摘要
针对风力发电机组运行过程难以建立精确的数学模型的特点,将动态模糊神经网络应用于风力发电变桨距系统的辨识中。该模糊神经网络的结构基于扩展的径向基神经网络,在功能上等价于TSK模糊系统,其学习算法的最大特点是参数的调整和结构的辨识同时进行,且学习速度快。通过对风力发电变桨距系统中桨距角和风力机转速的非线性动态过程所进行的仿真实验,表明该方法在变桨距系统辨识中具有比较高的辨识精度和效率。
For it is difficult to establish the accurate mathematical model of wind power generation, iidentification of variable-pitch system based on dynamic fuzzy neural network is presented in this paper. The structure of the fuzzy neural network is based on the extended radial basis neural network, whose function is equivalent to TSK fuzzy systems. And the greatest feature of the learning algorithms is that to adjust the parameters and to identify the structure are at the same time, which learning speed is very fast. Through the nonlinear dynamic system simulation of the pitch angle and the wind turbine speed in the wind power system. The results show that the method has higher recognition accuracy and efficiency.
出处
《电气技术》
2011年第1期18-20,28,共4页
Electrical Engineering
关键词
风力发电
变桨距
动态模糊神经网络
辨识
wind power generation
variable pitch
dynamic fuzzy neural network
identification
