一种时变耦合映象格子模型的初值估计方法

耦合映象格子（Coupled map lattice，CML）模型是非线性科学研究中的一个重要模型。从CML系统中恢复系统的初始条件对信号处理等问题的研究非常重要。本文在符号动力学方法的基础上，针对全局耦合映象模型，提出一种基于时变映象系数恢复信号初值的新方法。实验结果表明，本文方法能够有效地恢复初值的统计特性，使整个格点信号均值等于给定信号均值。此外，采用时变映象系数恢复的信号值与原信号之间偏差、均方误差（Mean square error，MSE）都较传统方法小，而且与原信号之间有较强的相关性，能够更好地刻画实际信号的物理过程，并对系统初始条件作出稳键估计。

Estimation Method of Initial Conditions Based on Time-Varying Coupled Map Lattice Model

Coupled map lattice(CML) model is an attractive one in nonlinear system research.Recovering initial conditions in CML system are very important to chaotic signal processing.Based on the traditional symbolic dynamic-based method,a novel algorithm based on a time-varying parameter of globally coupled map lattice is proposed.Results show that the new algorithm can recover the statistical property of initial conditions.The mean of the recovered initial conditions is equal to the given value.This method has minor biases,lower mean square errors(MSEs) and a higher correlation with the given data.So it is more appropriate to describe the physical property of practical systems,and gives a robust estimation for initial conditions of the system.