Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit

Jerome Frutiger; Jens Abildskov; Gürkan Sin

doi:10.1016/b978-0-444-63578-5.50079-7

Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit

Jerome Frutiger, Jens Abildskov, Gürkan Sin

Department of Chemical and Biochemical Engineering

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

Abstract

Flammability data is needed to assess the risk of fire and explosions. This study presents a new group contribution (GC) model to predict the upper flammability limit UFL oforganic chemicals. Furthermore, it provides a systematic method for outlier treatment inorder to improve the parameter estimation of the GC model. The new method identifies and removes outliers based on the empirical cumulative distribution plot. It is compared to outlier detection based on Cook’s distance and normal cumulative distribution.

Original language	English
Title of host publication	Proceedings of the 25th European Symposium on Computer Aided Process Engineering
Editors	Krist V. Gernaey, Jakob K. Huusom, Rafiqul Gani
Publisher	Elsevier
Publication date	2015
Pages	503-508
ISBN (Print)	978-0-444-63429-0
DOIs	https://doi.org/10.1016/b978-0-444-63578-5.50079-7
Publication status	Published - 2015
Event	25th European Symposium on Computer Aided Process Engineering : 12th International Symposium on Process Systems Engineering - Copenhagen, Denmark Duration: 31 May 2015 → 4 Jun 2015 http://www.pse2015escape25.dk/

Conference

Conference	25th European Symposium on Computer Aided Process Engineering
Country/Territory	Denmark
City	Copenhagen
Period	31/05/2015 → 04/06/2015
Internet address	http://www.pse2015escape25.dk/

Series	Computer Aided Chemical Engineering
Volume	37
ISSN	1570-7946

Keywords

Outlier treatment
Flammability limit
Group contribution

Access to Document

10.1016/b978-0-444-63578-5.50079-7

OpenUrl availability

Full text

Cite this

Frutiger, J., Abildskov, J., & Sin, G. (2015). Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit. In K. V. Gernaey, J. K. Huusom, & R. Gani (Eds.), Proceedings of the 25th European Symposium on Computer Aided Process Engineering (pp. 503-508). Elsevier. https://doi.org/10.1016/b978-0-444-63578-5.50079-7

Frutiger, Jerome ; Abildskov, Jens ; Sin, Gürkan. / Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit. Proceedings of the 25th European Symposium on Computer Aided Process Engineering . editor / Krist V. Gernaey ; Jakob K. Huusom ; Rafiqul Gani. Elsevier, 2015. pp. 503-508 (Computer Aided Chemical Engineering, Vol. 37).

@inproceedings{3a12925f98094b61896899a4c4484110,

title = "Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit",

abstract = "Flammability data is needed to assess the risk of fire and explosions. This study presents a new group contribution (GC) model to predict the upper flammability limit UFL oforganic chemicals. Furthermore, it provides a systematic method for outlier treatment inorder to improve the parameter estimation of the GC model. The new method identifies and removes outliers based on the empirical cumulative distribution plot. It is compared to outlier detection based on Cook{\textquoteright}s distance and normal cumulative distribution.",

keywords = "Outlier treatment, Flammability limit, Group contribution",

author = "Jerome Frutiger and Jens Abildskov and G{\"u}rkan Sin",

year = "2015",

doi = "10.1016/b978-0-444-63578-5.50079-7",

language = "English",

isbn = "978-0-444-63429-0 ",

series = "Computer Aided Chemical Engineering",

publisher = "Elsevier",

pages = "503--508",

editor = "Gernaey, {Krist V. } and { Huusom}, {Jakob K.} and Gani, { Rafiqul }",

booktitle = "Proceedings of the 25th European Symposium on Computer Aided Process Engineering",

address = "United Kingdom",

note = "25th European Symposium on Computer Aided Process Engineering : 12th International Symposium on Process Systems Engineering, PSE2015/ESCAPE25 ; Conference date: 31-05-2015 Through 04-06-2015",

url = "http://www.pse2015escape25.dk/",

}

Frutiger, J, Abildskov, J & Sin, G 2015, Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit. in KV Gernaey, JK Huusom & R Gani (eds), Proceedings of the 25th European Symposium on Computer Aided Process Engineering . Elsevier, Computer Aided Chemical Engineering, vol. 37, pp. 503-508, 25th European Symposium on Computer Aided Process Engineering , Copenhagen, Denmark, 31/05/2015. https://doi.org/10.1016/b978-0-444-63578-5.50079-7

Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit. / Frutiger, Jerome; Abildskov, Jens ; Sin, Gürkan.
Proceedings of the 25th European Symposium on Computer Aided Process Engineering . ed. / Krist V. Gernaey; Jakob K. Huusom; Rafiqul Gani. Elsevier, 2015. p. 503-508 (Computer Aided Chemical Engineering, Vol. 37).

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

TY - GEN

T1 - Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit

AU - Frutiger, Jerome

AU - Abildskov, Jens

AU - Sin, Gürkan

PY - 2015

Y1 - 2015

N2 - Flammability data is needed to assess the risk of fire and explosions. This study presents a new group contribution (GC) model to predict the upper flammability limit UFL oforganic chemicals. Furthermore, it provides a systematic method for outlier treatment inorder to improve the parameter estimation of the GC model. The new method identifies and removes outliers based on the empirical cumulative distribution plot. It is compared to outlier detection based on Cook’s distance and normal cumulative distribution.

AB - Flammability data is needed to assess the risk of fire and explosions. This study presents a new group contribution (GC) model to predict the upper flammability limit UFL oforganic chemicals. Furthermore, it provides a systematic method for outlier treatment inorder to improve the parameter estimation of the GC model. The new method identifies and removes outliers based on the empirical cumulative distribution plot. It is compared to outlier detection based on Cook’s distance and normal cumulative distribution.

KW - Outlier treatment

KW - Flammability limit

KW - Group contribution

U2 - 10.1016/b978-0-444-63578-5.50079-7

DO - 10.1016/b978-0-444-63578-5.50079-7

M3 - Article in proceedings

SN - 978-0-444-63429-0

T3 - Computer Aided Chemical Engineering

SP - 503

EP - 508

BT - Proceedings of the 25th European Symposium on Computer Aided Process Engineering

A2 - Gernaey, Krist V.

A2 - Huusom, Jakob K.

A2 - Gani, Rafiqul

PB - Elsevier

T2 - 25th European Symposium on Computer Aided Process Engineering

Y2 - 31 May 2015 through 4 June 2015

ER -

Frutiger J, Abildskov J , Sin G. Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit. In Gernaey KV, Huusom JK, Gani R, editors, Proceedings of the 25th European Symposium on Computer Aided Process Engineering . Elsevier. 2015. p. 503-508. (Computer Aided Chemical Engineering, Vol. 37). doi: 10.1016/b978-0-444-63578-5.50079-7

Outlier treatment for improving parameter estimation of group contribution based models for upper flammability limit

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this