针对确定突发事件中危险源的位置估计问题,提出一种基于 hermit基函数的投影滤波方法.通过将其概率解投影到指定状态空间中,通过投影空间中的艾尔米特基函数构造出近似解,即状态的先验概率密度函数,最后由贝叶斯估计得到状态的后验概率密度函数,给出算法的收敛性和计算复杂度分析.仿真实验证明投影滤波方法有效减少滤波估计中所需的计算量,并提高了估计精度.
Abstract
In this paper, a method applying projection filter algorithm based on hermit primary function has been proposed, which is focusing on dealing with the hazard position estimation of sudden accidents problem. By constructing an approximate solution with the hermit primary function in the projection space, the new algorithm could approximate the nonlinear filter result by solving for the prior probability density, then a posterior probability density function is gained through Bayesian formula, finally, the performance of convergence and computational complexity are considered and discussed. Simulating experiments results show that the new projection filter method can improve the estimating accuracy and reduce calculation.
关键词
投影滤波 /
贝叶斯估计 /
位置估计 /
随机微分模型
{{custom_keyword}} /
Key words
projection filter /
Bayesian estimation /
position estimation /
stochastic differential model
{{custom_keyword}} /
中图分类号:
U666.11
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李雄伟, 刘建业, 康国华. TERCOM地形高程辅助导航系统发展及应用研究[J]. 中国惯性技术学报, 2006, 14(1): 34-40. Li Xiongwei, Liu Jianye, Kang Guohua. Development and application of TERCOM elevation-aided navigation system[J]. Journal of Chinese Inertial Technology, 2006, 14(1): 34-40.
[2] Kalman R E, Bertram J. A unified approach to the theory of sampling systems[J]. Journal of the Franklin Institute, 1959, 267(5): 405-436.
[3] Bucy R S, Senne K D. Digital synthesis of nonlinear filters[J]. Automatica, 1971, 7: 287-298.
[4] Moylan P J. Note on Kalman-Bucy filters with zero measurement noise[J]. IEEE Transactions on Automatic Control, 1974, 19(3): 263-264.
[5] Johan B, Willem S. Kalman filter configurations for a lowcost loosely integrated inertial navigation system on an airship[J]. Control Engineering Practice, 2008, 16(12): 1509-1518.
[6] Julier S J, Uhlmann J K. Non-divergent estimation algorithm in the presence of unknown correlations[C]// Proceedings of the 1997 American Control Conference, Albuquerque, NM, USA: IEEE, 1997, 4: 2369-2373.
[7] Gordon N, Salmond D. Novel approach to non-linear and non-Gaussian Bayesian state estimation[J]. Proc of Institute Electric Engineering, 1993, 140(2): 107-113.
[8] Inclan C. Detection of multiple changes of variance using posterior odds[J]. Journal of Business & Economic Statistics, 1993, 11: 289-300.
[9] Klebaner F C. Introduction to stochastic calculus with applications[M]. Beijing: Beijing World Publishing Corporation, 2004.
[10] Beard R, Gunther J, Lawton J, et al. Nonlinear projection filter Based on galerkin approximation[J]. Journal of Guidance, Control and Dynamics, 1999, 22(2): 258-266.
[11] Brigo D, Hanzon B, LeGlanc F. A differential geometric approach to nonlinear filtering: The projection filter[J]. IEEE Transactions on Automatic Control, 1998, 43(2): 247-252.
[12] 姚西峰, 钱峰, 田蔚风. 基于粒子滤波的GPS/DR组合导航算法研究[J]. 计算机仿真, 2008, 25(7): 262-265. Yao Xifeng, Qian Feng, Tian Weifeng. A GPS/DR intergrated navigation algorithm based on particle filter[J]. Computer Simulation, 2008, 25(7): 262-265.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(60904087, D040103);中央高校基础科研业务费专项资金(HEUCFX41302); 黑龙江省留学归国人员科学基金(LC2013C21)
{{custom_fund}}