Title :
Neural network approach to power transmission line fault classification
Author :
Wang, Xiao-Ru ; Wu, Si-Tao ; Qian, Qing-Quan
Author_Institution :
Sch. of Electr. Eng., Southwest Jiaotong Univ., Sichuan, China
Abstract :
This paper presents a new solution to fault classification of high voltage transmission lines and shows its effectiveness in digital simulation on a realistic 500 kV power system. The scheme is based on backpropagation and Kohonen neural networks and a comparison between them is made. The Electromagnetic Transients Program (EMTP) is used to obtain fault patterns for the training and testing of neural networks. Feature selection, feature extraction and signal procession are studied and a fast, reliable fault classifier is obtained
Keywords :
backpropagation; fault diagnosis; feature extraction; pattern classification; power engineering computing; power transmission lines; self-organising feature maps; 500 kV; EMTP; Electromagnetic Transients Program; Kohonen neural networks; backpropagation; digital simulation; fault classification; fault classifier; fault patterns; feature extraction; feature selection; high voltage transmission line; neural network approach; power transmission line; Digital simulation; EMTP; Feature extraction; Neural networks; Power system faults; Power system reliability; Power system simulation; Power system transients; Power transmission lines; Voltage;
Conference_Titel :
Information, Communications and Signal Processing, 1997. ICICS., Proceedings of 1997 International Conference on
Print_ISBN :
0-7803-3676-3
DOI :
10.1109/ICICS.1997.652293