Power Quality Disturbance Classification using Decision Fusion

결정결합 방법을 이용한 전력외란 신호의 식별

  • 김기표 (한양대학교 공과대학 전기공학과) ;
  • 김병철 (한양대학교 공과대학 전기공학과) ;
  • 남상원 (한양대학교 공과대학 전기공학과)
  • Published : 2000.09.01

Abstract

In this paper, we propose an efficient feature vector extraction and decision fusion methods for the automatic classification of power system disturbances. Here, FFT and WPT(wavelet packet transform) are und to extract an appropriate feature for classifying power quality disturbances with variable properties. In particular, the WPT can be utilized to develop an adaptable feature extraction algorithm using best basis selection. Furthermore. the extracted feature vectors are applied as input to the decision fusion system which combines the decisions of several classifiers having complementary performances, leading to improvement of the classification performance. Finally, the applicability of the proposed approach is demonstrated using some simulations results obtained by analyzing power quality disturbances data generated by using Matlab.

Keywords