ARTIFICIAL NEURAL NETWORK BASED SMART SHUNT FAULT RECOGNITION SYSTEM FOR THE 33-kV NIGERIA POWER LINES

Mbamaluikem, Peter O and Olabode, Olufemi R and Adedokun, Adedoyin G (2018) ARTIFICIAL NEURAL NETWORK BASED SMART SHUNT FAULT RECOGNITION SYSTEM FOR THE 33-kV NIGERIA POWER LINES. In: 1st International Conference and Exhibition of the Federal Polytechnic, Ilaro, on the Technological Innovation and Global Competitiveness, November 5-8, 2018, International Conference Centre, Federal Polytechnic, Ilaro, Ogun State.

Text ANN smart shunt fault detector.pdf Download (983kB)

Abstract

The Nigeria 33-kV power lines are more exposed to the environment than 330-kV transmission lines and 132-kV sub-transmission lines, hence chances of occurrence of shunt faults in this power lines is very high. Such faults need to be recognized quickly at its occurrence to hasten its clearance in order to forestall power system damages and reduce the system downtime. Consequently, this paper presents a new approach to recognize shunt faults on the 33-kV Nigeria power line network using artificial neural network. The network is modeled and simulated in the MATLAB/Simulink 2015 a environment. This study employed a feed forward neural network with back-propagation algorithm in training the system. The proposed system uses as inputs, instantaneous values of voltages and currents during normal and abnormal situations on the power lines to detect the presence or absence of shunt faults on a particular line. The artificial neural network based smart fault recognition system developed achieved an accuracy of 100% for all shunt fault conditions tested. The results presented show that this approach has the potential to recognize all shunt faults on electric power lines on the 33-kV Nigeria power lines with high level of accuracy.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering, Science and Mathematics > School of Engineering Sciences
Depositing User:	Mr Adedamola Bameke
Date Deposited:	30 Jun 2020 16:53
Last Modified:	30 Jun 2020 16:53
URI:	http://eprints.federalpolyilaro.edu.ng/id/eprint/863

Actions (login required)

View Item