Power electronics inverter control with neural networks
Bor‐Ren Lin, Richard Gibson Hoft · 2002
Current-controlled voltage source inverters offer substantial advantages in improving motor system dynamics in high-performance AC drive systems. The controller switches follow a set of reference current waveforms. Fixed-band hysteresis and sinusoidal-band hysteresis controllers are studied. A neural-network-based current-controlled voltage source inverter is developed. The modes and learning techniques are investigated by simulation. The implementation of neural networks is described, and simulation results are presented.>