基于模型参考自适应模糊神经网络的直线永磁同步电动机速度伺服系统  

Model reference adaptive fuzzy neural network control based on speed servo system of linear permanent magnet synchronous motor

作　　者：沈显庆[1] 王成元[1] 

机构地区：[1]沈阳工业大学 电气工程学院

出　　处：《电机与控制学报》2005年第5期425-427,431,共4页Electric Machines and Control

摘　　要：针对直线永磁同步电动机全闭环控制系统易受干扰而降低系统性能指标,甚至造成不稳定等问题,采用模型参考自适应模糊神经网络在线辩识方法,用梯度法实时修正模糊控制器的输入和输出隶属度参数,建立了模型参考自适应模糊神经网络速度伺服系统模型,并给出了模糊神经网络控制器的设计。通过仿真和实验结果证明,这种方法提高了速度检测装置的分辨率和动态响应能力,并且使系统具有很强的鲁棒性。Accounting for the closed - loop control system of Linear Permanent Magnet Synchronous Motor is apt to be disturbed. It is the main problem which can degrade the performance of the control system and even destabilize the system. Presenting an on - line identification method of model reference adaptive control based on fuzzy neural network on the paper. The inputs and membership parameters of the fuzzy controller are modified in real -time by a gradient method. It is proved that the method above is valid for improving the resolving of velocity detect device and dynamic response by simulation and practice and the system is robust.

关 键 词：模型参考自适应 模糊神经网络 直线永磁同步电动机 时滞补偿器 

分 类 号：TM921.6[电气工程—电力电子与电力传动]