Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals

Nguyen Thi Ngoc Tho, Chandan Kumar Chakrabarty, Keem Siah Yap, Ahmad Basri Abd Ghani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Magnetic sensor is a relatively new method to collect time-resolved partial discharge (PD) signals in XLPE cables. This paper proposes a simple yet effective method to recognize patterns of PD signals obtained from the magnetic sensor. The technique consists of wavelet transformation to de-noise the signals, statistical analysis to extract features and multi-layer perceptron back propagation (MLP BP) neural network to classify different types of PD signals. The result is elaborated in this paper.

Original languageEnglish
Title of host publication2011 IEEE Conference on Open Systems, ICOS 2011
Pages243-246
Number of pages4
DOIs
Publication statusPublished - 2011
Event2nd IEEE International Conference on Open Systems, ICOS 2011 - Langkawi, Malaysia
Duration: 25 Sep 201128 Sep 2011

Other

Other2nd IEEE International Conference on Open Systems, ICOS 2011
CountryMalaysia
CityLangkawi
Period25/09/1128/09/11

Fingerprint

Partial discharges
Pattern recognition
Feature extraction
Magnetic sensors
Neural networks
Multilayer neural networks
Backpropagation
Statistical methods
Cables

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Software

Cite this

Tho, Nguyen Thi Ngoc ; Kumar Chakrabarty, Chandan ; Yap, Keem Siah ; Ghani, Ahmad Basri Abd. / Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals. 2011 IEEE Conference on Open Systems, ICOS 2011. 2011. pp. 243-246
@inproceedings{4d878282085a4960a02359eddbd39bf3,
title = "Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals",
abstract = "Magnetic sensor is a relatively new method to collect time-resolved partial discharge (PD) signals in XLPE cables. This paper proposes a simple yet effective method to recognize patterns of PD signals obtained from the magnetic sensor. The technique consists of wavelet transformation to de-noise the signals, statistical analysis to extract features and multi-layer perceptron back propagation (MLP BP) neural network to classify different types of PD signals. The result is elaborated in this paper.",
author = "Tho, {Nguyen Thi Ngoc} and {Kumar Chakrabarty}, Chandan and Yap, {Keem Siah} and Ghani, {Ahmad Basri Abd}",
year = "2011",
doi = "10.1109/ICOS.2011.6079231",
language = "English",
isbn = "9781612849317",
pages = "243--246",
booktitle = "2011 IEEE Conference on Open Systems, ICOS 2011",

}

Tho, NTN, Kumar Chakrabarty, C, Yap, KS & Ghani, ABA 2011, Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals. in 2011 IEEE Conference on Open Systems, ICOS 2011., 6079231, pp. 243-246, 2nd IEEE International Conference on Open Systems, ICOS 2011, Langkawi, Malaysia, 25/09/11. https://doi.org/10.1109/ICOS.2011.6079231

Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals. / Tho, Nguyen Thi Ngoc; Kumar Chakrabarty, Chandan; Yap, Keem Siah; Ghani, Ahmad Basri Abd.

2011 IEEE Conference on Open Systems, ICOS 2011. 2011. p. 243-246 6079231.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Feature extraction method and neural network pattern recognition on time-resolved partial discharge signals

AU - Tho, Nguyen Thi Ngoc

AU - Kumar Chakrabarty, Chandan

AU - Yap, Keem Siah

AU - Ghani, Ahmad Basri Abd

PY - 2011

Y1 - 2011

N2 - Magnetic sensor is a relatively new method to collect time-resolved partial discharge (PD) signals in XLPE cables. This paper proposes a simple yet effective method to recognize patterns of PD signals obtained from the magnetic sensor. The technique consists of wavelet transformation to de-noise the signals, statistical analysis to extract features and multi-layer perceptron back propagation (MLP BP) neural network to classify different types of PD signals. The result is elaborated in this paper.

AB - Magnetic sensor is a relatively new method to collect time-resolved partial discharge (PD) signals in XLPE cables. This paper proposes a simple yet effective method to recognize patterns of PD signals obtained from the magnetic sensor. The technique consists of wavelet transformation to de-noise the signals, statistical analysis to extract features and multi-layer perceptron back propagation (MLP BP) neural network to classify different types of PD signals. The result is elaborated in this paper.

UR - http://www.scopus.com/inward/record.url?scp=83155163787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83155163787&partnerID=8YFLogxK

U2 - 10.1109/ICOS.2011.6079231

DO - 10.1109/ICOS.2011.6079231

M3 - Conference contribution

SN - 9781612849317

SP - 243

EP - 246

BT - 2011 IEEE Conference on Open Systems, ICOS 2011

ER -