非线性系统混沌运动的神经网络控制

设计前馈反传神经网络控制非线性系统混沌运动的新方法.根据扰动参数模型输入输出数据,按照非线性学习算法训练网络产生系统稳定所需的小扰动控制信号,去镇定混沌运动,使嵌入在混沌吸引子中的不稳定周期轨道回到稳定不动点上.Hnon映射数值仿真结果表明,这种方法控制非线性混沌系统响应速度快、控制精度高关键词：混沌控制神经网络吸引子非线性

Neural network control for nonlinear chaotic motion

A novel method for chaotic control with feed forward backpropagating neural network is presented. Combined input output data obtained from the perturbation parameter model with nonlinear learning algorithm, neural networks are trained to generate the small disturbance control, then to suppress chaotic behaviour, the unstable periodic orbit embedded in the chaotic attractor is drived and directed to a stable fixed point. The numerical simulations on Henon map demonstrate that rapid response and higher accuracy of the nonlinear chaotic system can be obtained based on the proposed control scheme.