Power disturbance recognition using back-propagation neural networks

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper presents power disturbance recognition using back-propagation neural networks (BPNN). First, the discrete wavelet transform is used to extract the features of the power disturbance waveforms in the form of series coefficients of several levels. The Parseval theory is then utilized to calculate the energy of each level so that the number of coefficients can be reduced; then, the extracted results are used for recognition by the BPNN. Multi-event power disturbances are also fed to the recognition system for testing. From experiment results, the recognition rate is at least 83.67%. It proves the feasibility of the proposed method.

Original languageEnglish
Pages430-433
Number of pages4
Publication statusPublished - 2012 Jan 1
Event2012 International Workshop on Computer Science and Engineering, WCSE 2012 - Hong Kong, Hong Kong
Duration: 2012 Aug 32012 Aug 4

Conference

Conference2012 International Workshop on Computer Science and Engineering, WCSE 2012
CountryHong Kong
CityHong Kong
Period12-08-0312-08-04

Fingerprint

Backpropagation
Neural networks
Discrete wavelet transforms
Testing
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Wang, C-S. (2012). Power disturbance recognition using back-propagation neural networks. 430-433. Paper presented at 2012 International Workshop on Computer Science and Engineering, WCSE 2012, Hong Kong, Hong Kong.
Wang, Chau-Shing. / Power disturbance recognition using back-propagation neural networks. Paper presented at 2012 International Workshop on Computer Science and Engineering, WCSE 2012, Hong Kong, Hong Kong.4 p.
@conference{19de3a0c8b4e49e49f67a73afe93a532,
title = "Power disturbance recognition using back-propagation neural networks",
abstract = "This paper presents power disturbance recognition using back-propagation neural networks (BPNN). First, the discrete wavelet transform is used to extract the features of the power disturbance waveforms in the form of series coefficients of several levels. The Parseval theory is then utilized to calculate the energy of each level so that the number of coefficients can be reduced; then, the extracted results are used for recognition by the BPNN. Multi-event power disturbances are also fed to the recognition system for testing. From experiment results, the recognition rate is at least 83.67{\%}. It proves the feasibility of the proposed method.",
author = "Chau-Shing Wang",
year = "2012",
month = "1",
day = "1",
language = "English",
pages = "430--433",
note = "2012 International Workshop on Computer Science and Engineering, WCSE 2012 ; Conference date: 03-08-2012 Through 04-08-2012",

}

Wang, C-S 2012, 'Power disturbance recognition using back-propagation neural networks' Paper presented at 2012 International Workshop on Computer Science and Engineering, WCSE 2012, Hong Kong, Hong Kong, 12-08-03 - 12-08-04, pp. 430-433.

Power disturbance recognition using back-propagation neural networks. / Wang, Chau-Shing.

2012. 430-433 Paper presented at 2012 International Workshop on Computer Science and Engineering, WCSE 2012, Hong Kong, Hong Kong.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Power disturbance recognition using back-propagation neural networks

AU - Wang, Chau-Shing

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper presents power disturbance recognition using back-propagation neural networks (BPNN). First, the discrete wavelet transform is used to extract the features of the power disturbance waveforms in the form of series coefficients of several levels. The Parseval theory is then utilized to calculate the energy of each level so that the number of coefficients can be reduced; then, the extracted results are used for recognition by the BPNN. Multi-event power disturbances are also fed to the recognition system for testing. From experiment results, the recognition rate is at least 83.67%. It proves the feasibility of the proposed method.

AB - This paper presents power disturbance recognition using back-propagation neural networks (BPNN). First, the discrete wavelet transform is used to extract the features of the power disturbance waveforms in the form of series coefficients of several levels. The Parseval theory is then utilized to calculate the energy of each level so that the number of coefficients can be reduced; then, the extracted results are used for recognition by the BPNN. Multi-event power disturbances are also fed to the recognition system for testing. From experiment results, the recognition rate is at least 83.67%. It proves the feasibility of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85069789141&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069789141&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85069789141

SP - 430

EP - 433

ER -

Wang C-S. Power disturbance recognition using back-propagation neural networks. 2012. Paper presented at 2012 International Workshop on Computer Science and Engineering, WCSE 2012, Hong Kong, Hong Kong.