NEURAL NETWORK CONTROL OF UNCERTAINTY ROBOTIC MANIPULATOR WITH H∞ TRACKING PERFORMANCE
-
摘要: 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.最后通过在两自由度机器人控制中的应用表明该方案的可行性.Abstract: 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.
-
Keywords:
- H∞ Tracking control /
- neural network /
- robot
-
-
1 Karakasoglu A,Sundareshan M K.A Recurrent Neural Network Based Adaptive Variable Structure Model-Following Control of Robotic Manipulator.Autamatic,1995,31(10):1495~1507
2 Park J,Sandberg I W.Universal Approximation Using Radial Basis Function Networks.Neural Computation,1991,3:246~257
3 Bor-Sen Chen,T S Lee,J H Feng.A Nonlinear H∞ Cont rol Design in Systems Under Parameter Perturbation and Exeternal Disturbance.IN T J Cont rol,1994,59(2):439~461
4 Limebeer,ect.A Game Theoretic Approach to H∞ Control for Time-varying Systems.S IA M J Control and Optimization,1992,30:262~283
5 Doyle J C K G,Khargonekar P P.State-space Solution to Standard H∞ and H Control Problems.IEEE Trans,on Automatic Control,1989,34(8):831~847
6 Anderson B D O,Moore J B.Optimal Control:Linear Quadratic Methods.Englewood Cliffs,N J:Prenticce Hall,1990
7 Narendra K S,Annaswamy A M.Stable Adaptive Systems.Ennglewood Cliffs,N J:Prentice-Hall,1989
8 刘延年,忻欣,冯纯伯.基于神经网络的一类非线性连续系统的稳定自适应控制.控制理论与应用,1996,13(1):70~75
计量
- 文章访问数: 41
- HTML全文浏览量: 632
- PDF下载量: 148