Hybrid three-dimensional variation and particle filtering for nonlinear systems

doi:10.1088/1674-1056/22/3/030505

Chin. Phys. B ›› 2013, Vol. 22 ›› Issue (3): 30505-030505.doi: 10.1088/1674-1056/22/3/030505

Hybrid three-dimensional variation and particle filtering for nonlinear systems

冷洪泽, 宋君强

College of Computer, National University of Defense Technology, Changsha 410073, China

收稿日期:2012-06-10 修回日期:2012-09-07 出版日期:2013-02-01 发布日期:2013-02-01
基金资助:
Project supported by the National Natural Science Foundation of China (Grant No. 41105063).

Hybrid three-dimensional variation and particle filtering for nonlinear systems

Leng Hong-Ze (冷洪泽), Song Jun-Qiang (宋君强)

College of Computer, National University of Defense Technology, Changsha 410073, China

Received:2012-06-10 Revised:2012-09-07 Online:2013-02-01 Published:2013-02-01
Contact: Leng Hong-Ze E-mail:hzleng@nudt.edu.cn
Supported by:
Project supported by the National Natural Science Foundation of China (Grant No. 41105063).

摘要/Abstract

摘要： This work addresses the problem of estimating the states of nonlinear dynamic systems with sparse observations. We present a hybrid three-dimensional variation (3DVar) and particle piltering (PF) method, which combines the advantages of 3DVar and particle-based filters. By minimizing the cost function, this approach will produce a better proposal distribution of the state. Afterwards the stochastic resampling step in standard PF can be avoided through a deterministic scheme. The simulation results show that the performance of the new method is superior to the traditional ensemble Kalman filtering (EnKF) and the standard PF, especially in highly nonlinear systems.

关键词: three-dimensional variation (3DVar), particle piltering (PF), ensemble Kalman filtering (EnKF), chaos system

Abstract: This work addresses the problem of estimating the states of nonlinear dynamic systems with sparse observations. We present a hybrid three-dimensional variation (3DVar) and particle piltering (PF) method, which combines the advantages of 3DVar and particle-based filters. By minimizing the cost function, this approach will produce a better proposal distribution of the state. Afterwards the stochastic resampling step in standard PF can be avoided through a deterministic scheme. The simulation results show that the performance of the new method is superior to the traditional ensemble Kalman filtering (EnKF) and the standard PF, especially in highly nonlinear systems.

Key words: three-dimensional variation (3DVar), particle piltering (PF), ensemble Kalman filtering (EnKF), chaos system

中图分类号: (Nonlinear dynamics and chaos)

05.45.-a

02.60.-x (Numerical approximation and analysis)

冷洪泽, 宋君强. Hybrid three-dimensional variation and particle filtering for nonlinear systems[J]. Chin. Phys. B, 2013, 22(3): 30505-030505.

Leng Hong-Ze (冷洪泽), Song Jun-Qiang (宋君强). Hybrid three-dimensional variation and particle filtering for nonlinear systems[J]. Chin. Phys. B, 2013, 22(3): 30505-030505.

参考文献 25

[1]	Eubank R L 2006 A Kalman Filter Primer (Boca Raton, Fla.: Chapman& Hall/CRC)
[2]	Speyer J L and Chung W H 2008 Stochastic Processes, Estimation,and Control (Philadelphia: Society for Industrial and Applied Mathematics)
[3]	Psiaki M L 2005 Journal of Guidance, Control, and Dynamics 28 885
[4]	Houtekamer P L and Mitchell H L 2005 Quart. J. R. Meteorol. Soc. 1313269
[5]	Hunt B R, Kostelich E J and Szunyogh I 2007 Physica D 230 112
[6]	Reich S 2012 Quart. J. R. Meteorol. Soc. 138 222
[7]	Zhang Z T and Zhang J S 2010 Chin. Phys. B 19 104601
[8]	Arulampalam M S, Maskell S, Gordon N and Clapp T 2002 IEEETrans. Signal Process. 50 174
[9]	Schon T, Gustafsson F and Nordlund P 2005 IEEE Trans. Signal Process.53 2279
[10]	Eyink G L and Kim S 2006 J. Stat. Phys. 123 1071
[11]	Nakano S, Ueno G and Higuchi T 2007 Nonlin. Processes Geophys. 14395
[12]	Vanleeuwen P J 2010 Quart. J. R. Meteorol. Soc. 136 1991
[13]	Bi J, Guan W and Qi L T 2012 Chin. Phys. B 21 068901
[14]	Kunihama T, Omori Y and Zhang Z 2012 J. Time Series Anal. 33 61
[15]	Kotceha J H and Djuric PM2003 IEEE Trans. Signal Process. 51 2592
[16]	Merwe R V D and Wan E 2003 Proceedings of the IEEE InternationalConference on Acoustics Speech, and Signal Processing (Hongkong)p. 701
[17]	Míguez J 2006 Digital Signal Processing 9 1
[18]	Won S P, Melek W W and Golnaraghi F 2010 IEEE Trans. IndustrialElectron. 57 1787
[19]	Won S P, Melek W W and Golnaraghi F 2011 Meas. Sci. Technol. 22125108
[20]	Hoteit I, Luo X and Pham D 2012 Mon. Wea. Rev. 140 528
[21]	Stordal A, Karlsen H, Nvdal G, Skaug H and Vall`es B 2011 ComputationalGeosciences 15 293
[22]	Edwards AW F 1972 Likelihood (Cambridge: Cambridge UniversityPress)
[23]	Vanleeuwen P J 2009 Mon. Wea. Rev. 137 4089
[24]	Zupanski M, Navon I M and Zupanski D 2008 Q. J. R. Meteorol. Soc.134 1039
[25]	Zupanski M 2005 Mon. Wea. Rev. 133 1710

Hybrid three-dimensional variation and particle filtering for nonlinear systems

Hybrid three-dimensional variation and particle filtering for nonlinear systems

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 25

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	徐艳春, 杨春玲, 瞿晓东. A new approach to detecting weak signal in strong noise based on chaos system control[J]. 中国物理B, 2010, 19(3): 30516-030516.
[2]	高飞, 李卓球, 童恒庆. Parameters estimation online for Lorenz system by a novel quantum-behaved particle swarm optimization[J]. 中国物理B, 2008, 17(4): 1196-1201.