Detection and classification of short-circuit faults on a transmission line using current signal
This study offers two Support Vector Machine (SVM) models for fault detection and fault classification, respectively. Different short circuit events were generated using a 154 kV transmission line modeled in MATLAB/Simulink software. Discrete Wavelet Transform (DWT) is performed to the measured sing...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Polish Academy of Sciences
2021-06-01
|
Series: | Bulletin of the Polish Academy of Sciences: Technical Sciences |
Subjects: | |
Online Access: | https://journals.pan.pl/Content/119905/PDF/11_02316_Bpast.No.69(4)_27.08.21_druk.pdf |
_version_ | 1811314152176615424 |
---|---|
author | Melih Coban Suleyman S. Tezcan |
author_facet | Melih Coban Suleyman S. Tezcan |
author_sort | Melih Coban |
collection | DOAJ |
description | This study offers two Support Vector Machine (SVM) models for fault detection and fault classification, respectively. Different short circuit events were generated using a 154 kV transmission line modeled in MATLAB/Simulink software. Discrete Wavelet Transform (DWT) is performed to the measured single terminal current signals before fault detection stage. Three level wavelet energies obtained for each of three-phase currents were used as input features for the detector. After fault detection, half cycle (10 ms) of three-phase current signals was recorded by 20 kHz sampling rate. The recorded currents signals were used as input parameters for the multi class SVM classifier. The results of the validation tests have demonstrated that a quite reliable, fault detection and classification system can be developed using SVM. Generated faults were used to training and testing of the SVM classifiers. SVM based classification and detection model was fully implemented in MATLAB software. These models were comprehensively tested under different conditions. The effects of the fault impedance, fault inception angle, mother wavelet, and fault location were investigated. Finally, simulation results verify that the offered study can be used for fault detection and classification on the transmission line. |
first_indexed | 2024-04-13T11:06:47Z |
format | Article |
id | doaj.art-a17b35f4fc87494aa0f79e54763b5cd3 |
institution | Directory Open Access Journal |
issn | 2300-1917 |
language | English |
last_indexed | 2024-04-13T11:06:47Z |
publishDate | 2021-06-01 |
publisher | Polish Academy of Sciences |
record_format | Article |
series | Bulletin of the Polish Academy of Sciences: Technical Sciences |
spelling | doaj.art-a17b35f4fc87494aa0f79e54763b5cd32022-12-22T02:49:15ZengPolish Academy of SciencesBulletin of the Polish Academy of Sciences: Technical Sciences2300-19172021-06-01694https://doi.org/10.24425/bpasts.2021.137630Detection and classification of short-circuit faults on a transmission line using current signalMelih Coban0https://orcid.org/0000-0001-9528-7187Suleyman S. Tezcan1https://orcid.org/0000-0001-6846-8222Bolu Abant Izzet Baysal University, Bolu, TurkeyGazi University, Ankara, TurkeyThis study offers two Support Vector Machine (SVM) models for fault detection and fault classification, respectively. Different short circuit events were generated using a 154 kV transmission line modeled in MATLAB/Simulink software. Discrete Wavelet Transform (DWT) is performed to the measured single terminal current signals before fault detection stage. Three level wavelet energies obtained for each of three-phase currents were used as input features for the detector. After fault detection, half cycle (10 ms) of three-phase current signals was recorded by 20 kHz sampling rate. The recorded currents signals were used as input parameters for the multi class SVM classifier. The results of the validation tests have demonstrated that a quite reliable, fault detection and classification system can be developed using SVM. Generated faults were used to training and testing of the SVM classifiers. SVM based classification and detection model was fully implemented in MATLAB software. These models were comprehensively tested under different conditions. The effects of the fault impedance, fault inception angle, mother wavelet, and fault location were investigated. Finally, simulation results verify that the offered study can be used for fault detection and classification on the transmission line.https://journals.pan.pl/Content/119905/PDF/11_02316_Bpast.No.69(4)_27.08.21_druk.pdftransmission linefault detectionfault classificationsupport vector machine |
spellingShingle | Melih Coban Suleyman S. Tezcan Detection and classification of short-circuit faults on a transmission line using current signal Bulletin of the Polish Academy of Sciences: Technical Sciences transmission line fault detection fault classification support vector machine |
title | Detection and classification of short-circuit faults on a transmission line using current signal |
title_full | Detection and classification of short-circuit faults on a transmission line using current signal |
title_fullStr | Detection and classification of short-circuit faults on a transmission line using current signal |
title_full_unstemmed | Detection and classification of short-circuit faults on a transmission line using current signal |
title_short | Detection and classification of short-circuit faults on a transmission line using current signal |
title_sort | detection and classification of short circuit faults on a transmission line using current signal |
topic | transmission line fault detection fault classification support vector machine |
url | https://journals.pan.pl/Content/119905/PDF/11_02316_Bpast.No.69(4)_27.08.21_druk.pdf |
work_keys_str_mv | AT melihcoban detectionandclassificationofshortcircuitfaultsonatransmissionlineusingcurrentsignal AT suleymanstezcan detectionandclassificationofshortcircuitfaultsonatransmissionlineusingcurrentsignal |