Harmonic elimination in PWM inverters using neural networks

Author

Mohaddes, M. ; Gole, A.M. ; McLaren, P.G.

Author_Institution

Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada

fYear

1994

fDate

25-28 Sep 1994

Firstpage

64

Abstract

An artificial neural network (ANN) is used to derive the chopping angles for a pulse width modulated inverter. The neural network is trained off line and later implemented in the control system. The AC voltage magnitude order is used as the input to the controller. The ANN outputs three firing angles and thus controls the magnitude of the fundamental frequency voltage while eliminating the two lowest order harmonics. The performance of the ANN controlled inverter is studied using an electromagnetic transients simulation program (EMTDC)

Keywords

PWM invertors; digital simulation; frequency control; learning (artificial intelligence); neural nets; power engineering computing; power system harmonics; simulation; voltage control; AC voltage magnitude; PWM inverters; artificial neural network; chopping angles; control system; controller input; electromagnetic transients simulation program; firing angles; fundamental frequency control; fundamental frequency voltage magnitude; harmonic elimination; lowest order harmonics; off line training; pulse width modulated inverter; voltage control; Frequency control; Learning systems; Neural network applications; Power conversion harmonics; Pulse width modulated inverters; Simulation; Voltage control;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1994. Conference Proceedings. 1994 Canadian Conference on

Conference_Location

Halifax, NS

Print_ISBN

0-7803-2416-1

Type

conf

DOI

10.1109/CCECE.1994.405660

Filename

405660