Analysis of neural and fuzzy-power electronic control

Current-controlled voltage-source inverters offer substantial advantages in improving motor-system dynamics for high-performance AC-drive systems. The controller switches follow a set of reference current waveforms. Fixed-band hysteresis and sinusoidal-band hysteresis controllers have been studied. Neural network and fuzzy-logic-based current-controlled voltage-source inverters are developed. The models and learning techniques have been investigated by simulation. The implementation of neural networks is described, and simulation results are presented. The new UPS (uninterruptible power supply) with a fuzzy-logic compensator is then proposed. The proposed fuzzy-logic compensator is used to prevent voltage drop from nonlinear loads. The total harmonic distortion (THD) of the proposed scheme is better than that of the conventional deadbeat control method for linear and nonlinear loads. Finally, the application of fuzzy control to DC-DC converters, operating at finite switching frequency, is studied. Several control methods currently used for buck, boost and buck/boost converters are compared to the fuzzy-converter control. The fuzzy-logic and neural-network controller for a unity power-factor rectifier are also discussed. The simulations presented show that the fuzzy-control method has better dynamic performance and less steady-state error