混沌时间序列的2阶预测模型

2-order Prediction Model of Chaotic Time Series

为了克服传统预测方法对混沌时间序列预测精度不高的缺点,提出一种新的基于1阶预测模型(1-OP)和信息融合理论的混沌时间序列2阶预测模型(2-OP).首先根据相空间重构理论建立2个1阶预测模型,然后根据融合估计原理建立2阶预测模型.最后利用Lorenz和Mackey-Glass时间序列对该模型进行验证,结果表明,2阶预测模型对多变量和单变量混沌系统都是有效的.

It introduces a novel 2-order prediction model（2-OP）for chaotic time series based on 1-order prediction model（1-OP） and information fusion theory,in order to overcome the prediction accuracy disavantage of traditional forecasting methods.First,two 1-order prediction models are established based on the Takens theorem,then,2-order prediction model is established according to fusion estimation principle.Finally,the Lorenz equations and the Mackey-Glass equation are applied to test this model,and the results show that the 2-order prediction model is effective for univariate and multivariate chaotic systems.