is simple and accurate and requires only local voltage and current at the bus. Detailed testing using EMTP has been done to show the benefits of the new adaptive scheme. The results demonstrate the suitability of the techniques for real world applications.