Volume 12, Issue 4 (December 2016)                   IJEEE 2016, 12(4): 292-300 | Back to browse issues page

XML Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Mollanezhad Heydarabadi M, Akbari Foroud A. Current Directional Protection of Series Compensated Line Using Intelligent Classifier. IJEEE 2016; 12 (4) :292-300
URL: http://ijeee.iust.ac.ir/article-1-928-en.html
Abstract:   (5421 Views)

Current inversion condition leads to incorrect operation of current based directional relay in power system with series compensated device. Application of the intelligent system for fault direction classification has been suggested in this paper. A new current directional protection scheme based on intelligent classifier is proposed for the series compensated line. The proposed classifier uses only half cycle of pre-fault and post fault current samples at relay location to feed the classifier. A lot of forward and backward fault simulations under different system conditions upon a transmission line with a fixed series capacitor are carried out using PSCAD/EMTDC software. The applicability of decision tree (DT), probabilistic neural network (PNN) and support vector machine (SVM) are investigated using simulated data under different system conditions. The performance comparison of the classifiers indicates that the SVM is a best suitable classifier for fault direction discriminating. The backward faults can be accurately distinguished from forward faults even under current inversion without require to detect of the current inversion condition.

Full-Text [PDF 289 kb]   (2142 Downloads)    
Type of Study: Research Paper | Subject: Protection
Received: 2016/04/15 | Revised: 2017/08/23 | Accepted: 2017/01/26

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License
© 2022 by the authors. Licensee IUST, Tehran, Iran. This is an open access journal distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.