Two-level DTC based on ANN controller of DFIG using 7-level hysteresis command to reduce flux ripple comparing with traditional command

This paper presents an improved direct torque control (DTC) based on artificial neural networks (ANN). The DTC technique is known to offer fast decoupled command of electromagnetic torque and rotor flux via a simple command structure. On the other hand, we proposed a novel hysteresis comparator of electromagnetic torque for six sectors DTC command of a doubly fed induction generator (DFIG) for a wind energy conversion system to reduce the electromagnetic torque, rotor flux, and stator current. To improve the dynamic and static command performance of the DFIG, the switching table is designed using ANN controller. Simulation results with the traditional DTC and proposed DTC with seven-level hysteresis comparator are presented and compared. Results show the effectiveness and the robustness of the approach proposed.