Document Type : Original Article
Department of Electrical & Electronics Engineering, Faculty of Engineering and Architecture, Nisantasi University, Istanbul, Turkey
In this paper, a neural third-order sliding mode-direct torque control (NTOSM-DTC) for an asynchronous generator (AG) based dual-rotor wind turbine (DRWT) is proposed. The classical DTC strategy with traditional proportional-integral (PI) controllers has been widely applied to induction machines in recent years due to the high characteristics that it provides in comparison with the classical DTC switching technique. Meanwhile, it has a major drawback that are the significant current, rotor flux and torque ripples generated by the traditional PI controllers. To overcome these drawbacks, the improvement of this control technique by removing these controllers is designed in this paper. The proposed intelligenet nonlinear control technique is based on replacing the classical PI controllers with neural TOSM controllers which will have the same inputs as these controllers. The simulation was performed in Matlab software, and the results obtained make it possible to evaluate the characteristics of the proposed intelligenet nonlinear control technique over the traditional one.