网络环境下的不确定非线性系统远程智能控制

针对一类网络环境下的不确定非线性动态系统,提出了一种基于神经网络非线性补偿和线性反馈控制相结合的智能远程控制方法。该方法通过构造神经网络在线估计器学习局部子系统的非线性特性,从而将局部子系统线性化,神经网络权重的在线学习没有持续激励的要求,且可保证闭环误差系统一致最终有界稳定。最后对线性化的闭环时延控制系统,远程控制器采用基于李亚普诺夫(Lyapunov)稳定性理论的线性状态反馈控制,从而保证了整个闭环网络控制系统的稳定性。

Remote intelligent control of nonlinear uncertain system under network environment

A remote intelligent control strategy for nonlinear system with uncertainty under network environment is presented, which is based on neural networks nonlinear compensator and linear state feedback controller. A neural networks on-line observer is used to learning the nonlinear characteristics of the local system in order to realize feedback linearization. The weights of neural networks are updated on-line without need of persistency of excitation and the uniformly ultimately bounded stability of the closed-loop error system can be obtained. Finally, a remote controller with state feedback is applied to the linearized system with time-delay, and stability of the closed-loop networked-control system is guaranteed by Lyapunov stability theory.