VHDL modeling for classification of power quality disturbance employing wavelet transform, artificial neural network and fuzzy logic

Md. Mamun Ibne Reaz, F. Choong, F. Mohd-Yasin

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

The identification and classification of voltage and current disturbances are important tasks in the monitoring and protection of power systems. Most power quality disturbances are non-stationary and transitory and both detection and classification have proved to be very demanding. New intelligent system technologies that use wavelet transforms, expert systems and artificial neural networks include some unique advantages regarding fault analysis. This paper presents a new approach to classifying six classes of signals: five types of disturbance including sag, swell, transient, fluctuation, interruption, and the normal waveform. The concept of discrete wavelet transform for feature extraction from the power disturbance signal, combined with an artificial neural network and incorporating fuzzy logic to offer a powerful tool for detecting and classifying power quality problems, is introduced. The system was modeled using VHDL, a hardware description language, followed by extensive testing and simulation to verify the functionality of the system that allows efficient hardware implementation of the same. The extensive simulation results confirm the feasibility of the proposed algorithm. This method proposed herein classified and obtained 98.19% classification accuracy from the application of this system to software-generated signals and utility sampled disturbance events.

Original languageEnglish
Pages (from-to)867-881
Number of pages15
JournalSimulation
Volume82
Issue number12
DOIs
Publication statusPublished - Jan 2006
Externally publishedYes

Fingerprint

Computer hardware description languages
Power Quality
Power quality
Wavelet transforms
Wavelet Transform
Fuzzy Logic
Fuzzy logic
Artificial Neural Network
Disturbance
Neural networks
Modeling
Discrete wavelet transforms
Intelligent systems
Expert systems
Feature extraction
Fault Analysis
Hardware
Hardware Implementation
Intelligent Systems
Expert System

Keywords

  • Artificial neural network
  • Fuzzy logic
  • Modeling
  • Power quality
  • VHDL
  • Wavelet transform

ASJC Scopus subject areas

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computer Graphics and Computer-Aided Design
  • Software
  • Safety, Risk, Reliability and Quality

Cite this

VHDL modeling for classification of power quality disturbance employing wavelet transform, artificial neural network and fuzzy logic. / Ibne Reaz, Md. Mamun; Choong, F.; Mohd-Yasin, F.

In: Simulation, Vol. 82, No. 12, 01.2006, p. 867-881.

Research output: Contribution to journalArticle

@article{7064e98ad5b142f39c8a86ba536111f9,
title = "VHDL modeling for classification of power quality disturbance employing wavelet transform, artificial neural network and fuzzy logic",
abstract = "The identification and classification of voltage and current disturbances are important tasks in the monitoring and protection of power systems. Most power quality disturbances are non-stationary and transitory and both detection and classification have proved to be very demanding. New intelligent system technologies that use wavelet transforms, expert systems and artificial neural networks include some unique advantages regarding fault analysis. This paper presents a new approach to classifying six classes of signals: five types of disturbance including sag, swell, transient, fluctuation, interruption, and the normal waveform. The concept of discrete wavelet transform for feature extraction from the power disturbance signal, combined with an artificial neural network and incorporating fuzzy logic to offer a powerful tool for detecting and classifying power quality problems, is introduced. The system was modeled using VHDL, a hardware description language, followed by extensive testing and simulation to verify the functionality of the system that allows efficient hardware implementation of the same. The extensive simulation results confirm the feasibility of the proposed algorithm. This method proposed herein classified and obtained 98.19{\%} classification accuracy from the application of this system to software-generated signals and utility sampled disturbance events.",
keywords = "Artificial neural network, Fuzzy logic, Modeling, Power quality, VHDL, Wavelet transform",
author = "{Ibne Reaz}, {Md. Mamun} and F. Choong and F. Mohd-Yasin",
year = "2006",
month = "1",
doi = "10.1177/0037549707077782",
language = "English",
volume = "82",
pages = "867--881",
journal = "Simulation",
issn = "0037-5497",
publisher = "SAGE Publications Ltd",
number = "12",

}

TY - JOUR

T1 - VHDL modeling for classification of power quality disturbance employing wavelet transform, artificial neural network and fuzzy logic

AU - Ibne Reaz, Md. Mamun

AU - Choong, F.

AU - Mohd-Yasin, F.

PY - 2006/1

Y1 - 2006/1

N2 - The identification and classification of voltage and current disturbances are important tasks in the monitoring and protection of power systems. Most power quality disturbances are non-stationary and transitory and both detection and classification have proved to be very demanding. New intelligent system technologies that use wavelet transforms, expert systems and artificial neural networks include some unique advantages regarding fault analysis. This paper presents a new approach to classifying six classes of signals: five types of disturbance including sag, swell, transient, fluctuation, interruption, and the normal waveform. The concept of discrete wavelet transform for feature extraction from the power disturbance signal, combined with an artificial neural network and incorporating fuzzy logic to offer a powerful tool for detecting and classifying power quality problems, is introduced. The system was modeled using VHDL, a hardware description language, followed by extensive testing and simulation to verify the functionality of the system that allows efficient hardware implementation of the same. The extensive simulation results confirm the feasibility of the proposed algorithm. This method proposed herein classified and obtained 98.19% classification accuracy from the application of this system to software-generated signals and utility sampled disturbance events.

AB - The identification and classification of voltage and current disturbances are important tasks in the monitoring and protection of power systems. Most power quality disturbances are non-stationary and transitory and both detection and classification have proved to be very demanding. New intelligent system technologies that use wavelet transforms, expert systems and artificial neural networks include some unique advantages regarding fault analysis. This paper presents a new approach to classifying six classes of signals: five types of disturbance including sag, swell, transient, fluctuation, interruption, and the normal waveform. The concept of discrete wavelet transform for feature extraction from the power disturbance signal, combined with an artificial neural network and incorporating fuzzy logic to offer a powerful tool for detecting and classifying power quality problems, is introduced. The system was modeled using VHDL, a hardware description language, followed by extensive testing and simulation to verify the functionality of the system that allows efficient hardware implementation of the same. The extensive simulation results confirm the feasibility of the proposed algorithm. This method proposed herein classified and obtained 98.19% classification accuracy from the application of this system to software-generated signals and utility sampled disturbance events.

KW - Artificial neural network

KW - Fuzzy logic

KW - Modeling

KW - Power quality

KW - VHDL

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=34250339338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250339338&partnerID=8YFLogxK

U2 - 10.1177/0037549707077782

DO - 10.1177/0037549707077782

M3 - Article

AN - SCOPUS:34250339338

VL - 82

SP - 867

EP - 881

JO - Simulation

JF - Simulation

SN - 0037-5497

IS - 12

ER -