Neural MPPT of Variable-Pitch Wind Generators With Induction Machines in a Wide Wind Speed Range

This paper proposes a maximum power point tracking (MPPT) technique for variable-pitch wind generators with induction machines (IMs), which can suitably be adopted in both the maximum power range and the constant-power range of the wind speed. To this aim, an MPPT technique based on the growing neural gas (GNG) wind turbine surface identification and corresponding function inversion has been adopted here to cover also the situation of variable-power region. To cope with the constant-power region, the blade pitch angle has been controlled on the basis of the closed-loop control of the mechanical power absorbed by the IM. The wind speed is then estimated in the constant-power region on the basis of the actual position of the blade pitch angle. The proposed methodology has been verified both in numerical simulation and experimentally on a properly devised test setup. In addition, a comparison between the proposed approach and the previously developed GNG-based MPPT has been performed on a real wind speed profile. Finally, the effect of the torsional stiffness of the mechanical transmission system has been analyzed.