Neural network based sensorless maximum wind energy capture with compensated power coefficient

This work describes a small wind generation system where neural network principles are applied for wind speed estimation and robust maximum wind power extraction control against potential drift of wind turbine power coefficient curve. The new control system will deliver maximum electric power to a customer with lightweight, high efficiency, and high reliability without mechanical sensors. A turbine directly driven permanent magnet synchronous generator (PMSG) is considered for the proposed small wind generation system in this paper. The new control system has been developed, analyzed and verified by simulation studies. Performance has then been evaluated in detail. Finally, the proposed method is also applied to a 15 kW variable speed cage induction machine wind generation (CIWG) system and the experimental results are presented.