Extraction of voltage harmonics using multi-layer perceptron neural network

TÜMAY M., MERAL M. E., BAYINDIR K. Ç.

NEURAL COMPUTING & APPLICATIONS, vol.17, pp.585-593, 2008 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 17
  • Publication Date: 2008
  • Doi Number: 10.1007/s00521-007-0154-2
  • Journal Name: NEURAL COMPUTING & APPLICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.585-593
  • Keywords: dynamic voltage restorer, harmonic extraction, multi layer perceptron, neural networks
  • Van Yüzüncü Yıl University Affiliated: No

Abstract

This paper presents a harmonic extraction algorithm using artificial neural networks for Dynamic Voltage Restorers (DVRs). The suggested algorithm employs a feed forward Multi Layer Perceptron (MLP) Neural Network with error back propagation learning to effectively track and extract the 3rd and 5th voltage harmonics. For this purpose, two different MLP neural network structures are constructed and their performances compared. The effects of hidden layer, supervisors and learning rate are also presented. The proposed MLP Neural Network algorithm is trained and tested in MATLAB program environment. The results show that MLP neural network enable to extract each harmonic effectively.