Improved ANN-based algorithm for detection and classification of faults on transmission lines

This paper presents a relaying algorithm based on Artificial Neural Network (ANN) technique for the protection of transmission line. A feed forward ANN with six inputs and eleven outputs has been developed for the detection and classification of faults. Data was generated by simulating a 400 kV, 50H...

Full description

Saved in:
Bibliographic Details
Published in2016 1st India International Conference on Information Processing (IICIP) pp. 1 - 6
Main Authors Fayaz, Farhana, Isa, Abubakar, Verma, H. K., Deb, Soma
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2016
Subjects
artificial neural network
Artificial neural networks
Delays
fault detection
Neurons
phase selection
power system faults
Power transmission lines
Testing
Training
Transmission line matrix methods
transmission line protection
Online AccessGet full text
DOI10.1109/IICIP.2016.7975360

Cover

More Information
Summary:This paper presents a relaying algorithm based on Artificial Neural Network (ANN) technique for the protection of transmission line. A feed forward ANN with six inputs and eleven outputs has been developed for the detection and classification of faults. Data was generated by simulating a 400 kV, 50Hz, 100 km transmission line in PSCAD/EMTDC at a sampling frequency of 2 kHz. Three ANN configurations with different combinations of inputs have been attempted. Initially all the three ANN configurations were trained and tested using truncated data for their comparative performance. ANN-2 configuration has been found to be the best one and has an accuracy of 100% for fault detection and classification in both training and testing phases with the relay operating time of 12.5 ms. ANN-2 has been further trained and tested using full data. Two-fold cross verification was carried out. An accuracy of 100% was obtained on testing with 12.5 ms delay each time.
DOI:10.1109/IICIP.2016.7975360