Evaluation of neural networks for simulation of three-phase bubble column reactors

T. M. Leib, P. L. Mills, J. J. Lerou, J. R. Turner

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

The use of a neural network model (NNM) to simulate the performance of a three-phase slurry bubble-column reactor for Fischer-Tropsch synthesis is investigated. The learning set needed to generate the NNM is obtained from a cell-type model where the number of cells relates to the degree of backmixing. To develop the neural network and to perform the required learning, model-predicted output responses are generated from the cell model by using all possible combinations of six key input parameters. The axial variation of the output responses is represented by a recurrent NNM. The NNM parameters are then identified using a special-purpose package that implements both training and analysis. To simulate the behaviour of an actual reactor, data used for training are corrupted with random noise. The NNM obtained from noisy data exhibits substantial filtering capability.

Original languageEnglish (US)
Pages (from-to)690-696
Number of pages7
JournalChemical Engineering Research and Design
Volume73
Issue numberA6
StatePublished - Aug 1995

Fingerprint

Bubble columns
Neural networks
Fischer-Tropsch synthesis
Recurrent neural networks

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)

Cite this

Leib, T. M., Mills, P. L., Lerou, J. J., & Turner, J. R. (1995). Evaluation of neural networks for simulation of three-phase bubble column reactors. Chemical Engineering Research and Design, 73(A6), 690-696.
Leib, T. M. ; Mills, P. L. ; Lerou, J. J. ; Turner, J. R. / Evaluation of neural networks for simulation of three-phase bubble column reactors. In: Chemical Engineering Research and Design. 1995 ; Vol. 73, No. A6. pp. 690-696.
@article{411320d2827f43a89db654f5d3ef2404,
title = "Evaluation of neural networks for simulation of three-phase bubble column reactors",
abstract = "The use of a neural network model (NNM) to simulate the performance of a three-phase slurry bubble-column reactor for Fischer-Tropsch synthesis is investigated. The learning set needed to generate the NNM is obtained from a cell-type model where the number of cells relates to the degree of backmixing. To develop the neural network and to perform the required learning, model-predicted output responses are generated from the cell model by using all possible combinations of six key input parameters. The axial variation of the output responses is represented by a recurrent NNM. The NNM parameters are then identified using a special-purpose package that implements both training and analysis. To simulate the behaviour of an actual reactor, data used for training are corrupted with random noise. The NNM obtained from noisy data exhibits substantial filtering capability.",
author = "Leib, {T. M.} and Mills, {P. L.} and Lerou, {J. J.} and Turner, {J. R.}",
year = "1995",
month = "8",
language = "English (US)",
volume = "73",
pages = "690--696",
journal = "Chemical Engineering Research and Design",
issn = "0263-8762",
publisher = "Institution of Chemical Engineers",
number = "A6",

}

Leib, TM, Mills, PL, Lerou, JJ & Turner, JR 1995, 'Evaluation of neural networks for simulation of three-phase bubble column reactors', Chemical Engineering Research and Design, vol. 73, no. A6, pp. 690-696.

Evaluation of neural networks for simulation of three-phase bubble column reactors. / Leib, T. M.; Mills, P. L.; Lerou, J. J.; Turner, J. R.

In: Chemical Engineering Research and Design, Vol. 73, No. A6, 08.1995, p. 690-696.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluation of neural networks for simulation of three-phase bubble column reactors

AU - Leib, T. M.

AU - Mills, P. L.

AU - Lerou, J. J.

AU - Turner, J. R.

PY - 1995/8

Y1 - 1995/8

N2 - The use of a neural network model (NNM) to simulate the performance of a three-phase slurry bubble-column reactor for Fischer-Tropsch synthesis is investigated. The learning set needed to generate the NNM is obtained from a cell-type model where the number of cells relates to the degree of backmixing. To develop the neural network and to perform the required learning, model-predicted output responses are generated from the cell model by using all possible combinations of six key input parameters. The axial variation of the output responses is represented by a recurrent NNM. The NNM parameters are then identified using a special-purpose package that implements both training and analysis. To simulate the behaviour of an actual reactor, data used for training are corrupted with random noise. The NNM obtained from noisy data exhibits substantial filtering capability.

AB - The use of a neural network model (NNM) to simulate the performance of a three-phase slurry bubble-column reactor for Fischer-Tropsch synthesis is investigated. The learning set needed to generate the NNM is obtained from a cell-type model where the number of cells relates to the degree of backmixing. To develop the neural network and to perform the required learning, model-predicted output responses are generated from the cell model by using all possible combinations of six key input parameters. The axial variation of the output responses is represented by a recurrent NNM. The NNM parameters are then identified using a special-purpose package that implements both training and analysis. To simulate the behaviour of an actual reactor, data used for training are corrupted with random noise. The NNM obtained from noisy data exhibits substantial filtering capability.

UR - http://www.scopus.com/inward/record.url?scp=0029137464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029137464&partnerID=8YFLogxK

M3 - Article

VL - 73

SP - 690

EP - 696

JO - Chemical Engineering Research and Design

JF - Chemical Engineering Research and Design

SN - 0263-8762

IS - A6

ER -