论文部分内容阅读
本文针对机械手轨迹跟随控制问题，提出了一种稳定的神经网络自适应控制器设计方法，这里机械手的非线性动力学假设是未知的．提出方法是神经网络方法和扇区自适应变结构控制方法的集成．扇区变结构控制的作用有两个，其一是在系统神经网络控制失灵的情形下提供闭环系统的全局稳定性；其二是在神经网络的近似域内改进系统的跟随性能．本文采用李雅普诺夫稳定理论给出了系统的稳定性和跟随误差收敛性的证明，并且通过数字仿真验证了提出方法的有效性．
In this paper, a robust neural network adaptive controller design method is proposed for robot trajectory following control problem, where the nonlinear dynamics assumption of manipulator is unknown. The proposed method is the integration of neural network method and sector adaptive variable structure control method. There are two functions of the variable structure control of the sector, one is to provide the global stability of the closed-loop system under the control failure of the system neural network; the other is to improve the system following performance in the approximate domain of the neural network. In this paper, Lyapunov stability theory is used to show the stability of the system and the convergence of the following error. The validity of the proposed method is verified by numerical simulation.