A Unified Framework for Systematic Model Improvement

Niels Rode Kristensen; Henrik Madsen; Sten Bay Jørgensen

doi:10.1016/S1570-7946(03)80488-1

A Unified Framework for Systematic Model Improvement

Niels Rode Kristensen, Henrik Madsen, Sten Bay Jørgensen

Department of Chemical and Biochemical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

A unified framework for improving the quality of continuous time models of dynamic systems based on experimental data is presented. The framework is based on an interplay between stochastic differential equation (SDE) modelling, statistical tests and multivariate nonparametric regression. This combination provides systematic methods for pinpointing and repairing model deficiencies by uncovering their structural origin. The potential of the proposed framework in terms of modelling complex dynamic phenomena such as reaction kinetics is illustrated with a case study involving a model of a fed-batch bioreactor, where it is illustrated how an incorrectly modelled biomass growth rate can be pinpointed and an estimate provided of the functional relation needed to properly describe it.

Original language	English
Title of host publication	Process Systems Engineering 2003 : 8th International Symposium on Process Systems Engineering
Volume	15B
Publication date	2003
Pages	1292-1297
ISBN (Print)	978-0-444-51404-2
DOIs	https://doi.org/10.1016/S1570-7946(03)80488-1
Publication status	Published - 2003
Event	8th International Symposium on Process Systems Engineering - Kunming, China Duration: 22 Jun 2003 → 27 Jun 2003 Conference number: 8

Conference

Conference	8th International Symposium on Process Systems Engineering
Number	8
Country/Territory	China
City	Kunming
Period	22/06/2003 → 27/06/2003

Series	Computer Aided Chemical Engineering
Volume	15
ISSN	1570-7946

Access to Document

10.1016/S1570-7946(03)80488-1

OpenUrl availability

Full text

Cite this

@inproceedings{d1c33fb7e81243f491e20ad08c7e82ca,

title = "A Unified Framework for Systematic Model Improvement",

abstract = "A unified framework for improving the quality of continuous time models of dynamic systems based on experimental data is presented. The framework is based on an interplay between stochastic differential equation (SDE) modelling, statistical tests and multivariate nonparametric regression. This combination provides systematic methods for pinpointing and repairing model deficiencies by uncovering their structural origin. The potential of the proposed framework in terms of modelling complex dynamic phenomena such as reaction kinetics is illustrated with a case study involving a model of a fed-batch bioreactor, where it is illustrated how an incorrectly modelled biomass growth rate can be pinpointed and an estimate provided of the functional relation needed to properly describe it.",

author = "Kristensen, {Niels Rode} and Henrik Madsen and J{\o}rgensen, {Sten Bay}",

year = "2003",

doi = "10.1016/S1570-7946(03)80488-1",

language = "English",

isbn = "978-0-444-51404-2 ",

volume = "15B",

series = "Computer Aided Chemical Engineering",

publisher = "Elsevier",

pages = "1292--1297",

booktitle = "Process Systems Engineering 2003",

note = "8th International Symposium on Process Systems Engineering, PSE8 ; Conference date: 22-06-2003 Through 27-06-2003",

}

Kristensen, NR, Madsen, H & Jørgensen, SB 2003, A Unified Framework for Systematic Model Improvement. in Process Systems Engineering 2003: 8th International Symposium on Process Systems Engineering. vol. 15B, Computer Aided Chemical Engineering, vol. 15, pp. 1292-1297, 8th International Symposium on Process Systems Engineering, Kunming, China, 22/06/2003. https://doi.org/10.1016/S1570-7946(03)80488-1

A Unified Framework for Systematic Model Improvement. / Kristensen, Niels Rode; Madsen, Henrik; Jørgensen, Sten Bay.
Process Systems Engineering 2003: 8th International Symposium on Process Systems Engineering. Vol. 15B 2003. p. 1292-1297 (Computer Aided Chemical Engineering, Vol. 15).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A Unified Framework for Systematic Model Improvement

AU - Kristensen, Niels Rode

AU - Madsen, Henrik

AU - Jørgensen, Sten Bay

N1 - Conference code: 8

PY - 2003

Y1 - 2003

N2 - A unified framework for improving the quality of continuous time models of dynamic systems based on experimental data is presented. The framework is based on an interplay between stochastic differential equation (SDE) modelling, statistical tests and multivariate nonparametric regression. This combination provides systematic methods for pinpointing and repairing model deficiencies by uncovering their structural origin. The potential of the proposed framework in terms of modelling complex dynamic phenomena such as reaction kinetics is illustrated with a case study involving a model of a fed-batch bioreactor, where it is illustrated how an incorrectly modelled biomass growth rate can be pinpointed and an estimate provided of the functional relation needed to properly describe it.

AB - A unified framework for improving the quality of continuous time models of dynamic systems based on experimental data is presented. The framework is based on an interplay between stochastic differential equation (SDE) modelling, statistical tests and multivariate nonparametric regression. This combination provides systematic methods for pinpointing and repairing model deficiencies by uncovering their structural origin. The potential of the proposed framework in terms of modelling complex dynamic phenomena such as reaction kinetics is illustrated with a case study involving a model of a fed-batch bioreactor, where it is illustrated how an incorrectly modelled biomass growth rate can be pinpointed and an estimate provided of the functional relation needed to properly describe it.

U2 - 10.1016/S1570-7946(03)80488-1

DO - 10.1016/S1570-7946(03)80488-1

M3 - Article in proceedings

SN - 978-0-444-51404-2

VL - 15B

T3 - Computer Aided Chemical Engineering

SP - 1292

EP - 1297

BT - Process Systems Engineering 2003

T2 - 8th International Symposium on Process Systems Engineering

Y2 - 22 June 2003 through 27 June 2003

ER -

A Unified Framework for Systematic Model Improvement

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this