Expert system for power quality disturbance classifier

Mamun Bin Ibne Reaz, Florence Choong, Mohd Shahiman Sulaiman, Faisal Mohd-Yasin, Masaru Kamada

Research output: Contribution to journalArticle

120 Citations (Scopus)

Abstract

Identification and classification of voltage and current disturbances in power systems are important tasks in the monitoring and protection of power system. Most power quality disturbances are non-stationary and transitory and the detection and classification have proved to be very demanding. The concept of discrete wavelet transform for feature extraction of power disturbance signal combined with artificial neural network and fuzzy logic incorporated as a powerful tool for detecting and classifying power quality problems. This paper employes a different type of univariate randomly optimized neural network combined with discrete wavelet transform and fuzzy logic to have a better power quality disturbance classification accuracy. The disturbances of interest include sag, swell, transient, fluctuation, and interruption. The system is modeled using VHSIC Hardware Description Language (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. This proposed method classifies, and achieves 98.19% classification accuracy for the application of this system on software-generated signals and utility sampled disturbance events.

Original languageEnglish
Pages (from-to)1979-1988
Number of pages10
JournalIEEE Transactions on Power Delivery
Volume22
Issue number3
DOIs
Publication statusPublished - Jul 2007

Keywords

  • Artificial neural network
  • Classification
  • Feature extraction
  • Fuzzy logic
  • Power quality
  • VHSIC hardware description language (VHDL)
  • Wavelet transform

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Expert system for power quality disturbance classifier'. Together they form a unique fingerprint.

  • Cite this