Transmission Line Fault Detection and Classification of Multi-Dataset Using Artificial Neural

Ogar, V. N., Gamage, K. A.A. , Hussain, S. and Akpama, E. J. (2021) Transmission Line Fault Detection and Classification of Multi-Dataset Using Artificial Neural. International Conference on Information Technology and Economic Development (ICITED2021), Calabar, Nigeria, 18-20 Nov 2021.

Full text not currently available from Enlighten.

Abstract

This paper focuses on fault classification and detection in the transmission line, and these lines are instrumental in the transportation of electricity from the generation to the distribution station. However, faults always affect the line due to human interference, weather, ageing conductors, and long-distance transmission line. An 11/132 kV, 100 MVA, 50Hz transmission line was modelled using MATLAB/SIMULINK to extract faulty line voltage and current data. The training was carried out for 143 fault cases using the Artificial Neural network's backpropagation algorithm. The individual phases were analysed and subjected to fault detection and classification. A total of 90% of the data was used for training, while validation and testing used 5% each, respectively. 77.6% of the data was ideally classified with Root Mean Square Error (RMSE) of 0.12348, while 22.4% of the remaining data was at a confusing state. Also, RMSE 0.00415 for fault identification was recorded, and 95% of the data were correctly classified at the fault location zone. At the same time, 5% of the data was in a confused state. The proposed model can be helpful in fast and accurate localisation and detection of faults based on their types and severity on the transmission line. This model produces a valid result, easy to use, precision and speed in execution.

Item Type:Conference or Workshop Item
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Ogar, VINCENT and Gamage, Professor Kelum and Hussain, Dr Sajjad
Authors: Ogar, V. N., Gamage, K. A.A., Hussain, S., and Akpama, E. J.
College/School:College of Science and Engineering > School of Engineering > Systems Power and Energy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record