A novel adaptive controller using radial basis function neural network for the wind energy conversion system

For a safe and efficient operation of large variable-pitch wind turbines, the controller plays a vital role. Below the rated wind speed, there is a power-optimal rotor speed for a given wind speed, achieved by designing a generator torque control. Pitch control is appropriate above the rated wind speed, to keep the rotor speed constant. In order to deal with nonlinearities and uncertainties, in this paper an approximate-adaptive control based on radial basis function networks is proposed, developed within a Lyapunov framework. Simulation results demonstrate that the proposed controller has ability to deal with system nonlinearities and uncertainties.