Triple Phase Shift Control of Dual Active Bridge Converter using Machine Learning Methods

Control of Dual Active Bridge (DAB) converters can be particularly challenging due to the involvement of multiple parameters such as phase shift, duty cycles, etc. This paper proposes a triple-phase shift control (TPSC) method for the DAB converter. TPSC shows better performance compared to the conventional phase shift control by significantly decreasing the current amount that flows through the high frequency (HF) transformer. Furthermore, different machine learning (ML) models that are compatible with multi-output regression problems are evaluated for the TPSC of the DAB converter. The lookup table that is generally used in TPSC of a DAB converter is replaced with a neural network model, leading to about 99% efficiency. All the proposed methods are tested via simulations in MATLAB-Simulink.