Compensation capacitance tunings of wireless power transfer systems using artificial neural network

Abstract

This letter proposes a new method for tuning compensation capacitances of wireless power transfer (WPT) systems using an artificial neural network (ANN). A field solver is used to analyze the compensation capacitances that maximize the output power at a set resonant frequency in a WPT system with ferrite shields. The compensation capacitances can be tuned using the ANN learned from the results acquired by the field solver. The electrical parameters for tuning the compensation capacitances acquired by the proposed method have maximum errors within 3.40% and mean absolute errors within 1.38%.