Loading…

Comparative Analysis of ANN-Based FL and Travelling Wave-Based FL for Location of Fault on Transmission Lines

This paper attempts to develop a backpropagation neural network algorithm for fault detection and location in overhead transmission lines and high-speed protection system using terminal data. The suggested neural FL is trained using various available sets of data from a selected power system model a...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering Electrical Engineering, Electronics and telecommunication engineering, Computer engineering, 2019-06, Vol.100 (3), p.267-276
Main Authors: Maheshwari, Ashish, Agarwal, Vinesh, Sharma, Sanjeev Kumar
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper attempts to develop a backpropagation neural network algorithm for fault detection and location in overhead transmission lines and high-speed protection system using terminal data. The suggested neural FL is trained using various available sets of data from a selected power system model and simulating distinct fault scenarios (fault location and fault types) and various power system data (source voltages, source capacities and time constant of source). Two ANN-based fault locators (FLs) termed as FL1 and FL2 are recommended for a correlative study of FL. The study is carried out with reference to travelling wave-based FL in order to determine which FL delivers greater performance. The result shows that the proposed ANN-based FL provides better results in locating the fault as compared to travelling wave-based FL. The result also indicates that the recommended ANN-based FL is capable of identifying and determining the different single line to ground fault with greater accuracy.
ISSN:2250-2106
2250-2114
DOI:10.1007/s40031-019-00370-7