变参数PI与神经网络控制的风电系统仿真  

Simulation of Variable-Parameter Pi and Neural Network Control System for Wind Generation

作　　者：唐建平[1] 廖勇[1] 姚骏[1] 

机构地区：[1]重庆大学电气工程学院高电压与电工新技术教育部重点实验室,重庆400044

出　　处：《计算机仿真》2008年第3期251-254,297,共5页Computer Simulation

摘　　要：建立了交流励磁风力发电机系统的仿真模型。针对交流励磁发电机数学模型的强非线性,参数时变性等特点,提出了变参数PI与神经网络的协调控制方法。以交流励磁风力发电机的最佳风能跟踪控制为目的,对基于变参数PI与神经网络协调控制的交流励磁风力发电机控制系统进行了仿真研究。仿真结果表明所提的控制方法具有良好的动、静态性能和较强的鲁棒性,是一种适合在线学习的新型交流励磁风力发电机励磁控制方法。A simulation model of alternating current excited wind generator system is established in this paper. For the nonlinear mathematical model and the variable parameters of alternating current excitation wind generator, the variable parameter PI and neural network control method is proposed. For the purpose of the optimal wind power tracking control, the generator system based on the variable parameter PI and neural network control method is simulated and analyzed. The simulation result shows that the proposed control method can improve the dynamic and stable performance of the generator with good robustness. It is a new on - line learning control method for alternating current excitation wind generator system.

关 键 词：交流励磁发电机 风力发电 神经网络 鲁棒性 

分 类 号：TM301.2[电气工程—电机] TP183[自动化与计算机技术—控制理论与控制工程]