基于Hermite多项式函数链模糊神经网络的PMLSM分数阶反推控制

Fractional-order backstepping control based on Hermite polynomial functional link fuzzy neural network for PMLSM

针对永磁直线同步电动机(PMLSM)伺服系统中存在的参数变化、负载扰动和摩擦力等不确定性因素,采用了函数链模糊神经网络(FLFNN)和分数阶反推控制(FOBC)相结合的控制方案来提高系统的控制性能。首先,采用FOBC实现系统的全局调节和位置跟踪,提高系统的收敛速度和控制精度;然后,采用Hermite多项式函数链模糊神经网络(HFLFNN)直接估计系统中存在的不确定性,同时利用指数补偿器对估计误差进行补偿,进一步提高系统的鲁棒性;最后,利用Lyapunov函数推导出系统中控制参数的在线调整估计律。实验结果表明所提出的控制方法切实可行,能够有效地抑制不确定性对系统的影响。与FOBC相比,具有更好的跟踪性能和鲁棒性能。

For permanent magnet linear synchronous motor(PMLSM)exists uncertain factors such as parameters change,load disturbance,and friction,a control scheme combining function link fuzzy neural network(FLFNN)and fractional backstepping control(FOBC)is adopted to improve the control performance of the system.Firstly,the fractional-order backstepping control scheme was used to realize the global regulation and position tracking of the system,so as to improve the convergence speed and control accuracy of the system.Then,the functional link fuzzy neural network based on Hermite polynomial(HFLFNN)was used to directly estimate the uncertainties in the system.At the same time,the exponential compensator was used to compensate the estimation error,which further improves the robustness of the system.Finally,the Lyapunov function was used to derive the on-line adjusting estimation law of control parameters in the system.The experimental results show that the proposed control method is feasible and can effectively suppress the influence of uncertainties on the system.Compared with FOBC,it has better tracking performance and robustness.