摘要
针对受参数不确定和外扰影响的混沌Lorenz系统,提出一种基于径向基函数(RBF)神经网络的滑模控制方法. 基于被控系统在不稳定平衡点处状态误差的可控规范形,设计滑模切换面并将其作为神经网络的唯一输入.单入 单出形式的RBF控制器隐层只需7个径向基函数,网络的权值则依滑模趋近条件在线确定.仿真表明该控制器对 系统参数突变和外部干扰具有鲁棒性,同时抑制了抖振.
A novel adaptive radial basis function(RBF) neural network sliding mode strategy is developed to control Lorenz chaos with parametric uncertainties and external disturbances. Based on the controllable canonical form of system state error at its unstable equilibrium,a sliding surface is defined as the only input to the RBF controller. Only seven RBFs are required for the controller and their weights are trained on-line based on the sliding surface approaching condition. The simulation results show that this method is feasible and effective,and the robustness to parametric uncertainties and external disturbance is provided.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2004年第12期4080-4086,共7页
Acta Physica Sinica
