无刷双馈电机的PID神经网络控制  

PID neural network control of brushless doubly-fed machine

作　　者：郭红霞[1] 杨金明[1] 刘文刚[1] 

机构地区：[1]华南理工大学电力学院,广东广州510640

出　　处：《控制理论与应用》2008年第1期53-56,共4页Control Theory & Applications

基　　金：国家自然科学基金重点资助项目(60534040)

摘　　要：无刷双馈电机(BDFM)兼有笼型、绕线型感应电机和电励磁同步电机的共同优点,在电气传动和风力发电中具有很好的应用前景.由于无刷双馈电机两套绕组形成的复杂空间耦合关系,使得基于模型的控制方法异常复杂,为此设计了一种PID神经网络(PIDNN)的无刷双馈电机的控制方法,经过训练的PID神经网络控制器能够实现准确的转速跟踪,且有较好的动态特性,仿真结果验证了这种控制方法的有效性.Brushless doubly-fed machine （BFDM） possesses the common advantages of squirrel-cage induction machine, wire wound induction machine and electromagenetic synchoronous machine. Therefore, it has a good prospect for application in AC drive and wind generating. Because of the complicated spatial coupling characteristics of BFDM between the two windings, the control methods based on the model of BFDM are very complicated. A PID neural network controller （PIDNN） is designed and applied to the speed regulation of BFDM. The exact speed-tracking is then realized by PIDNN controller after training. The dynamics is satisfactory. Finally, the simulaiton result validates the feasibility and effectiveness of this method.

关 键 词：无刷双馈电机 PID神经网络控制 转速控制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]