A Novel Approach to the Classification of the Transient Phenomena in Power Transformers Using Combined Wavelet Transform and Neural Network

P L Mao, R K Aggarwal

Research output: Contribution to journalArticle

182 Citations (Scopus)

Abstract

The wavelet transform is a powerful tool in the analysis of the power transformer transient phenomena because of its ability to extract information from the transient signals simultaneously in both the time and frequency domain. This paper presents a novel technique for accurate discrimination between an intemal fault and a magnetizing inrush current in the power transformer by combining wavelet transforms with neural networks. The wavelet transform is first applied to decompose the differential current signals of the power transformer into a series of detailed wavelet components. The spectral energies of the wavelet components are calculated and then employed to train a neural network to discriminate an intemal fault from the magnetizing inrush current. The simulated results presented clearly show that the proposed technique can accurately discriminate between an intemal fault and a magnetizing inrush current in power transformer protection.
Original languageEnglish
Pages (from-to)70-70
Number of pages1
JournalPower Engineering Review, IEEE
Volume21
Issue number7
Publication statusPublished - 2001

Fingerprint

Power transformers
Wavelet transforms
Neural networks
Transformer protection

Keywords

  • wavelet transform
  • magnetizing inrush current
  • Power transformer
  • artificial neural network
  • fault detection

Cite this

@article{566c891577a849dd8fe0bd1cfcc5a7cf,
title = "A Novel Approach to the Classification of the Transient Phenomena in Power Transformers Using Combined Wavelet Transform and Neural Network",
abstract = "The wavelet transform is a powerful tool in the analysis of the power transformer transient phenomena because of its ability to extract information from the transient signals simultaneously in both the time and frequency domain. This paper presents a novel technique for accurate discrimination between an intemal fault and a magnetizing inrush current in the power transformer by combining wavelet transforms with neural networks. The wavelet transform is first applied to decompose the differential current signals of the power transformer into a series of detailed wavelet components. The spectral energies of the wavelet components are calculated and then employed to train a neural network to discriminate an intemal fault from the magnetizing inrush current. The simulated results presented clearly show that the proposed technique can accurately discriminate between an intemal fault and a magnetizing inrush current in power transformer protection.",
keywords = "wavelet transform, magnetizing inrush current, Power transformer, artificial neural network, fault detection",
author = "Mao, {P L} and Aggarwal, {R K}",
year = "2001",
language = "English",
volume = "21",
pages = "70--70",
journal = "Power Engineering Review, IEEE",
issn = "0272-1724",
publisher = "IEEE",
number = "7",

}

TY - JOUR

T1 - A Novel Approach to the Classification of the Transient Phenomena in Power Transformers Using Combined Wavelet Transform and Neural Network

AU - Mao, P L

AU - Aggarwal, R K

PY - 2001

Y1 - 2001

N2 - The wavelet transform is a powerful tool in the analysis of the power transformer transient phenomena because of its ability to extract information from the transient signals simultaneously in both the time and frequency domain. This paper presents a novel technique for accurate discrimination between an intemal fault and a magnetizing inrush current in the power transformer by combining wavelet transforms with neural networks. The wavelet transform is first applied to decompose the differential current signals of the power transformer into a series of detailed wavelet components. The spectral energies of the wavelet components are calculated and then employed to train a neural network to discriminate an intemal fault from the magnetizing inrush current. The simulated results presented clearly show that the proposed technique can accurately discriminate between an intemal fault and a magnetizing inrush current in power transformer protection.

AB - The wavelet transform is a powerful tool in the analysis of the power transformer transient phenomena because of its ability to extract information from the transient signals simultaneously in both the time and frequency domain. This paper presents a novel technique for accurate discrimination between an intemal fault and a magnetizing inrush current in the power transformer by combining wavelet transforms with neural networks. The wavelet transform is first applied to decompose the differential current signals of the power transformer into a series of detailed wavelet components. The spectral energies of the wavelet components are calculated and then employed to train a neural network to discriminate an intemal fault from the magnetizing inrush current. The simulated results presented clearly show that the proposed technique can accurately discriminate between an intemal fault and a magnetizing inrush current in power transformer protection.

KW - wavelet transform

KW - magnetizing inrush current

KW - Power transformer

KW - artificial neural network

KW - fault detection

M3 - Article

VL - 21

SP - 70

EP - 70

JO - Power Engineering Review, IEEE

JF - Power Engineering Review, IEEE

SN - 0272-1724

IS - 7

ER -