遥操作机器人神经网络Smith预估控制(英文)

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。

NEURAL NETWORK SMITH PREDICTIVE CONTROL FOR TELEROBOTS WITH TIME DELAY

A neural network Smith predictive control strategy is proposed to deal with inpu t and feedback time delays in telerobot systems. The delay time is assumed to b e invariant and unknown. The proposed control structure consists of a slave syst em and a master controller. In the slave system, a recurrent neural network (RNN ) with on-line weight tuning algorithm is employed to approximate the dynamics of the time-delay-free nonlinear plant, which is used to linearize the slave s ystem. The master controller is a Smith predictor for the linearized slave syste m, which provides prediction and maintains the desirable tracking performance. S tability propriety is guaranteed based on the Lyapunov method. A simulation of a two-link robotic manipulator is provided to illustrate the effectiveness of th e proposed control strategy.