Resonant MIMO Converter for Future High-Voltage DC Grids in More Electric Aircraft Applications

This paper presents a MIMO (Multiple Input-Multiple Output) bidirectional converter designed for aerospace applications and a neural network (NN) training model. The system comprises a five-level T-inverter, a two-cell cascaded inverter, and a high-frequency transformer. It addresses the newer High DC voltages proposed in the literature and offers ground isolation between the High-Voltage DC grid, the 28 V low-voltage grid, and the aircraft loads. The structure can also support extra modules for bidirectional operation. The paper’s second contribution is training a neural network to optimize the system’s behavior by having a model that considers switching angles, output power, bi-directionality, and noise emission. The algorithm is able to find an optimal model considering the phase and duty cycle of the switches of the converter and the current ripple in the DC buses. The study includes simulations and a case-study-experimental result using a Low-power prototype. The simulation results are compared with the implementation, showing good efficiency even for light load operation.