基于神经网络的永磁直线同步电机自适应滑模控制  

Neural-network-based Adaptive Sliding Mode Control for PMLSM

作　　者：杨伟民[1] 潘丽姣[1] 陆华才[2] 

机构地区：[1]义乌工商学院计算机工程系,浙江义乌322000 [2]浙江大学现代制造工程研究所,浙江杭州310027

出　　处：《电气自动化》2009年第3期9-11,共3页Electrical Automation

基　　金：国家自然科学基金项目(50475101)

摘　　要：针对永磁直线同步电机(PMLSM)直接驱动系统的非线性与电机参数时变、易受扰动的特性,将滑模控制和神经网络控制相结合,用两个神经网络控制器分别实现滑模等效控制和滑模切换控制,构成神经网络自适应滑模控制。仿真结果表明,神经网络滑模控制和常规的滑模控制相比,具有更好的动态稳定性和跟踪性能,对外界干扰具有较强的鲁棒性。An adaptive sliding mode control based on neural network control is proposed to control the speed of the mover of a permanent magnet linear synchronous motor （PMLSM） servo drive system considering nonlinear and parameters time-variation. The control system consists of two neural networks, one is used for sliding equivalent control and the other for sliding switch control. Simulation results show that the adaptive sliding mode controller based on neural network is superior to the conventional sliding mode controller in dynamic stability performance and speed tracking power, and the former has strong robustness to external disturbance.

关 键 词：永磁直线同步电机 神经网络 滑模控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]