摘要：AbstractUnder the circumstance of inaccurate and intermittent wind speed measurement, maximum power capture control of wind turbines is still a hot and challenging topic in wind power generation field. This paper aims at improving wind turbines’ power production via an adaptive dual-layer sliding mode controller, with the help of estimated rotor effective wind speed. First, a novel effective wind speed estimation algorithm is proposed based on broad learning system (BLS), the training of which is completed by using data collected from the supervisory control and data acquisition (SCADA) system. Further, the trained BLS can deliver the estimated wind speed in an online manner to determine the optimal generator power command for maximum wind power extraction. In addition, a low-pass filter is designed to smooth the output, which is beneficial for drive train systems’ mechanical loads. Thereafter, a sliding mode control theory based maximum power point tracking (MPPT) controller is developed. To compensate for the uncertainties and mitigate the chattering phenomena, dual-layer adaptation laws are designed for the sliding mode controller. Finally, the effectiveness of the proposed control scheme is validated and demonstrated by the FAST (Fatigue, Aerodynamics, Structures, and Turbulence) tool.
关键词：Keywordswind turbineseffective wind speed (EWS) estimationbroad learning system (BLS)maximum power point tracking (MPPT)sliding mode control
