Improvement of algorithm to reduce training time of back-propagation neural network for transformer interturn fault location

This paper presents an algorithm based on a combination of Discrete Wavelet Transforms and back-propagation neural networks for location of interturn faults in a two-winding three-phase transformer. Fault conditions of the transformer are simulated using ATP/EMTP in order to obtain current signals....

Full description

Saved in:
Bibliographic Details
Main Authors: Ngaopitakkul, A., Pothisarn, C., Klomjit, J., Bunjongjit, S., Suechoey, B., Suttisinthong, N.
Format: Conference Proceeding
Language:English
Subjects:
Biological neural networks
Discrete wavelet transforms
Internal Winding Fault
Mathematical model
Neural Network
Neurons
Training
Transformer
Wavelet analysis
Wavelet Transform
Windings
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents an algorithm based on a combination of Discrete Wavelet Transforms and back-propagation neural networks for location of interturn faults in a two-winding three-phase transformer. Fault conditions of the transformer are simulated using ATP/EMTP in order to obtain current signals. The training process for the neural network and fault diagnosis decision are implemented by MATLAB. In addition, the choice of initial number of neurons for the first hidden layer to decrease duration time of train process is taken into account. A comparison between the proposed technique and conventional training is presented. The result is shown that the proposed technique is very effective in reduce training time and gives a satisfactory accuracy.
ISSN:2158-5695
DOI:10.1109/ICWAPR.2012.6294767