APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR SERIES COMPENSATED LINEPROTECTION

This paper investigates a feedforward neural network (with a quasi-New ton method for minimization of the error function) for on-line calcula tion of the voltage across a non-linear capacitor installation. This t echnique is incorporated into a new scheme which is independent of the series capacitor installation, operation of the capacitor protection. and the surrounding power system elements. The proposed scheme is sim ple and accurate and requires only local voltage and current at the bu s To improve the reach measurement of distance relays and fault locato rs. Detailed testing using EMTP has been done to show the benefits, ro bustness and generalization capabilities of the ANN technique.