Design and analysis of multilevel inverter for electric vehicle by using the ANN

In this study, a novel setup for a bidirectional multilevel converter for use in EVs is presented. It is equipped with a multi-stage DC-DC converter that can balance the voltage across the DC link capacitor. This is a crucial necessity in EVs, and the multilayer DC-DC converter allows for bidirectional operation. When a problem occurs in a T-type multilevel inverter (MLI), the suggested arrangement only requires two additional restore voltage balance. To alleviate the consequences of parameter mismatching with little detriment to the inverter's performance, this research proposes a model-free control technique based on artificial neural networks (ANNs). In order to keep the power quality stable, the suggested ANN controller lowers the THD of the system. When compared to a 3-level T-type MLI, its output quality is better, it has lower switching losses, lower THD, and needs fewer filters. Voltage is produced via pulse width modulation. When compared to two-level inverters, three-level inverters have several advantages, including higher efficiency, lower output harmonics, and greater dependability. PV, wind, and fuel cells may all benefit from its utilisation. A MATLAB/Simulink simulation model is used to verify and evaluate the suggested setup. The proof-of-concept data is also provided by a 1 kW laboratory prototype.