Skip to main content

Artificial Neural Network Based Fault Classification and Location for Transmission Lines

Research Authors
Ahmed Elnozahy,
Khairy Sayed,
Mohamed Bahyeldin.
Research Department
Research Year
2019
Research Journal
2019 IEEE Conference on Power Electronics and Renewable Energy (CPERE)
Research Publisher
IEEE
Research Vol
NULL
Research Rank
3
Research_Pages
pp. 140-144
Research Website
https://ieeexplore.ieee.org/document/8980173
Research Abstract

Due to various faults occur to transmission lines
and because it was necessary to find and recover these faults
quickly as possible. This paper discussing fault detection,
classification and determining fault location as fast as possible
via Artificial Neural Network (ANN) algorithm. The software
used for modeling the proposed network is a
MATLAB/SIMULINK software environment. The training,
testing and evaluation of the intelligent locator processes are
done based on a multilayer Perceptron feed forward neural
network with back propagation algorithm. Mean Square Error
(MSE) algorithm is used to evaluate the performance of the
detector/classifier as well as fault locator. The results show that
the validation performance (MSE) for the fault
detector/classifier is 2.36e-9 and for fault locator is 2.179e-5.
The system can detect if there is a fault or not, can classify the
fault type and determine the fault location very precisely.