首页 | 官方网站   微博 | 高级检索  
     

自组织状态空间模型参数初始分布搜索算法
引用本文:甘敏,彭辉,黄云志,董学平.自组织状态空间模型参数初始分布搜索算法[J].自动化学报,2012,38(9):1538-1543.
作者姓名:甘敏  彭辉  黄云志  董学平
作者单位:1.合肥工业大学电气与自动化工程学院 合肥 230009;
基金项目:国家国际科技合作计划(2011DFA10440);国家自然科学基金(70921001,61203106,71271215,51007016,60974022);湖南省科技厅国际合作重点项目(2009WK2009);中央高校基本科研业务费专项资金(2010HGBZ0597,2011HGQC0995)资助~~
摘    要:自组织状态空间模型为估计非线性非高斯状态空间模型中的未知参数提供了一种有效方法. 针对自组织状态空间模型中参数的初始分布难以确定的难点,提出了一种搜索自组织状态空间模型参数初始分布的算法. 所用搜索算法基于一种高效的进化模型,具有全局搜索能力,使得参数的初始分布向真实参数"移动". 数值实验分析结果验证了提出方法的有效性.

关 键 词:自组织状态空间模型    粒子滤波    参数估计    非线性    非高斯
收稿时间:2011-1-4
修稿时间:2012-5-10

Initial Distribution Search Algorithm for Self-organizing State Space Model
GAN Min,PENG Hui,HUANG Yun-Zhi,DONG Xue-Ping.Initial Distribution Search Algorithm for Self-organizing State Space Model[J].Acta Automatica Sinica,2012,38(9):1538-1543.
Authors:GAN Min  PENG Hui  HUANG Yun-Zhi  DONG Xue-Ping
Affiliation:1.School of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009;2.School of Information Science and Engineering, Central South University, Changsha 410083;3.Hunan Engineering Laboratory for Advanced Control and Intelligent Automation, Changsha 410083
Abstract:The self-organizing state space model provides an efficient approach to estimating unknown parameters in a nonlinear non-Gaussian state space model. However, a difficult problem is how to determinate the initial distributions of parameters for a self-organizing state space model. To address this problem, this paper proposes an algorithm to seek the initial distribution of parameters for a self-organizing state space model. The proposed algorithm is based on an efficient evolutionary computation model which has global search capability. It makes the initial distribution of parameters close to the true parameter situation. The results of numerical experiments show the effectiveness of the proposed algorithm.
Keywords:Self-organizing state space model  particle filter  parameter estimation  nonlinear  non-Gaussian
本文献已被 CNKI 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号