Detection and Location of High Impedance Fault on the Nigerian 330kV Transmission System Using Artificial Neural Network

Abstract

The effect of the occurrence of high impedance fault (HIF) in power system networks results to low current signal which cannot be detected by the electrical equipment which results to fire outbreaks. Nigerian power system network has witnessed the occurrence of HIF which has led to fire outbreak in buildings and in minor cases grid collapse. In this paper, the performance of ANN in the detection and location of HIF was studied and determined. The transmission network located in south-south region of the Nigerian 330kV power system network was obtained and modeled in SIMULINK. The line distance was split into six points and implemented in the SIMULINK to obtain the current signals at each point of the lines. The current signals were used as the input data with the split distance utilized as the target to the ANN model. The ANN had three input neurons (each neuron represented the phase current signal), the hidden layer had five neurons with each neuron incorporating log sigmoid curve and the output layer having one neuron which was the split distance. The outcome had the least error deviation value of 0.0118 making the performance of ANN effective in the point location of HIF occurrence on the transmission line.