Hardware implementation of neural network controlled optimal PWM inverter using TMS320C30 board

An optimal PWM scheme is used to control a voltage source inverter. The switching angles are controlled by a feedforward artificial neural network in a way that all nontriplen harmonics up to the 29/sup th/ are completely removed from the output and the amplitude of the fundamental is set at the desired level. The neural network is emulated by a TMS320C30 DSP board along with the other parts of the control unit of the inverter.