𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A new method for the estimation of parameters in differential equations

✍ Scribed by Bruno Van Den Bosch; Leon Hellinckx

Publisher
American Institute of Chemical Engineers
Year
1974
Tongue
English
Weight
646 KB
Volume
20
Category
Article
ISSN
0001-1541

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

A new objective function for estimating parameters in differential equations, based upon a weighted least squares criterion for the residuals of these equations, is presented. The use of Lobatto quadrature in combination with the collocation technique reduces the original problem to one of minimizing a simple algebraic expression with respect to a series of unknowns. The method can be applied to different types of differential equations as shwon by a series of examples and leads to very good estimates. It becomes particularly useful for systems which are linear in the parameters and for which all states are observable since in this case the usual convergence problem is avoided. The gain in computation time when compared with classical methods is significant.

πŸ“œ SIMILAR VOLUMES

A new algorithm for the estimation of pa
A new algorithm for the estimation of parameters in ordinary differential equations
✍ M. Hwang; J. H. Seinfeld πŸ“‚ Article πŸ“… 1972 πŸ› American Institute of Chemical Engineers 🌐 English βš– 382 KB πŸ‘ 2 views

A new computational algorithm for the estimation of parameters in ordinary differential equations from noisy data is presented. The algorithm is computationally faster than quasilinearization because of the reduction of the number of ordinary differential equations that must be solved a t each itera

Numerical Methods for Parameter Estimati
Numerical Methods for Parameter Estimation in Nonlinear Differential Algebraic Equations
✍ Hans Georg Bock; Ekaterina Kostina; Johannes P. SchlΓΆder πŸ“‚ Article πŸ“… 2007 πŸ› John Wiley and Sons 🌐 English βš– 459 KB πŸ‘ 1 views

## Abstract Nonlinear Differential Algebraic Equations (DAEs) are an important class of models for dynamic processes. To establish models that describe the process behavior in a quantitatvely correct way, often parameters in the model have to be determined from observations or measurements of the p