An effective wavelet-based feature extraction method for classification of power quality disturbance signals


Uyar M., Yildirim S., Gencoglu M. T.

ELECTRIC POWER SYSTEMS RESEARCH, cilt.78, sa.10, ss.1747-1755, 2008 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 78 Sayı: 10
  • Basım Tarihi: 2008
  • Doi Numarası: 10.1016/j.epsr.2008.03.002
  • Dergi Adı: ELECTRIC POWER SYSTEMS RESEARCH
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.1747-1755
  • Anahtar Kelimeler: wavelet & multiresolution analysis, norm entropy, feature extraction, power quality, disturbance classification, neural networks, NEURAL-NETWORK, SYSTEM, TRANSFORM, RECOGNITION
  • Bursa Uludağ Üniversitesi Adresli: Hayır

Özet

This paper presents a wavelet norm entropy-based effective feature extraction method for power quality (PQ)disturbance classification problem. The disturbance classification schema is performed with wavelet neural network (WNN). It performs a feature extraction and a classification algorithm composed of a wavelet feature extractor based on norm entropy and a classifier based on a multi-layer perceptron. The PQ signals used in this study are seven types. The performance of this classifier is evaluated by using total 2800 PQ disturbance signals which are generated the based model. The classification performance of different wavelet family for the proposed algorithm is tested. Sensitivity of WNN under different noise conditions which are different levels of noises with the signal to noise ratio is investigated. The rate of average correct classification is about 92.5% for the different PQ disturbance Signals under noise conditions. (C) 2008 Elsevier B.V. All rights reserved.