Parameter estimation in complicated rational functions

doi:10.1016/0097-8485(95)00082-8

Computers & Chemistry

Volume 20, Issue 3, September 1996, Pages 331-337

https://doi.org/10.1016/0097-8485(95)00082-8 Get rights and content

Abstract

An extension of the previously proposed method [Dimitrov S.D. & Kamenski D.I. (1991) Computers Chem. Engng 15, 657] for unconstrained parameter estimation in models, expressed as the ratio of any linear functions of the unknown parameters, is described. The results from simulated and real data show that the method provides non-local convergence properties. Also, it is superior to the Gauss-Newton and Marquardt algorithms with respect to sensitivity to the initial parameter estimates.

References (21)

S.D. Dimitrov et al.
Computers Chem. Engng
(1991)
S.D. Dimitrov et al.
Computers Chem. Engng
(1995)
D.I. Kamenski et al.
Computers Chem. Engng
(1993)
O.G. Mekenyan et al.
Eur. Polym. J.
(1983)
J.W. Ponton
Computers Chem. Engng
(1993)
G.A. Baker et al.
Padé Approximants
(1981)
Y. Bard
Nonlinear Parameter Estimation
(1974)
J.E. Dennis et al.
Numerical Methods for Unconstrained Optimization and Nonlinear Equations
(1983)
V.A. Evstatiev et al.
DAN SSSR
(1979)
G.E. Forsythe et al.
Computer Methods for Mathematical Computations
(1977)

There are more references available in the full text version of this article.

Cited by (8)

Binary mixture properties: Fitting with canonical rational functions
1999, Computers and Chemical Engineering
Simple empirical functions have been proposed for binary mixture properties fitting. The models are defined as rational functions of the canonical polynomials of Scheffé. The correlations are relatively easy to use and are applicable to a wide variety of properties–composition relationships. If the ternary effects are insignificant they represent the ternary data using parameters obtained from binary information with high accuracy. Additional advantages are also their good interpolating properties. In order to establish the statistical characteristics of the proposed models, non-isothermal viscosity data for eight binary mixtures were tested successfully. The mean absolute deviation between the observed and predicted values was found to be less than 1%.
Overall stability constants: Estimation by non-linear least squares methods
1997, Computers and Chemistry
This paper presents a comparative study of four non-linear least squares methods for overall stability constants estimation on the basis of complex formation function. Techniques included are the Gauss-Newton method, the Marquardt method, the modified simplex method and the recently proposed method of Dimitrov and Kamenski (1996) [Computers and Chemistry 20, 331–337 (1996)]. Results from 15 experimental data sets are reported to illustrate the applicability of these methods. Additionally, the reliability of different approaches for getting initial parameter guesses, which exploit specific features of the phenomenon studied, are also discussed.
NOVIFAST: A Fast Algorithm for Accurate and Precise VFA MRI T 1 Mapping
2018, IEEE Transactions on Medical Imaging
Concurrent optimization of mesh refinement and design parameters in multidisciplinary design
2012, Journal of Aircraft
Concurrent optimization of mesh refinement and design parameters in multidisciplinary design
2012, 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference 2012
Concurrent optimization of mesh refinement and design parameters in multidisciplinary design
2012, Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference

View all citing articles on Scopus

View full text

Parameter estimation in complicated rational functions

Abstract

Computers Chem. Engng

Computers Chem. Engng

Computers Chem. Engng

Eur. Polym. J.

Computers Chem. Engng

Padé Approximants

Nonlinear Parameter Estimation

Numerical Methods for Unconstrained Optimization and Nonlinear Equations

DAN SSSR

Computer Methods for Mathematical Computations