An online optimization approach to SHEPWM applied to NPC inverter

The Selective Harmonic Elimination (SHE) PWM technique has become a significant PWM method for less switching loss for three-level neutral-point-clamped (NPC) inverter. This paper introduces an online optimization approach to the SHEPWM technology based on genetic algorithm and BP neural network. The method doesnpsilat need to preset the initial values and to predict the trend of these values over whole range of modulation index when solving the SHE nonlinear and transcendental equations. Hence, easy convergence and less computing-time are achieved. Simulation and experimental results demonstrate the validity of the proposed method. The method can achieve online SHEPWM control of the NPC inverter.