Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks

Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks

ABSTRACT: An artificial neural network (ANN) was built using selected input data of Newtonian fluids in pilot scale external loop airlift reactors of varying designs, in order to predict the mass transfer coefficient in other external loop airlift reactors with more general geometry. 663 data points...

Full description

Bibliographic Details
Main Authors: N. Naidoo, W.J. Pauck, M. Carsky
Format: Article
Language:English
Published: Elsevier 2020-07-01
Series:South African Journal of Chemical Engineering
Subjects:
Mass transfer
Pilot scale
Airlift reactors
Neural networks
Online Access:http://www.sciencedirect.com/science/article/pii/S1026918520300160
id doaj-bb06e6cc0df945299c8caf4b082b1fa4
record_format Article
spelling doaj-bb06e6cc0df945299c8caf4b082b1fa42020-11-25T03:52:44ZengElsevierSouth African Journal of Chemical Engineering1026-91852020-07-01338389Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural NetworksN. Naidoo0W.J. Pauck1M. Carsky2Department of Chemical Engineering, Faculty of Engineering and the Built Environment, Steve Biko Campus, Durban University of Technology, Durban, South Africa; Corresponding author.Department of Chemical Engineering, Faculty of Engineering and the Built Environment, Steve Biko Campus, Durban University of Technology, Durban, South AfricaSchool of Engineering, University of KwaZulu-Natal, Durban, South AfricaABSTRACT: An artificial neural network (ANN) was built using selected input data of Newtonian fluids in pilot scale external loop airlift reactors of varying designs, in order to predict the mass transfer coefficient in other external loop airlift reactors with more general geometry. 663 data points were generated using air-glycerine and air-water systems in 5 different configurations of pilot scale external loop airlift reactors with 3 categories of sparger design. The data was modelled using the artificial neural network software, Predict (Version 3.30) by Neuralware. The correlation coefficient (R) for the neural network model was 0.98.The model was tested with unseen external data from various sources of which the R values ranged from 0.91 to 0.99. Additional external data, out of the experimental range of this investigation was evaluated, for which the R values ranged from 0.67 to 0.85. The ANN gave excellent approximations for the data within or below the training parameters.http://www.sciencedirect.com/science/article/pii/S1026918520300160Mass transferPilot scaleAirlift reactorsNeural networks
collection DOAJ
language English
format Article
sources DOAJ
author N. Naidoo
W.J. Pauck
M. Carsky
spellingShingle N. Naidoo
W.J. Pauck
M. Carsky
Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
South African Journal of Chemical Engineering
Mass transfer
Pilot scale
Airlift reactors
Neural networks
author_facet N. Naidoo
W.J. Pauck
M. Carsky
author_sort N. Naidoo
title Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
title_short Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
title_full Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
title_fullStr Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
title_full_unstemmed Predicting Mass Transfer in Pilot Scale External Loop Airlift Reactors using Neural Networks
title_sort predicting mass transfer in pilot scale external loop airlift reactors using neural networks
publisher Elsevier
series South African Journal of Chemical Engineering
issn 1026-9185
publishDate 2020-07-01
description ABSTRACT: An artificial neural network (ANN) was built using selected input data of Newtonian fluids in pilot scale external loop airlift reactors of varying designs, in order to predict the mass transfer coefficient in other external loop airlift reactors with more general geometry. 663 data points were generated using air-glycerine and air-water systems in 5 different configurations of pilot scale external loop airlift reactors with 3 categories of sparger design. The data was modelled using the artificial neural network software, Predict (Version 3.30) by Neuralware. The correlation coefficient (R) for the neural network model was 0.98.The model was tested with unseen external data from various sources of which the R values ranged from 0.91 to 0.99. Additional external data, out of the experimental range of this investigation was evaluated, for which the R values ranged from 0.67 to 0.85. The ANN gave excellent approximations for the data within or below the training parameters.
topic Mass transfer
Pilot scale
Airlift reactors
Neural networks
url http://www.sciencedirect.com/science/article/pii/S1026918520300160
work_keys_str_mv AT nnaidoo predictingmasstransferinpilotscaleexternalloopairliftreactorsusingneuralnetworks
AT wjpauck predictingmasstransferinpilotscaleexternalloopairliftreactorsusingneuralnetworks
AT mcarsky predictingmasstransferinpilotscaleexternalloopairliftreactorsusingneuralnetworks
_version_ 1724481244333342720

Similar Items