Convergence Enhancement of Super-Twisting Sliding Mode Control Using Artificial Neural Network for DFIG-Based Wind Energy Conversion Systems

The technological development of wind energy conversion systems (WECS) is emphasized on the injection power into utility grid more smoothly and robustly. Sliding mode control (SMC) has proven to be a popular solution for grid-connected WECS due its robust nature. super twisting sliding (STSMC), variant SMC, an effective approach suppress inherent chattering in SMC provide error-free control. anti-disturbance capabilities STSMC deteriorate non-linear part that based variable approaching law time delay created by disturbance uncertainties. This paper enhances combining attributes artificial intelligence with STSMC. Initially, designed both inner outer loop doubly fed induction generator (DFIG) proposed. Then, neural network (ANN)-based compensation term added improve convergence capability proposed ANN paradigm validated using processor (PIL) experimental setup carried out Matlab/Simulink.