UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Statistical diagnosis of process-model mismatch by means of the Lagrange multiplier test

Quaglio, M; Fraga, E; Galvanin, F; (2019) Statistical diagnosis of process-model mismatch by means of the Lagrange multiplier test. In: Kiss, Anton and Zondervan, Edwin and Lakerveld, Richard and Ozkan, Leyla, (eds.) Proceedings of the 29th European Symposium on Computer Aided Process Engineering (ESCAPE-29). (pp. pp. 679-684). Elsevier: Cham, Switzerland.

[img] Text
stat_diagnosis_LM_test_v3.pdf - Accepted version
Access restricted to UCL open access staff

Download (315kB)

Abstract

Modelling chemical processes frequently requires the construction of complex systems of differential and algebraic equations involving a high number of state variables and parameters. Whenever a model structure is proposed, its adequacy is checked with a goodness-of-fit test. The goodness-of-fit test is capable of detecting the presence of overfitting or under-fitting. However, when some modelling error is detected, the test does not provide guidance on how to modify the model equations to match the behaviour of the physical system under analysis. In this work, a test statistic is derived from a tailored Lagrange multiplier test with the aim of diagnosing potential sources of process-model mismatch and to provide guidance on how to evolve approximated model structures towards a higher level of complexity. The proposed test is applied on a simulated case study of a yeast growth model in a fed-batch bioreactor.

Type: Proceedings paper
Title: Statistical diagnosis of process-model mismatch by means of the Lagrange multiplier test
Event: 29th European Symposium on Computer Aided Process Engineering (ESCAPE-29), 16-19 June 2019, Eindhoven, The Netherlands
ISBN: 9780128186343
DOI: 10.1016/B978-0-12-818634-3.50114-4
Publisher version: https://doi.org/10.1016/B978-0-12-818634-3.50114-4
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: model misspecification, model building, Lagrange multiplier, maximum likelihood, Fisher information
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Chemical Engineering
URI: https://discovery.ucl.ac.uk/id/eprint/10075596
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item