A Neural Network Based Adaptive Sliding Mode Controller for Pitch Angle Control of a Wind Turbine

In the Wind Energy Conversion System (WECS), at high-speed ranges, the blade pitch angle is used to control the mechanical input power and due to inherent nonlinearities and uncertainties in the wind turbine model, the use of sliding mode controller will produce satisfactory results. In this paper to regulate the extracted power of wind turbine at its constant rated power, an adaptive sliding mode controller is designed to control the wind turbine speed. To estimate the nonlinear term caused by the approximation of power coefficient and uncertainties in the aerodynamic model, a Radial Basis Function Neural Network (RBF-NN) is employed. Furthermore, a suitable continues function instead of sign function is introduced to reduce the chattering phenomenon. A closed-loop convergence has been proved for the complete control system. Finally to validate the proposed method an illustrative example is performed on a 5-megawatt wind turbine.