Low-cost microprocessor-based alternating current voltage controller using genetic algorithms and neural network

Abstract

A low-cost, high-performance microprocessor-based pulse width modulated (PWM) AC voltage controller with a novel harmonic reduction technique is proposed. Genetic algorithm is adopted to evaluate the optimal turn-on and turn-off angles in the PWM pattern such that the total current harmonic distortion is minimised. The evolved angles are only optimised at a desired output voltage. In the proposed design, an artificial neural network trained by sets of optimal angles is utilised, making the designed system applicable to all operating points. The simulation and experimental results verify that the proposed technique is a suitable technique, and its performance is comparable to the conventional techniques. © 2010 © The Institution of Engineering and Technology.