An Artificial Neural Network-Based Model Predictive Control for Three-Phase Flying Capacitor Multilevel Inverter

Model predictive control (MPC) has been used widely in power electronics due to its simple concept, fast dynamic response, and good reference tracking. However, it suffers from parametric uncertainties, since directly relies on the mathematical model of system predict optimal switching states be at next sampling time. As a result, uncertain parameters lead an ill-designed MPC. Thus, this paper offers model-free strategy basis artificial neural networks (ANNs), for mitigating effects parameter mismatching while having little negative impact inverter’s performance. This method includes two related stages. First, MPC is as expert studied converter order provide dataset, while, second stage, obtained dataset utilized train proposed ANN. The case study herein based four-level three-cell flying capacitor inverter. In study, MATLAB/Simulink simulate performance method, taking into account various operating conditions. Afterward, simulation results are reported comparison with conventional scheme, demonstrating superior terms robustness against mismatch low total harmonic distortion (THD), especially when changes occur parameters, compared Furthermore, experimental validation provided Hardware-in-the-Loop (HIL) using C2000TM-microcontroller-LaunchPadXL TMS320F28379D kit, applicability ANN-based implemented DSP controller.