Detection and Classification of High Impedance Fault in Nigerian 330 kV Transmission Network using ANN: A Case Study of the Southeast Transmission Network

Abstract

High Impedance Fault (HIF) occurs when an energized conductor comes in direct or indirect contact with a quasi-insulator. If not detected and eradicated, it would lead to fire outbreak, pose a risk to human lives, and negate the existing environmental friendliness. The transmission lines data of the 330 kV, south east Nigeria network were obtained and modeled in SIMULINK for the detection and classification of the HIF. The transmission lines modeled were from Afam GS (Generating Station) to Alaoji GS, Alaoji GS to Owerri GS, Alaoji GS to Onitsha TS (Transmission Station), and from Onitsha TS to New Heaven TS. The HIF was situated on the 25 km transmission line connecting Afam GS to Alaji GS which was the central part of the Network. The current signal for each of the HIF classes at each location was used as the input data to the Artificial Neural Network (ANN) model with the HIF classification code used as the ANN target. On inserting the developed ANN in the transmission network and testing its performance, it was observed that the maximum HIF classification deviation occurred on the transmission line connecting Alaoji and Onitsha (two phase HIF) at 0.003 (0.15%). This proved that ANN model is capable and suitable in HIF detection and classification on transmission line network in South East.