基于RBF神经网络和扰动观测器的PMLSM位置控制

Using RBF Neural Network and Disturbance-Observer to the Position Control of the PMLSM System

针对永磁直线同步电机的位置控制,其控制精度易受模型误差和负载扰动等因素的影响,设计了一种改进型的滑模趋近律控制器,提出了基于RBF神经网络的建模误差逼近器和非线性负载扰动观测器。首先,利用改进型的滑模趋近律算法,加快到达滑模面的速度,降低系统的滑模抖振;其次,采用RBF神经网络算法逼近系统的建模误差;最后,非线性扰动观测器对系统的负载扰动进行估计。此外,系统采用前馈补偿控制策略,以提高系统的控制精度。仿真结果表明:通过与传统的滑模趋近律控制方法相比,文章提出的方法提高了系统的控制精度、增强了系统的鲁棒性。

For the position control of permanent magnet linear synchronous motor(PMLSM),an improved sliding approach mode controller is designed in this paper,aiming at the fact that the tracking accuracy of PMLSM is susceptible to system model error and load disturbances.In addition,an RBF neural network model error approximator and Non-linear disturbance load observer are proposed in this paper.Firstly,the improved algorithm of sliding mode approach law can accelerate the speed of reaching the sliding mode surface,which significantly reduces the chattering of the system.Secondly,the change of system model error can be estimated by RBF neural network approximator.Finally,the nonlinear disturbance observational algorithm can be used to estimate the load disturbance of the system.In addition,in order to improve the control accuracy of the system,the feedforward compensation strategy was applied in the system.The simulation results show the proposed method improves the control accuracy and robustness of the system,compared with the traditional sliding mode approach control method.