Design of fuzzy neural network control for single-stage boost inverter

This study mainly focuses on the development of a fuzzy-neural-network (FNN) control system for a single-stage boost inverter. First, the dynamic model of a single-stage boost inverter is analyzed and built for the later control manipulation. Then, a model-free FNN control system with varied learning rates is designed. The effectiveness of the proposed FNN control system is verified by experimental results of a 1kW single-stage boost inverter prototype, and its merits are indicated in comparison with a traditional double-loop proportional-integral (PI) control framework. Experimental results show that the superior FNN control system has significant improvements of 45.2% total harmonic distortion (THD) and 37.1% normalized-mean-square-error (NMSE) compared to the conventional double-loop PI control framework under nonlinear loads.