신경망 제어기를 이용한 풍력발전시스템의 피치제어

Abstract

Wind turbine system can obtain the maximum wind energy using torque control under the rated wind speed, and wind turbine power is controlled as the rated power using pitch control over the rated wind speed. In this paper, we present two methods for wind turbine pitch controller using neural networks. The first method is that the difference between a rated and current speed of generator has been used for another input of neural network controller as well as wind speed. As a result, the generator speed and power are maintained as the rated ones. However vibrations of pitch angle and generator speed have been considered to be improved. And the second methods is that the changing rate of generator speed has been used for another input of neural network controller as well as the difference between the rated and current generator speed. As a result, problems of the first method have been improved. Error back-propagation algorithm is used for training the neural network pitch controller and Matlab/Simulink is used to confirm the performance of proposed method