Loading...
Switching angle design for pulse width modulation AC voltage controller using genetic algorithm and distributed artificial neural network
Author(s)
Date Issued
July 26, 2011
Type
Conference Paper
Abstract
This paper proposes a technique to design the switching angles in a PWM AC voltage controller using genetic algorithms (GA) and distributed artificial neural network (ANN). In the proposed technique, GA is used to evaluate the turn on and turn off angles of PWM pattern to reduce the low order harmonic content in PWM output voltage. The results from GA are then used to train the distributed ANN. The advantages gained from the proposed technique are the reduction of complexity of training process and the improvement of the ability of the ANN. In addition, the total harmonic distortion of voltage, which calculated from the low order harmonic content, is adopted in the proposed fitness function. Thus, the load value is not necessary to be known before stating the proposed technique. Simulation results show that the proposed technique is superior to the conventional fixed-duration pulse technique.
Citation
Imecs 2011 International Multiconference of Engineers and Computer Scientists 2011, 2, 970-974, 2011
