永磁直线同步电机的智能互补滑模控制

针对永磁直线同步电机(PMLSM)伺服系统的位置跟踪精度问题,提出了一种基于径向基函数(RBF)神经网络的智能互补滑模控制(ICSMC)方法。建立了包含端部效应、参数变化、外部扰动及非线性摩擦等不确定性因素的PMLSM动态方程。设计了互补滑模控制器,采用广义滑模面和互补滑模面相结合的设计,降低了系统跟踪误差,提高了系统响应速度,并削弱了抖振现象;利用RBF神经网络直接对系统存在的不确定性进行估计,在线调整RBF网络参数以改善系统动态性能,提高系统鲁棒性,并用李雅普诺夫定理保证系统闭环稳定性。通过分析系统实验结果,验证了所提出的控制方法有效降低了系统跟踪误差,并使系统具有良好的动态性能和鲁棒性能。

Intelligent Complementary Sliding Mode Control for Permanent Magnet Linear Synchronous Motor

Intelligent complementary sliding mode control(ICSMC)based on radial basis function(RBF)neural network is proposed for position tracking precision in permanent magnet linear synchronous motor(PMLSM)servo system.Firstly,PMLSM dynamic equation which contains uncertainty factors such as the end effect,parameter variations,external disturbances and nonlinear friction is established.Then,complementary sliding mode controller is designed by adopting the combination of the generalized sliding surface and the complementary sliding surface in order to reduce the system tracking error,improve response speed and weak the chattering.RBF neural network is employed to estimate the system uncertainty directly.Moreover,RBF network parameters which are trained online can improve the system dynamic performance and robustness.Furthermore,the Lyapunov theorem is used to guarantee the close-loop system stability.By analyzing the system experiment results, it is proved that the proposed control method effectively reduces the system tracking error, and makes the system have good dynamic performance and robust performance.