Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines

R K Aggarwal, J I Lorenzo, A L Orille

Research output: Contribution to conferencePaper

Abstract

This paper presents a novel approach to fault detection, faulted phase selection and direction estimation based on artificial neural networks (ANNs). The main target in this work is to find a relay design that is fast with a detection time independent of fault conditions (i.e. current transformer saturation, dynamic arcing faults, short circuit level and system topology) and that uses only unfiltered voltage and current samples, with the same structure and parameters for each relay location in a network. The neural relay is trained globally using training patterns from more than one relaying position in order to be as generic as possible. The CAD of the ANN-based relay is implemented into a hardware model (a DSP evaluation module plugged into a PC) and tested under laboratory conditions via the real-time digital simulation (RTDS) system.
Original languageEnglish
Pages72-75 Vol.1
Publication statusPublished - 2004
EventDevelopments in Power System Protection, 2004. Eighth IEE International Conference on -
Duration: 1 Jan 2004 → …

Conference

ConferenceDevelopments in Power System Protection, 2004. Eighth IEE International Conference on
Period1/01/04 → …

Fingerprint

Relay protection
Electric lines
Neural networks
Electric instrument transformers
Electric potential
Fault detection
Short circuit currents
Computer aided design
Topology
Hardware

Keywords

  • real-time digital simulation
  • power transmission faults
  • faulted phase selection
  • neural relay
  • relay protection
  • unfiltered current samples
  • training patterns
  • high-voltage techniques
  • RTDS
  • ANN
  • CAD
  • direction estimation
  • artificial neural network
  • fault detection
  • protection relay
  • unfiltered voltage samples
  • neural nets
  • high voltage transmission lines

Cite this

Aggarwal, R. K., Lorenzo, J. I., & Orille, A. L. (2004). Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines. 72-75 Vol.1. Paper presented at Developments in Power System Protection, 2004. Eighth IEE International Conference on, .

Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines. / Aggarwal, R K; Lorenzo, J I; Orille, A L.

2004. 72-75 Vol.1 Paper presented at Developments in Power System Protection, 2004. Eighth IEE International Conference on, .

Research output: Contribution to conferencePaper

Aggarwal, RK, Lorenzo, JI & Orille, AL 2004, 'Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines' Paper presented at Developments in Power System Protection, 2004. Eighth IEE International Conference on, 1/01/04, pp. 72-75 Vol.1.
Aggarwal RK, Lorenzo JI, Orille AL. Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines. 2004. Paper presented at Developments in Power System Protection, 2004. Eighth IEE International Conference on, .
Aggarwal, R K ; Lorenzo, J I ; Orille, A L. / Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines. Paper presented at Developments in Power System Protection, 2004. Eighth IEE International Conference on, .
@conference{e67097b5959d4abeb29abc1913980a3c,
title = "Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines",
abstract = "This paper presents a novel approach to fault detection, faulted phase selection and direction estimation based on artificial neural networks (ANNs). The main target in this work is to find a relay design that is fast with a detection time independent of fault conditions (i.e. current transformer saturation, dynamic arcing faults, short circuit level and system topology) and that uses only unfiltered voltage and current samples, with the same structure and parameters for each relay location in a network. The neural relay is trained globally using training patterns from more than one relaying position in order to be as generic as possible. The CAD of the ANN-based relay is implemented into a hardware model (a DSP evaluation module plugged into a PC) and tested under laboratory conditions via the real-time digital simulation (RTDS) system.",
keywords = "real-time digital simulation, power transmission faults, faulted phase selection, neural relay, relay protection, unfiltered current samples, training patterns, high-voltage techniques, RTDS, ANN, CAD, direction estimation, artificial neural network, fault detection, protection relay, unfiltered voltage samples, neural nets, high voltage transmission lines",
author = "Aggarwal, {R K} and Lorenzo, {J I} and Orille, {A L}",
year = "2004",
language = "English",
pages = "72--75 Vol.1",
note = "Developments in Power System Protection, 2004. Eighth IEE International Conference on ; Conference date: 01-01-2004",

}

TY - CONF

T1 - Implementation and laboratory test of a fully integrated neural network based protection relay for high voltage transmission lines

AU - Aggarwal, R K

AU - Lorenzo, J I

AU - Orille, A L

PY - 2004

Y1 - 2004

N2 - This paper presents a novel approach to fault detection, faulted phase selection and direction estimation based on artificial neural networks (ANNs). The main target in this work is to find a relay design that is fast with a detection time independent of fault conditions (i.e. current transformer saturation, dynamic arcing faults, short circuit level and system topology) and that uses only unfiltered voltage and current samples, with the same structure and parameters for each relay location in a network. The neural relay is trained globally using training patterns from more than one relaying position in order to be as generic as possible. The CAD of the ANN-based relay is implemented into a hardware model (a DSP evaluation module plugged into a PC) and tested under laboratory conditions via the real-time digital simulation (RTDS) system.

AB - This paper presents a novel approach to fault detection, faulted phase selection and direction estimation based on artificial neural networks (ANNs). The main target in this work is to find a relay design that is fast with a detection time independent of fault conditions (i.e. current transformer saturation, dynamic arcing faults, short circuit level and system topology) and that uses only unfiltered voltage and current samples, with the same structure and parameters for each relay location in a network. The neural relay is trained globally using training patterns from more than one relaying position in order to be as generic as possible. The CAD of the ANN-based relay is implemented into a hardware model (a DSP evaluation module plugged into a PC) and tested under laboratory conditions via the real-time digital simulation (RTDS) system.

KW - real-time digital simulation

KW - power transmission faults

KW - faulted phase selection

KW - neural relay

KW - relay protection

KW - unfiltered current samples

KW - training patterns

KW - high-voltage techniques

KW - RTDS

KW - ANN

KW - CAD

KW - direction estimation

KW - artificial neural network

KW - fault detection

KW - protection relay

KW - unfiltered voltage samples

KW - neural nets

KW - high voltage transmission lines

M3 - Paper

SP - 72-75 Vol.1

ER -