具有H^∞跟踪特性的不确定性机器人神经网络控制

NEURAL NETWORK CONTROL OF UNCERTAINTY ROBOTIC MANIPULATOR WITH H ∞ TRACKING PERFORMANCE

针对不确定性机器人提出一种具有Ｈ∞跟踪特性的神经网络（ＮＮ）控制器，使Ｈ∞控制理论与ＮＮ有机地结合起来．通过适当选择控制变量加权因子可以使由于ＮＮ近似误差以及外部干扰引起的误差动态衰减到期望的程度下．文中基于Ｌｙａｐｕｎｏｖ方法给出了ＮＮ学习自适应律，Ｈ∞跟踪特性的证明．

In this paper, a Neural Network control with H ∞ tracking performance for uncertainty robotic manipulator is proposed. The control scheme combined H ∞ control theory and NN adptive algorithm organically. If the weight to control variables is appropriatly chosen, the influence of both NN aproximation error and external disturbance can be attenuated to a desired level. Based on Lyapunov method, NN learning law is given and H ∞ tracking performance is illustrated. Finally, the developed controller is applied to a two link robotic manipulator. Simulation results demonstrate that the control scheme is effective.