机械手的神经网络直接离散时间自适应控制算法

Direct discrete time adaptive algorithm for manipulator control using neural networks

提出了一种机械手的神经网络直接离散时间自适应控制算法。该算法是神经网络方法和自适应动态滑动模控制方法的集成。自适应动态滑动模控制的作用有两个：其一是在神经网络控制失灵的情形下提供控制系统的全局稳定性；其二是改善系统的跟随性能。整个系统的全局稳定性和跟随误差的收敛性采用李雅普诺夫稳定性理论进行了证明，并得到了一种新颖的神经网络权值调整算法。

A direct discrete time adaptive algorithm for manipulator control using neural networks is proposed, which is the integration of a neural network approach with an adaptive implementation of the dynamic sliding mode control. The dynamic sliding mode control serves two purposes, one is to provide the global stability of the closed loop system, and the other is to improve the tracking performance. The whole system stability and tracking error convergence are proved by Lyapunov stability theory which yields a novel neural network weight tuning algorithm.