Improvement of wavelet based methods for classification of power quality disturbances

Author

Milchevski, Aleksandar ; Taskovski, Dimitar

Author_Institution

Dept. of Electron., Ss Cyril & Methodius Univ., Skopje, Macedonia

fYear

2010

fDate

26-29 Sept. 2010

Firstpage

1

Lastpage

4

Abstract

In this paper an improvement of wavelet based methods for detection and classification of power quality disturbances is presented. In the feature extraction process wavelet analysis is also used as in the comparing methods. However, the feature vector is extended with three other coefficients in order to improve the accuracy of the algorithm. In order to evaluate the proposed method, large number of experiments is performed, using SVM (Support Vector Machines) as a classification method. The obtained classification accuracy is higher than 98%.

Keywords

feature extraction; power supply quality; power system faults; signal classification; support vector machines; wavelet transforms; feature extraction process; feature vector; power quality disturbance classification; support vector machines; wavelet analysis; wavelet based methods; Accuracy; Classification algorithms; Feature extraction; Power quality; Support vector machine classification; Wavelet analysis; Pattern classification; Power Quality; SVM; wavelets;

fLanguage

English

Publisher

ieee

Conference_Titel

Harmonics and Quality of Power (ICHQP), 2010 14th International Conference on

Conference_Location

Bergamo

Print_ISBN

978-1-4244-7244-4

Electronic_ISBN

978-1-4244-7245-1

Type

conf

DOI

10.1109/ICHQP.2010.5625384

Filename

5625384