摘要
根据流形理论 ,利用混沌时间序列中某点邻域内最近几点的P次迭代像 ,提出了一种多步自适应预测算法 .仿真说明 ,这种算法使得预测速度成倍提高 ,而预测稳定后得到的误差均方根序列呈指数增长趋势 ,这个指数就是该混沌时间序列的Lyapunov指数 .
In this paper a class of nonlinear adaptive multi-step-prediction algorithm based on the manifold theory was proposed. We have performed the multi-step-prediction by exploiting images of P-step iterations of several nearest neighbors with this method. The simulation indicated that this method was available and could improve the prediction speed, and that the series of the standard deviation of error after prediction has an exponential growth ratio that is the largest Lyapunov exponent.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2003年第12期2995-3001,共7页
Acta Physica Sinica
基金
国防科技预研基金 (批准号 :5 14 3 5 0 5 0 10 1DZ0 2 0 3 )资助的课题~~