基于神经网络给定补偿的交流永磁直线伺服系统滑模控制

针对直接驱动的永磁直线同步电动机 (PMLSM )伺服系统 ,应用滑模变结构控制理论设计了一种具有强鲁棒性的速度控制器。为使系统具有自学习能力 ,削弱滑模控制所引起的“抖振” ,采用基于神经网络前馈给定补偿的滑模控制策略。仿真结果表明 ,该方案有效地克服了永磁直线同步电机特有的端部效应所产生的推力波动对系统的影响 ,对参数变化及阻力扰动具有很强的鲁棒性 ,而且提高了系统的稳态性能

Sliding Mode Control Based on Neural Network Command-compensator for AC Permanent Magnet Linear Servo System

In this paper, a robust speed controller for a direct drive permanent magnet linear synchronous motor(PMLSM)servo system was designed based on sliding mode variable structure control theory To make the servo system provide with the capability of self study and minimize the chattering of control, a sliding mode control strategy with a feed forward command compensator based on neural network(NN)was proposed Simulation results verify that the proposed control strategy solve the thrust ripple problem of PMLSM because of end effect, and make the direct drive system have strong robustness to parameter variation and resistance perturbation Smeanwhile, the system steady characteristic is improved greatly