摘要
基于径向基函数神经网络的智能方法对混沌进行控制 .该方法不需要被控混沌系统的解析模型 ,控制的目标可以为周期轨道 ,也可以为连续变化的目标函数 ,在模型参数发生摄动和存在测量噪声情况下 ,控制仍然有效 .研究了神经网络误差对控制精度的影响 ,并给出相关的定理及证明 .针对Logistic映射和Henon吸引子的仿真结果 ,表明了此方法的有效性和可行性 .
An intelligent control method based on RBF neural network is proposed for chaos control. The control objective can be either periodic orbits or continuous variable functions without the need of an analytic model. The method is still effective when there are parameter perturbation and measurement noise. The influence of the RBF model error upon control precision is studied, and related theorem is developed and testified. Simulation results with a Logistic mapping and Henon attractor show the effectiveness and feasibility of this method.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2003年第3期531-535,共5页
Acta Physica Sinica
