A finite-difference method for linearization in nonlinear estimation algorithms

被引:150
|
作者
Schei, TS [1 ]
机构
[1] SINTEF, Elect & Cybernet, N-7034 Trondheim, Norway
关键词
covariance matrices; estimation algorithms; extended Kalman filters; factorization methods; nonlinear filters; Jacobian matrices; linearization; parameter estimation; recursive estimation; state estimation;
D O I
10.1016/S0005-1098(97)00127-1
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Linearizations of nonlinear functions that are based on Jacobian matrices often cannot be applied in practical applications of nonlinear estimation techniques. An alternative linearization method is presented in this paper. The method assumes that covariance matrices are determined on a square root factored form. A factorization of the output covariance from a nonlinear vector function is directly determined by "perturbing" the nonlinear function with the columns of the factored input covariance, without explicitly calculating the linearization and with no differentiations involved. The output covariance is more accurate than that obtained with the ordinary Jacobian linearization method. It also has an advantage that Jacobian matrices do not have to be derived symbolically. (C) 1997 Elsevier Science Ltd.
引用
收藏
页码:2053 / 2058
页数:6
相关论文
共 50 条
  • [1] A finite-difference method for linearization in nonlinear estimation algorithms (Reprinted from Automatica, vol 33, pg 2053-2058, 1997)
    Schei, TS
    MODELING IDENTIFICATION AND CONTROL, 1998, 19 (03) : 141 - 152
  • [2] Finite-difference method for singular nonlinear systems
    Buhmiler, Sandra
    Rapajic, Sanja
    Medic, Slavica
    Grbic, Tatjana
    NUMERICAL ALGORITHMS, 2018, 79 (01) : 65 - 86
  • [3] Finite-difference method for singular nonlinear systems
    Sandra Buhmiler
    Sanja Rapajić
    Slavica Medić
    Tatjana Grbić
    Numerical Algorithms, 2018, 79 : 65 - 86
  • [4] METHOD OF INVESTIGATING THE CONVERGENCE OF NONLINEAR FINITE-DIFFERENCE SCHEMES
    ARDELYAN, NV
    DIFFERENTIAL EQUATIONS, 1987, 23 (07) : 737 - 745
  • [5] A New Finite-Difference Method for Nonlinear Absolute Value Equations
    Wang, Peng
    Zhang, Yujing
    Zhu, Detong
    MATHEMATICS, 2025, 13 (05)
  • [6] A convergent finite-difference method for a nonlinear variational wave equation
    Holden, H.
    Karlsen, K. H.
    Risebro, N. H.
    IMA JOURNAL OF NUMERICAL ANALYSIS, 2009, 29 (03) : 539 - 572
  • [7] The finite-difference method (FDM)
    不详
    ADVANCES IN IMAGING AND ELECTRON PHYSICS, VOL 116, 2001, 116 : 115 - 191
  • [8] REGULARIZED FINITE-DIFFERENCE ALGORITHMS AND THEIR USE IN GEOPHYSICS
    STRAKHOV, VN
    IVANOV, SN
    IZVESTIYA AKADEMII NAUK SSSR FIZIKA ZEMLI, 1984, (02): : 63 - 83
  • [9] Derivative-Free Finite-Difference Homeier Method for Nonlinear Models
    Al-Shorman, Yanal
    Said Solaiman, Obadah
    Hashim, Ishak
    Springer Proceedings in Mathematics and Statistics, 2023, 414 : 105 - 112
  • [10] The finite-difference method of one-dimensional nonlinear systems analysis
    Shahverdian, AY
    FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY, 2000, 8 (01) : 49 - 65