An Integrated Protective Scheme for a multi- ended Egyptian Transmission Line using Radial Basis Neural Network

This paper presents a novel approach to fault detection, faulty phase(s) identification, faulty section estimation, and fault location determination for a multi-ended transmission line in Egypt based on artificial neural networks. In order to perform this approach, the protection task is subdivided into different neural network modules for fault detection, fault classification as well as fault location. The suggested approach uses the Radial Basis Function Artificial Neural Network (RBFANN). The proposed scheme consists of nine RBFANNs, one for fault classification and faulty phase identification, four networks for faulty section estimation one for each fault type, and four networks for fault location within the faulty section, again one for each fault type. The three-phase voltages and currents are sampled at 1 kHz. Pre and post-fault data are utilized as inputs for the proposed scheme. The Electromagnetic Transient Program (EMTP) is used to generate simulation data for the typical Egyptian 500 kV transmission line in normal and faulty conditions to train and test the RBFNN. Testing results proved that the proposed RBF networks could provide great performance for high speed relaying. It is accurate, fast, and reliable.