论文部分内容阅读
针对遥操作机器人通讯通道中存在的时延 ,提出了一种神经网络 Smith预估控制方法。控制系统适合于时延不变但未知的情况。控制系统包括主控制器和从系统两部分。从系统采用动态神经网络辨识机器人的动态模型 ,神经网络权重在线学习 ,用神经网络的输出对非线性系统进行局部非线性补偿 ,将非线性系统线性化。主系统针对线性化的从系统 ,采用 Smith预估控制解决时延问题并保证系统的性能品质。通过李雅普诺夫稳定理论保证了时延控制系统的稳定性。对两关节机器人的仿真结果说明了该方法的有效性。
Aiming at the delay existing in teleoperation robot communication channel, a neural network Smith predictor control method is proposed. The control system is suitable for the case of constant delay but unknown. The control system includes the main controller and the slave system. The dynamic neural network is used to identify the dynamic model of the robot and the online learning weight of the neural network. The output of the neural network is used to locally nonlinear compensate the nonlinear system, and the nonlinear system is linearized. The main system for linearized from the system, using Smith predictive control to solve the delay problem and ensure system performance and quality. The stability of delay control system is guaranteed by Lyapunov stability theory. The simulation results of two-joint robot demonstrate the effectiveness of the method.