仿射非线性系统神经网络自适应控制器的研究及其在机械手中的应用

RESEARCH ON NEURAL NETWORK ADAPTIVE CONTROLLER OF AFFINE NONLINEAR SYSTEM AND ITS APPLICATION IN ROBOT CONTROL

摘要: 本文提出了一种利用神经网络逼近具有不确定性及随机干扰的仿射非线性系统的新算法，采用自适应控制率在线调节网络权值，并基于控制理论选择控制量以削减噪声干扰．从理论上证明采用该算法后系统全局稳定性．最后将该算法用于两连杆机械手轨迹跟踪，仿真结果表明该算法具有跟踪精度高，收敛速度快的优点．

Abstract: A control law is presented in this paper, which uses neural network technique to approximate the affine nonlinear system having unknown or uncertain dynamics and noise disturbances.An adaptive control law to adjust the network parameters on-line is adopted and the control value is chosen according to- H-∞--control theory to attenuate the disturbance. This control law is applied to a two link robot manipulator, and simulation results show its validity.