Skip to Main Content
The author proposes an adaptive learning pulse width modulation (PWM) for a current controller which adaptively minimizes a current ripple with a constant switching frequency. This employs neuro- and/or fuzzy computing philosophy as well as adaptive learning pattern recognition principles to overcome the problems concerning variations of the system parameters. The proposed system is applied to an electrical drive system with an induction motor(IM) and is studied by various simulations. As opposed to the known classical methods, the proposed system shows the better performance.