内容：
针对风力发电机组精确的数学模型难以建立的特点,采用RBF神经网络对风电机组进行了系统辨识。通过对风力发电机组转矩环和桨距环的动态过程进行分析,设计了基于RBF神经网络算法的风力发电机组转矩环与桨距环的辨识系统,采用RBF基函数构成隐含层空间,RBF参数确定后,非线性映射关系就确定了,将输入矢量直接映射到隐含层空间,对隐含层节点输出进行了线性加权求和,得到了输出层。研究结果表明,进行转矩环辨识时,辨识系统的输入信号为转矩给定,输出信号为发电机转速,辨识结果的误差率为1%;进行桨距环辨识时,辨识系统的输入信号为桨距角,输出信号为发电机转速,辨识结果的误差率为3%;采用RBF神经网络算法进行系统辨识具有较高的辨识精度和效率。 Aiming at the difficulty of establishing the mathematical model of the wind turbine, the RBF neural network is used to identify the wind turbine. Based on the analysis of the dynamic process of the torque ring and the pitch ring of the wind turbine, the identification system of the torque ring and the pitch ring of the wind turbine based on the RBF neural network algorithm is designed. The RBF basis function is used to construct the hidden layer space, After the RBF parameter is determined, the nonlinear mapping relation is determined, the input vector is directly mapped to the hidden layer space, and the output of the hidden layer node is linearly summed to obtain the output layer. The results show that when the torque ring is identified, the input signal of the identification system is given by the torque, the output signal is the generator speed, and the error rate of the identification result is 1%. When the pitch ring is identified, the input signal of the system The output signal is the generator speed, and the error rate is 3%. The RBF neural network algorithm is used to identify the system with high recognition accuracy and efficiency.

文件列表（点击上边下载按钮，如果是垃圾文件请在下面评价差评或者投诉）: