Autor(i):
M. Podmajerský
Názov:
Parameter Estimation in Processes form Experimental Data
Identifikácia parametrov procesov z experimentálnych dát
Škola:
FCHPT STU
Rok:
2007
Jazyk:
angličtina
Anotácia:
This work deals with dynamic and global optimization for parameter estimation of differential algebraic systems. The estimation of parameters in semi-empirical models is essential in numerous areas of engineering and applied science. The error-in-variables method has been studied from a computational standpoint. This method involves the minimization of a weighted sum of squared errors subject to the model equations. In this work, a method converting the dynamic system of equations into a set of algebraic constraints through the use of orthogonal collocation on finite elements is implemented within MATLAB code DYNOPT. It is compared to a integration method implemented within FORTRAN code GDOC.
Školiteľ:
prof. Ing. Miroslav Fikar, DrSc., prof. M. A. Latifi
Konzultant:
Ing. Michal Čižniar

Kategória publikácie:
ZZZ – Interné publikácie fakulty - nie sú ďalej spracovávané (Diplom. práce, Bakalár. projekty, ŠVOČ ...)
Oddelenie:
OIaRP
Vložil/Upravil:
prof. Ing. Miroslav Fikar, DrSc.
Posledná úprava:
30.5.2007 17:11:01

Plný text:
351.pdf (1.47 MB)
Príloha:
351.zip (91.9 kB)

BibTeX:
@mastersthesis{uiam351,
author={M. Podmajersk\'y},
title={Parameter Estimation in Processes form Experimental Data},
school={FCHPT STU},
year={2007},
annote={This work deals with dynamic and global optimization for parameter estimation of differential algebraic systems. The estimation of parameters in semi-empirical models is essential in numerous areas of engineering and applied science. The error-in-variables method has been studied from a computational standpoint. This method involves the minimization of a weighted sum of squared errors subject to the model equations. In this work, a method converting the dynamic system of equations into a set of algebraic constraints through the use of orthogonal collocation on finite elements is implemented within MATLAB code DYNOPT. It is compared to a integration method implemented within FORTRAN code GDOC.},
supervisor={prof. Ing. Miroslav Fikar, DrSc., prof. M. A. Latifi},
consultant={Ing. Michal {\v{C}}i\v{z}niar},
url={https://www.uiam.sk/assets/publication_info.php?id_pub=351}
}