Torque Ripple Reduction of DTC DFIG Drive Using Neural PI Regulators

This paper presents the application of artificial neural networks (ANNs) in direct torque control (DTC) with space vector pulse width modulation (SVPWM) of a three-phase doubly fed induction generator (DFIG). This technique are considered in order to reduce rotor flux ripple, harmonic distortion of stator current and electromagnetic torque. Also, the performances of the DTC with ANN controllers are test and compared to DTC with proportional integral (PI) controllers. The results obtained in the Matlab/Simulink environment using robustness tests show that the DTC-ANN is efficient, has superior dynamic performance and is more robust during parameter variations.