Prototyping of wavelet transform, artificial neural network and fuzzy logic for power quality disturbance classifier

Md. Mamun Ibne Reaz, F. Choong, M. S. Sulaiman, F. Mohd-Yasin

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

Identification and classification of voltage and current disturbances in power systems are important tasks in their monitoring and protection. Introduction of knowledge-based approaches, in conjunction with signal processing and decision fusion techniques, enable us to identify delicate power quality related events. This article focuses on the application of wavelet transform technique to extract features from power quality disturbance waveforms and their classification using a combination of artificial neural network and fuzzy logic. The disturbances of interest include sag, swell, transient, fluctuation and interruption waveform. The system is modelled using VHDL and synthesized to Mercury EP1M120F484C5 FPGA, tested and validated. Comparisons, verification and analysis on disturbance signals validate the utility of this approach and achieved a classification accuracy of 98.19%. This novel and efficient method, and also implementation of the method in hardware based on FPGA technology, showed improved performance over existing approaches for power quality disturbance detection and classification.

Original languageEnglish
Pages (from-to)1-17
Number of pages17
JournalElectric Power Components and Systems
Volume35
Issue number1
DOIs
Publication statusPublished - 1 Jan 2007
Externally publishedYes

Fingerprint

Power quality
Wavelet transforms
Fuzzy logic
Classifiers
Neural networks
Field programmable gate arrays (FPGA)
Computer hardware description languages
Signal processing
Fusion reactions
Hardware
Monitoring
Electric potential

Keywords

  • Artificial neural network
  • Classification
  • Feature extraction
  • FPGA
  • Fuzzy logic
  • Power quality
  • VHDL
  • Wavelet transform

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Prototyping of wavelet transform, artificial neural network and fuzzy logic for power quality disturbance classifier. / Ibne Reaz, Md. Mamun; Choong, F.; Sulaiman, M. S.; Mohd-Yasin, F.

In: Electric Power Components and Systems, Vol. 35, No. 1, 01.01.2007, p. 1-17.

Research output: Contribution to journalArticle

@article{86a09bf28b71440c8a4beccafdcf5945,
title = "Prototyping of wavelet transform, artificial neural network and fuzzy logic for power quality disturbance classifier",
abstract = "Identification and classification of voltage and current disturbances in power systems are important tasks in their monitoring and protection. Introduction of knowledge-based approaches, in conjunction with signal processing and decision fusion techniques, enable us to identify delicate power quality related events. This article focuses on the application of wavelet transform technique to extract features from power quality disturbance waveforms and their classification using a combination of artificial neural network and fuzzy logic. The disturbances of interest include sag, swell, transient, fluctuation and interruption waveform. The system is modelled using VHDL and synthesized to Mercury EP1M120F484C5 FPGA, tested and validated. Comparisons, verification and analysis on disturbance signals validate the utility of this approach and achieved a classification accuracy of 98.19{\%}. This novel and efficient method, and also implementation of the method in hardware based on FPGA technology, showed improved performance over existing approaches for power quality disturbance detection and classification.",
keywords = "Artificial neural network, Classification, Feature extraction, FPGA, Fuzzy logic, Power quality, VHDL, Wavelet transform",
author = "{Ibne Reaz}, {Md. Mamun} and F. Choong and Sulaiman, {M. S.} and F. Mohd-Yasin",
year = "2007",
month = "1",
day = "1",
doi = "10.1080/15325000600815431",
language = "English",
volume = "35",
pages = "1--17",
journal = "Electric Power Components and Systems",
issn = "1532-5008",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Prototyping of wavelet transform, artificial neural network and fuzzy logic for power quality disturbance classifier

AU - Ibne Reaz, Md. Mamun

AU - Choong, F.

AU - Sulaiman, M. S.

AU - Mohd-Yasin, F.

PY - 2007/1/1

Y1 - 2007/1/1

N2 - Identification and classification of voltage and current disturbances in power systems are important tasks in their monitoring and protection. Introduction of knowledge-based approaches, in conjunction with signal processing and decision fusion techniques, enable us to identify delicate power quality related events. This article focuses on the application of wavelet transform technique to extract features from power quality disturbance waveforms and their classification using a combination of artificial neural network and fuzzy logic. The disturbances of interest include sag, swell, transient, fluctuation and interruption waveform. The system is modelled using VHDL and synthesized to Mercury EP1M120F484C5 FPGA, tested and validated. Comparisons, verification and analysis on disturbance signals validate the utility of this approach and achieved a classification accuracy of 98.19%. This novel and efficient method, and also implementation of the method in hardware based on FPGA technology, showed improved performance over existing approaches for power quality disturbance detection and classification.

AB - Identification and classification of voltage and current disturbances in power systems are important tasks in their monitoring and protection. Introduction of knowledge-based approaches, in conjunction with signal processing and decision fusion techniques, enable us to identify delicate power quality related events. This article focuses on the application of wavelet transform technique to extract features from power quality disturbance waveforms and their classification using a combination of artificial neural network and fuzzy logic. The disturbances of interest include sag, swell, transient, fluctuation and interruption waveform. The system is modelled using VHDL and synthesized to Mercury EP1M120F484C5 FPGA, tested and validated. Comparisons, verification and analysis on disturbance signals validate the utility of this approach and achieved a classification accuracy of 98.19%. This novel and efficient method, and also implementation of the method in hardware based on FPGA technology, showed improved performance over existing approaches for power quality disturbance detection and classification.

KW - Artificial neural network

KW - Classification

KW - Feature extraction

KW - FPGA

KW - Fuzzy logic

KW - Power quality

KW - VHDL

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=33750190904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750190904&partnerID=8YFLogxK

U2 - 10.1080/15325000600815431

DO - 10.1080/15325000600815431

M3 - Article

AN - SCOPUS:33750190904

VL - 35

SP - 1

EP - 17

JO - Electric Power Components and Systems

JF - Electric Power Components and Systems

SN - 1532-5008

IS - 1

ER -