Three-phase active power filter control using neural networks

Author

Vázquez, J.R. ; Salmerón, P.R.

Author_Institution

Dept. of Electr. Eng, Huelva Univ., Spain

Volume

3

fYear

2000

fDate

29-31 May 2000

Firstpage

924

Abstract

A new control method for active power filters (APF) using neural networks is presented. It is pulse width modulation control (PWM) designed with two blocks that include neural networks. The first one includes adaptive networks that estimate the reference compensation current; adaptive linear neurons (Adaline) were used. The second one includes a feedforward network that works as a hysteresis band comparator; this network is multilayer and it has been trained by a backpropagation algorithm. A practical case with Matlab-Simulink is presented to check the proposed control performance.

Keywords

active filters; adaptive control; backpropagation; feedforward neural nets; multilayer perceptrons; neurocontrollers; power harmonic filters; power supply quality; power system control; power system harmonics; pulse width modulation; Adaline; Matlab-Simulink; adaptive linear neurons; adaptive networks; backpropagation algorithm; feedforward network; harmonics suppression; hysteresis band comparator; multilayer network; neural networks; power quality; pulse width modulation control; reference compensation current estimation; three-phase active power filter control; Active filters; Adaptive systems; Backpropagation algorithms; Computer languages; Hysteresis; Multi-layer neural network; Neural networks; Neurons; Pulse width modulation; Space vector pulse width modulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 2000. MELECON 2000. 10th Mediterranean

Print_ISBN

0-7803-6290-X

Type

conf

DOI

10.1109/MELCON.2000.879683

Filename

879683