Application of Neural Network Fitting for Pitch Angle Control of Small Wind Turbines
Mohamed E. M. Salem, Hesham M. El-Batsh, Ahmed El-Betar, Ali M.A. Attia
Abstract
Wind turbines are usually designed to withstand extreme winds statically so that they can survive a storm. In order to deal with power control and safety in operation during high wind speed, a pitch angle control system is proposed and has been employed in commercial wind turbines. In the present study, a small pitch-controlled wind turbine model with 0.8 m rotor diameter has been designed, constructed and tested in the wind tunnel. A linkage mechanism has been used to control the pitch angle by using a DC servo-motor as an actuator; this proved to be efficient and convenient for small wind turbines and worked perfectly. This study covers two main tasks. First, carefully extract the characteristic of the small wind turbine model under study at different wind velocities and pitch setting angles. Second, a pitch angle control system is implemented to control the power output of the turbine at wind speeds above the rated speed. The neural network fitting function provides a suitable and good controlling action in pitch angle control system which can achieve wind turbine the required power curve. All measurements and control actions were achieved by using the Arduino Mega board supported with MATLAB SIMULINK.