Adaptive control of a variable-speed variable-pitch wind turbine using RBF neural network

To be competitive economically, various control systems are used in large scale wind turbines. These systems enable the wind turbine to work efficiently and produce the maximum power output in varying wind speed. In this paper, an adaptive control based on Radial-Basis-Function (RBF) neural network (NN) is proposed for different operation modes of variable-speed variable-pitch (VSVP) wind turbines including torque control at speeds lower than rated wind speeds, pitch control at higher wind speeds, and smooth transition between these two modes. The adaptive neural network control approximates the non-linear dynamics of the wind turbine based on input/output measurements and ensures smooth tracking of optimal tip-speed-ratio at different wind speeds. The robust NN weight updating rules are obtained using Lyapunov stability analysis. The proposed control algorithm is first tested with a simplified mathematical model of a wind turbine. Second, the validity of results is verified by simulation studies on a 5 MW wind turbine simulator.