Development of neural network models for a crude oil distillation column

This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the models were developed for real time optimisation (RTO) applications, they are steady-state, multivariable models. Training and testing data used to develop the models were ge...

Full description

Bibliographic Details
Main Authors: Mohd. Yusof, Khairiyah, Karray, Fakhri, Douglas, Peter L.
Format: Article
Language:English
Published: Penerbit UTM Press 2003
Subjects:
Online Access:http://eprints.utm.my/1508/
http://eprints.utm.my/1508/1/JT38F%5B6%5D.pdf
_version_ 1848890153244819456
author Mohd. Yusof, Khairiyah
Karray, Fakhri
Douglas, Peter L.
author_facet Mohd. Yusof, Khairiyah
Karray, Fakhri
Douglas, Peter L.
author_sort Mohd. Yusof, Khairiyah
building UTeM Institutional Repository
collection Online Access
description This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the models were developed for real time optimisation (RTO) applications, they are steady-state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO.
first_indexed 2025-11-15T20:37:32Z
format Article
id utm-1508
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:37:32Z
publishDate 2003
publisher Penerbit UTM Press
recordtype eprints
repository_type Digital Repository
spelling utm-15082017-11-01T04:17:41Z http://eprints.utm.my/1508/ Development of neural network models for a crude oil distillation column Mohd. Yusof, Khairiyah Karray, Fakhri Douglas, Peter L. TP Chemical technology This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the models were developed for real time optimisation (RTO) applications, they are steady-state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO. Penerbit UTM Press 2003-06 Article PeerReviewed application/pdf en http://eprints.utm.my/1508/1/JT38F%5B6%5D.pdf Mohd. Yusof, Khairiyah and Karray, Fakhri and Douglas, Peter L. (2003) Development of neural network models for a crude oil distillation column. Jurnal Teknologi F (38F). pp. 53-64. ISSN 0127-9696 http://www.penerbit.utm.my/onlinejournal/38/F/JT38F6.pdf
spellingShingle TP Chemical technology
Mohd. Yusof, Khairiyah
Karray, Fakhri
Douglas, Peter L.
Development of neural network models for a crude oil distillation column
title Development of neural network models for a crude oil distillation column
title_full Development of neural network models for a crude oil distillation column
title_fullStr Development of neural network models for a crude oil distillation column
title_full_unstemmed Development of neural network models for a crude oil distillation column
title_short Development of neural network models for a crude oil distillation column
title_sort development of neural network models for a crude oil distillation column
topic TP Chemical technology
url http://eprints.utm.my/1508/
http://eprints.utm.my/1508/
http://eprints.utm.my/1508/1/JT38F%5B6%5D.pdf