New ANN method for multi-terminal HVDC protection relaying

Qingqing Yang, Simon Le Blond, Raj Aggarwal, Yawei Wang, Jianwei Li

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

This paper proposes a comprehensive novel multi-terminal HVDC protection scheme based on artificial neural network (ANN) and high frequency components detected from fault current signals only. The method is shown to accurately detect, classify and locate overhead line faults. Unlike existing travelling wave based methods which must capture the initial wavefront and require high sampling rates, the new approach is more robust since it gives accurate fault detection and fault location over a range of windowed post-fault signals. Furthermore, the proposed method is fault resistance independent meaning even a very high fault impedance has no effect on accurate fault location. A three-terminal VSC-HVDC system is modelled in PSCAD/EMTDC, which is used for obtaining the fault current data for transmission line terminals. The method is verified by studying different cases with a range of fault resistances in various fault locations, and in addition, external faults. The results show that the proposed method gives fast (<5 ms) and reliable (100%) fault detection and classification and accurate location (<1.16%) for DC line faults.

LanguageEnglish
Pages192-201
Number of pages10
JournalElectric Power Systems Research
Volume148
Early online date7 Apr 2017
DOIs
StatusPublished - 1 Jul 2017

Fingerprint

Electric fault location
Electric fault currents
Neural networks
Fault detection
Overhead lines
Wavefronts
Electric lines
Sampling

Keywords

  • Artificial neural network
  • Fault current signal
  • Fault detection
  • Fault location
  • Transmission line
  • VSC-HVDC system

Cite this

New ANN method for multi-terminal HVDC protection relaying. / Yang, Qingqing; Le Blond, Simon; Aggarwal, Raj; Wang, Yawei; Li, Jianwei.

In: Electric Power Systems Research, Vol. 148, 01.07.2017, p. 192-201.

Research output: Contribution to journalArticle

Yang, Qingqing ; Le Blond, Simon ; Aggarwal, Raj ; Wang, Yawei ; Li, Jianwei. / New ANN method for multi-terminal HVDC protection relaying. In: Electric Power Systems Research. 2017 ; Vol. 148. pp. 192-201.
@article{f9bafa91149e43c19d62dacbfd0debc5,
title = "New ANN method for multi-terminal HVDC protection relaying",
abstract = "This paper proposes a comprehensive novel multi-terminal HVDC protection scheme based on artificial neural network (ANN) and high frequency components detected from fault current signals only. The method is shown to accurately detect, classify and locate overhead line faults. Unlike existing travelling wave based methods which must capture the initial wavefront and require high sampling rates, the new approach is more robust since it gives accurate fault detection and fault location over a range of windowed post-fault signals. Furthermore, the proposed method is fault resistance independent meaning even a very high fault impedance has no effect on accurate fault location. A three-terminal VSC-HVDC system is modelled in PSCAD/EMTDC, which is used for obtaining the fault current data for transmission line terminals. The method is verified by studying different cases with a range of fault resistances in various fault locations, and in addition, external faults. The results show that the proposed method gives fast (<5 ms) and reliable (100{\%}) fault detection and classification and accurate location (<1.16{\%}) for DC line faults.",
keywords = "Artificial neural network, Fault current signal, Fault detection, Fault location, Transmission line, VSC-HVDC system",
author = "Qingqing Yang and {Le Blond}, Simon and Raj Aggarwal and Yawei Wang and Jianwei Li",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.epsr.2017.03.024",
language = "English",
volume = "148",
pages = "192--201",
journal = "Electric Power Systems Research",
issn = "0378-7796",
publisher = "Elsevier",

}

TY - JOUR

T1 - New ANN method for multi-terminal HVDC protection relaying

AU - Yang, Qingqing

AU - Le Blond, Simon

AU - Aggarwal, Raj

AU - Wang, Yawei

AU - Li, Jianwei

PY - 2017/7/1

Y1 - 2017/7/1

N2 - This paper proposes a comprehensive novel multi-terminal HVDC protection scheme based on artificial neural network (ANN) and high frequency components detected from fault current signals only. The method is shown to accurately detect, classify and locate overhead line faults. Unlike existing travelling wave based methods which must capture the initial wavefront and require high sampling rates, the new approach is more robust since it gives accurate fault detection and fault location over a range of windowed post-fault signals. Furthermore, the proposed method is fault resistance independent meaning even a very high fault impedance has no effect on accurate fault location. A three-terminal VSC-HVDC system is modelled in PSCAD/EMTDC, which is used for obtaining the fault current data for transmission line terminals. The method is verified by studying different cases with a range of fault resistances in various fault locations, and in addition, external faults. The results show that the proposed method gives fast (<5 ms) and reliable (100%) fault detection and classification and accurate location (<1.16%) for DC line faults.

AB - This paper proposes a comprehensive novel multi-terminal HVDC protection scheme based on artificial neural network (ANN) and high frequency components detected from fault current signals only. The method is shown to accurately detect, classify and locate overhead line faults. Unlike existing travelling wave based methods which must capture the initial wavefront and require high sampling rates, the new approach is more robust since it gives accurate fault detection and fault location over a range of windowed post-fault signals. Furthermore, the proposed method is fault resistance independent meaning even a very high fault impedance has no effect on accurate fault location. A three-terminal VSC-HVDC system is modelled in PSCAD/EMTDC, which is used for obtaining the fault current data for transmission line terminals. The method is verified by studying different cases with a range of fault resistances in various fault locations, and in addition, external faults. The results show that the proposed method gives fast (<5 ms) and reliable (100%) fault detection and classification and accurate location (<1.16%) for DC line faults.

KW - Artificial neural network

KW - Fault current signal

KW - Fault detection

KW - Fault location

KW - Transmission line

KW - VSC-HVDC system

UR - http://www.scopus.com/inward/record.url?scp=85017103892&partnerID=8YFLogxK

UR - https://doi.org/10.1016/j.epsr.2017.03.024

U2 - 10.1016/j.epsr.2017.03.024

DO - 10.1016/j.epsr.2017.03.024

M3 - Article

VL - 148

SP - 192

EP - 201

JO - Electric Power Systems Research

T2 - Electric Power Systems Research

JF - Electric Power Systems Research

SN - 0378-7796

ER -