基于模型参考神经网络的异步电机鲁棒速度控制方法  

The Robust Speed Controlling of Induction Motor Based on Model Reference Neural Network

作　　者：龙泳涛[1] 

机构地区：[1]湖南工程学院电气与信息工程系,411104

出　　处：《电气应用》2008年第4期27-30,共4页Electrotechnical Application

基　　金：湖南省自然科学基金(06JJ4060)

摘　　要：提出一种新型的基于模型参考神经网络的异步电机驱动系统鲁棒速度控制方法。由带负载转矩观测器的两层神经网络对象辨识器(NNPI)对未知的电机动态参数进行实时的自适应辨识与估计。由双层神经网络PI控制器(NNC)对异步电机转子速度进行鲁棒控制。神经网络使用学习算法以自动调节NNPIC的参数并有效地降低系统对参数变化以及负载扰动的敏感度。仿真结果表明该方法对于参数变化和负载转矩扰动具有很强的自适应能力,能够提高异步电机的性能,并减小其对参数变化、非线性影响以及负载扰动的敏感度。A novel robust speed control method for induction motor drives based on a two-layered neural network plant identifier （NNPI） and a two-layered neural network PI controller （NNC） are proposed. The NNPI is used to provide a realtime adaptive estimation of the unknown motor dynamics. The projection algorithm is used as the learning algorithm for these neural networks to automatically adjust the parameters of the NNC and to minimize the differences between the motor speed and the speed predicted by the NNPI. The simulation and experimental results demonstrate that the proposed robust control scheme can improve the performance of an induction motor drive and reduce its sensitivity to parameter variations and load disturbances.

关 键 词：神经网络 模型参考 异步电机鲁棒控制 

分 类 号：TM383.6[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]