For medium and high-powered applications, modular multilevel converters have become the most promising converter application. In this paper, a sliding mode controller based on an RBF neural network is proposed for a modular multilevel converter. The RBF neural network is designed to approximate the uncertainty mathematical model of a modular multilevel converter. The main innovation of the proposed method is that it does not require any model parameters and control parameters during the whole control process. This means that parameter changes caused by the external environment will not influence the controller performances. Finally, by comparing with a conventional PI controller, the simulation proves the feasibility and effectiveness of the proposed control method. In addition, the experimental results show that the grid-side current can become stable immediately while the active power is stabilized after 20 ms when the set value is changed.

This paper presents a fractional-order sliding mode control scheme based on an RBF neural network (RBFFOSMC) for a direct three matrix converter (DTMC) operating under unbalanced grid voltages. The RBF neural network (RBF NN) is designed to approximate a nonlinear fractional-order sliding mode controller. The proposed method aims to achieve constant active power whilst maintaining a near unity input power factor. First, an opportune reference current is accurately generated according to the reference power and the RBFFOSMC is designed in a dq reference frame to achieve a perfect tracking of the input current reference. An almost constant active power, free of low-frequency ripples, is then supplied from the grid after compensating for the output voltage. Simulation and experimental studies prove the feasibility and effectiveness of the proposed control method.