混沌时间序列多步自适应预测方法  

A novel multi-step adaptive prediction method for chaotic time series

作　　者：孟庆芳[1] 张强[2] 牟文英[1] 

机构地区：[1]山东大学信息科学与工程学院,济南250100 [2]济南市半导体元件实验所,济南250014

出　　处：《物理学报》2006年第4期1666-1671,共6页Acta Physica Sinica

摘　　要：针对混沌时间序列局域自适应预测方法在多步预测中预测器系数无法调节的问题,根据混沌时间序列的短期可预测性及自适应算法的自适应跟踪混沌运动轨迹的特点,提出了混沌时间序列多步自适应预测方法.仿真结果表明,此方法的多步预测性能明显好于局域自适应预测方法的多步预测性能.Based on the short-term predictability of chaotic time series and the adaptive tracking chaotic trajectory of adaptive algorithm, a novel multi-step adaptive prediction method is proposed in this paper to resolve the problem of adjusting the filter parameters of the local adaptive prediction method during multi-step prediction. Simulation results show that this multi-step adaptive prediction method can be successfully used to make multi-step predictions, and its performance is better than that of the local adaptive prediction algorithm.

关 键 词：多步自适应预测方法 局域自适应预测方法 混沌时间序列 运动轨迹 

分 类 号：TP11[自动化与计算机技术—控制理论与控制工程]