【摘要】 针对未知非线性、外界干扰和参数摄动等不确定因素对实际转台控制系统的影响,提出了自适应反演滑模神经网络的转台鲁棒控制器设计。自适应反演滑模控制作为主控制器,RBF神经网络实现了不确定上界值的在线辨识。仿真结果表明,基于RBF神经网络的自适应反演滑模控制很好地克服对象的不确定性,实现控制系统的较强鲁棒性,适于高精度飞行仿真转台系统的实时鲁棒控制。更多还原

【Abstract】 Considering unknown nonlinearities、external disturbances and parameter perturbations during the actual flight simulator system, a robust controller based on adaptive backstepping and neural network method was proposed. The method and design process of adaptive backstepping and slide mode technique were firstly proposed; secondly, RBF neural network, which is used for acquiring the upper bound of variations of system model, was proposed; finally, robust control of flight motion simulator was strongly realized. During the robust controller, backstepping and slide mode method is the main controller and RBF network controller is used to compute the value of upper bound of control system. Simulation shows that the method is perfect and it is very fit for robust control of high-precision servo system.更多还原