Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy

<p></p><div> <p>Artificial neural networks (ANNs) can understand the behavior of a given system from the historical measurements of its associated variables. Adjusting the weight and bias of the ANN model using an optimization algorithm is known as the training process. The A...

Full description

Saved in:
Bibliographic Details
Main Author: Haitao Xu (435549) (author)
Other Authors: Xiangwei Wu (173784) (author), Amith Khandakar (14151981) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513565312942080
author Haitao Xu (435549)
author2 Xiangwei Wu (173784)
Amith Khandakar (14151981)
author2_role author
author
author_facet Haitao Xu (435549)
Xiangwei Wu (173784)
Amith Khandakar (14151981)
author_role author
dc.creator.none.fl_str_mv Haitao Xu (435549)
Xiangwei Wu (173784)
Amith Khandakar (14151981)
dc.date.none.fl_str_mv 2023-03-16T06:22:44Z
dc.identifier.none.fl_str_mv 10.1002/ese3.1156
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Estimation_of_the_methanol_loss_in_the_gas_hydrate_prevention_unit_using_the_artificial_neural_networks_Investigating_the_effect_of_training_algorithm_on_the_model_accuracy/22258087
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Environmental engineering
General Energy
Safety, Risk, Reliability and Quality
dc.title.none.fl_str_mv Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p></p><div> <p>Artificial neural networks (ANNs) can understand the behavior of a given system from the historical measurements of its associated variables. Adjusting the weight and bias of the ANN model using an optimization algorithm is known as the training process. The ANN reliability is directly related to the success of the training process. Therefore, this study investigates the effect of optimization algorithms on the prediction accuracy of the multilayer perceptron neural networks (MLPNNs). The complex gas hydrate prevention unit is simulated using the MLPNN model trained by 20 different optimization algorithms. This study investigates the gradient-based, evolutionary, and Bayesian-based optimization algorithms. Combining statistical and ranking analyses confirms that the Levenberg–Marquardt (LM) is the most efficient optimization technique for training the MLPNN model. This training algorithm adjusts the weight and bis parameters of the MLPNN so that the highest accurate predictions have been achieved. On the other hand, the trained MLPNN by imperialist competitive algorithm shows the lowest accuracy for the considered task. The trained MLPNN by the LM algorithm predicts 239 laboratory-measured data sets about the methanol (MeOH) loss with the absolute average relative deviation of 6.4% and regression coefficient of 0.9643. Coupling the developed MLPNN and differential evolution optimization algorithm shows that temperature = 263 K and pressure = 6.92 MPa are the optimum condition for minimizing the MeOH loss in the gas hydrate prevention unit. Economic analysis confirms that the annual cost of methanol loss for the daily processing of 100 × 10<sup>6 </sup>m<sup>3</sup> of gas is ~17 million US dollars.</p></div><p></p><h2>Other Information</h2> <p> Published in: Energy Science & Engineering<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1002/ese3.1156" target="_blank">http://dx.doi.org/10.1002/ese3.1156</a></p>
eu_rights_str_mv openAccess
id Manara2_571254f02363beea3f8f5d682fb90d43
identifier_str_mv 10.1002/ese3.1156
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/22258087
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracyHaitao Xu (435549)Xiangwei Wu (173784)Amith Khandakar (14151981)EngineeringEnvironmental engineeringGeneral EnergySafety, Risk, Reliability and Quality<p></p><div> <p>Artificial neural networks (ANNs) can understand the behavior of a given system from the historical measurements of its associated variables. Adjusting the weight and bias of the ANN model using an optimization algorithm is known as the training process. The ANN reliability is directly related to the success of the training process. Therefore, this study investigates the effect of optimization algorithms on the prediction accuracy of the multilayer perceptron neural networks (MLPNNs). The complex gas hydrate prevention unit is simulated using the MLPNN model trained by 20 different optimization algorithms. This study investigates the gradient-based, evolutionary, and Bayesian-based optimization algorithms. Combining statistical and ranking analyses confirms that the Levenberg–Marquardt (LM) is the most efficient optimization technique for training the MLPNN model. This training algorithm adjusts the weight and bis parameters of the MLPNN so that the highest accurate predictions have been achieved. On the other hand, the trained MLPNN by imperialist competitive algorithm shows the lowest accuracy for the considered task. The trained MLPNN by the LM algorithm predicts 239 laboratory-measured data sets about the methanol (MeOH) loss with the absolute average relative deviation of 6.4% and regression coefficient of 0.9643. Coupling the developed MLPNN and differential evolution optimization algorithm shows that temperature = 263 K and pressure = 6.92 MPa are the optimum condition for minimizing the MeOH loss in the gas hydrate prevention unit. Economic analysis confirms that the annual cost of methanol loss for the daily processing of 100 × 10<sup>6 </sup>m<sup>3</sup> of gas is ~17 million US dollars.</p></div><p></p><h2>Other Information</h2> <p> Published in: Energy Science & Engineering<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1002/ese3.1156" target="_blank">http://dx.doi.org/10.1002/ese3.1156</a></p>2023-03-16T06:22:44ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1002/ese3.1156https://figshare.com/articles/journal_contribution/Estimation_of_the_methanol_loss_in_the_gas_hydrate_prevention_unit_using_the_artificial_neural_networks_Investigating_the_effect_of_training_algorithm_on_the_model_accuracy/22258087CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/222580872023-03-16T06:22:44Z
spellingShingle Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
Haitao Xu (435549)
Engineering
Environmental engineering
General Energy
Safety, Risk, Reliability and Quality
status_str publishedVersion
title Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
title_full Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
title_fullStr Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
title_full_unstemmed Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
title_short Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
title_sort Estimation of the methanol loss in the gas hydrate prevention unit using the artificial neural networks: Investigating the effect of training algorithm on the model accuracy
topic Engineering
Environmental engineering
General Energy
Safety, Risk, Reliability and Quality