Article
Full entry |
PDF
(1.0 MB)
Feedback
PDF
(1.0 MB)
Feedback
Keywords:
stochastic systems; state estimation; nonlinear filters; Fokker –Planck equation; numerical solutions; finite volume method; finite difference method
stochastic systems; state estimation; nonlinear filters; Fokker –Planck equation; numerical solutions; finite volume method; finite difference method
Summary:
The paper deals with a filter design for nonlinear continuous stochastic systems with discrete-time measurements. The general recursive solution is given by the Fokker–Planck equation (FPE) and by the Bayesian rule. The stress is laid on the computation of the predictive conditional probability density function from the FPE. The solution of the FPE and its integration into the estimation algorithm is the cornerstone for the whole recursive computation. A new usable numerical scheme for the FPE is designed. In the scheme, the separation technique based on the upwind volume method and the finite difference method for hyperbolic and parabolic part of the FPE is used. It is supposed that separation of the FPE and choice of a suitable numerical method for each part can achieve better estimation quality comparing to application of a single numerical method to the unseparated FPE. The approach is illustrated in some numerical examples.
References:
[1] Daum F. E.: New exact nonlinear filters. In: Bayesian Analysis of Time Series and Dynamic Models (J. C. Spall, ed.), Marcel Dekker, New York 1988, pp. 199–226
[2] Higham D. J., Kloeden P. E.: Maple and Matlab for Stochastic Differential Equations in Finance. Technical Report. University of Strathclyde 2001
[3] Chang J. S., Cooper G.: A practical difference scheme for Fokker–Planck equations. J. Comput. Phys. 6 (1970), 1–16 Zbl 0221.65153
[4] Moral P. del, Jacod J.: Interacting particle filtering with discrete observations. In: Sequential Monte Carlo Methods in Practice (A. Doucet, N. de Freitas, and N. Gordon, eds.), Springer-Verlag, New York 2001, pp. 43–75 MR 1847786
[5] Jazwinski A. H.: Stochastic Processes and Filtering Theory. Academic Press, New York 1970 Zbl 0203.50101
[6] Kalman R. E., Bucy R. S.: New results in linear filtering and prediction theory. J. Basic Engrg. 83 (1961), 95–108 MR 0234760
[7] Kouritzin M. A.: On exact filters for continuous signals with discrete observations. IEEE Trans. Automat. Control 43 (1998), 709–715 MR 1618075 | Zbl 0908.93064
[8] Kushner H. J., Budhijara A. S.: A nonlinear filtering algorithm based on an approximation of the conditional distribution. IEEE Trans. Automat. Control 45 (2000), 580–585 MR 1762882
[9] LeVeque R. J.: Finite Volume Methods for Hyperbolic Problems. Cambridge University Press, New York 2002 MR 1925043 | Zbl 1010.65040
[10] Lototsky S. V., Rozovskii B. L.: Recursive nonlinear filter for a continuous-discrete time model: Separation of parameters and observations. IEEE Trans. Automat. Control 43 (1998), 1154–1158 MR 1636479 | Zbl 0957.93085
[11] Mirkovic D.: $N$-dimensional Finite Element Package. Technical Report. Department of Mathematics, Iowa State University 1996
[12] Park B. T., Petrosian V.: Fokker–Planck equations of stochastic acceleration: A study of numerical methods. Astrophys. J., Suppl. Ser. 103 (1996), 255–267
[13] Press W. H., Flannery B. P., Teukolsky S. A., Vetterling W. T.: Numerical Recipes. Cambridge University Press, New York 1986 MR 0833288 | Zbl 1132.65001
[14] Risken H.: The Fokker–Planck Equation. Springer–Verlag, Berlin 1984 MR 0749386 | Zbl 0866.60071
[15] Schmidt G. C.: Designing nonlinear filters based on Daum’s theory. J. Guidance, Control and Dynamics 16 (1993), 371–376 Zbl 0775.93283
[16] Sorenson H. W., Alspach D. L.: Recursive Bayesian estimation using Gaussian sums. Automatica 7 (1971), 465–479 MR 0321581 | Zbl 0219.93020
[17] Spencer B. F., Bergman L. A.: On the numerical solution of the Fokker–Planck equation for nonlinear stochastic systems. Nonlinear Dynamics 4 (1993), 357–372
[18] Spencer B. F., Wojtkiewicz S. F., Bergman L. A.: Some experiments with massively parallel computation for Monte Carlo simulation of stochastic dynamical systems. In: Proc. Second Internat. Conference on Computational Stochastic Mechanics, Athens 1994
[19] Šimandl M., Švácha J.: Nonlinear filters for continuous-time processes. In: Proc. 5th Internat. Conference on Process Control, Kouty nad Desnou 2002
[20] Šimandl M., Královec J.: Filtering, prediction and smoothing with Gaussian sum Rrpresentation. In: Proc. Symposium on System Identification. Santa Barbara 2000
[21] Šimandl M., Královec, J., Söderström T.: Anticipative grid design in point-mass approach to nonlinear state estimation. IEEE Trans. Automat. Control 47 (2002), 699–702 MR 1893533
[22] Šimandl M., Královec, J., Söderström T.: Advanced point–mass method for nonlinear state estimation. Automatica 42 (2006), 1133–1145 Zbl 1118.93052
[23] Šimandl M., Švácha J.: Separation approach for numerical solution of the Fokker–Planck equation in estimation problem. In: Preprints of 16th IFAC World Congress. Prague 2005
[24] Zhang D. S., Wei G. W., Kouri D. J., Hoffman D. K.: Numerical method for the nonlinear Fokker–Planck equation. Amer. Physical Society 56 (1997), 1197–1206
[25] Zorzano M. P., Mais, H., Vazquez L.: Numerical solution for Fokker–Planck equations in accelerators. Phys. D: Nonlinear Phenomena 113 (1998), 379–381 Zbl 0962.82055
Search
Partner of
