摘要
基于贝叶斯理论,提出用马尔科夫链蒙特卡罗(MCMC)方法来估计Lorenz混沌系统的未知参数。首先导出了未知参数分布规律的后验概率密度函数;接着采用自适应Metropolis算法构造Markov链;然后截取收敛的链序列,计算混沌系统参数的估计值。数值试验表明:该方法具有很高的估计精度,同时具有较好的抗噪声性能。
Based on Bayesian theorem, a method is proposed to estimate the unknown parameters of Lorenz chaotic system using Markov Chain Monte Carlo （MCMC） method. Firstly, the posterior probability density function for unknown parameters is deduced. Secondly, taking the posterior probability as the invariant distribution, the Adaptive Metropolis algorithm is used to construct the Markov Chsins. Thirdly, the converged samples are used to calculate the mathematic expectation of the unknown parameters. The results of numerical experiments show that the parameters estimated by the new method have high precision and the noise is filtered effectively from observations at the same time.
出处
《国防科技大学学报》
EI
CAS
CSCD
北大核心
2010年第2期68-72,145,共6页
Journal of National University of Defense Technology
基金
国家自然科学基金资助项目(40775064
40505023)
