Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit

<div><p>Data-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input–output data obtained from a process simulat...

Full description

Saved in:
Bibliographic Details
Main Author: Mohamed Ibrahim (3465677) (author)
Other Authors: Saad Al-Sobhi (18153811) (author), Rajib Mukherjee (532424) (author), Ahmed AlNouss (9872265) (author)
Published: 2019
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513520357343232
author Mohamed Ibrahim (3465677)
author2 Saad Al-Sobhi (18153811)
Rajib Mukherjee (532424)
Ahmed AlNouss (9872265)
author2_role author
author
author
author_facet Mohamed Ibrahim (3465677)
Saad Al-Sobhi (18153811)
Rajib Mukherjee (532424)
Ahmed AlNouss (9872265)
author_role author
dc.creator.none.fl_str_mv Mohamed Ibrahim (3465677)
Saad Al-Sobhi (18153811)
Rajib Mukherjee (532424)
Ahmed AlNouss (9872265)
dc.date.none.fl_str_mv 2019-05-18T03:00:00Z
dc.identifier.none.fl_str_mv 10.3390/en12101906
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Impact_of_Sampling_Technique_on_the_Performance_of_Surrogate_Models_Generated_with_Artificial_Neural_Network_ANN_A_Case_Study_for_a_Natural_Gas_Stabilization_Unit/25406680
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Control engineering, mechatronics and robotics
Electrical engineering
Electronics, sensors and digital hardware
Environmental engineering
surrogate model
sampling technique
stabilization unit
process simulation
process systems engineering (PSE)
dc.title.none.fl_str_mv Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <div><p>Data-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input–output data obtained from a process simulator. To enhance the model robustness, proper sampling techniques are required to cover the entire domain of the process variables uniformly. In the present work, Monte Carlo with pseudo-random samples as well as Latin hypercube samples and quasi-Monte Carlo samples with Hammersley Sequence Sampling (HSS) are generated. The sampled data obtained from the process simulator are fitted to neural networks for generating a surrogate model. An illustrative case study is solved to predict the gas stabilization unit performance. From the developed surrogate models to predict process data, it can be concluded that of the different sampling methods, Latin hypercube sampling and HSS have better performance than the pseudo-random sampling method for designing the surrogate model. This argument is based on the maximum absolute value, standard deviation, and the confidence interval for the relative average error as obtained from different sampling techniques.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Energies<br> License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/en12101906" target="_blank">https://dx.doi.org/10.3390/en12101906</a></p>
eu_rights_str_mv openAccess
id Manara2_fc173398cec4798603c30b57f8b27a37
identifier_str_mv 10.3390/en12101906
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25406680
publishDate 2019
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization UnitMohamed Ibrahim (3465677)Saad Al-Sobhi (18153811)Rajib Mukherjee (532424)Ahmed AlNouss (9872265)EngineeringControl engineering, mechatronics and roboticsElectrical engineeringElectronics, sensors and digital hardwareEnvironmental engineeringsurrogate modelsampling techniquestabilization unitprocess simulationprocess systems engineering (PSE)<div><p>Data-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input–output data obtained from a process simulator. To enhance the model robustness, proper sampling techniques are required to cover the entire domain of the process variables uniformly. In the present work, Monte Carlo with pseudo-random samples as well as Latin hypercube samples and quasi-Monte Carlo samples with Hammersley Sequence Sampling (HSS) are generated. The sampled data obtained from the process simulator are fitted to neural networks for generating a surrogate model. An illustrative case study is solved to predict the gas stabilization unit performance. From the developed surrogate models to predict process data, it can be concluded that of the different sampling methods, Latin hypercube sampling and HSS have better performance than the pseudo-random sampling method for designing the surrogate model. This argument is based on the maximum absolute value, standard deviation, and the confidence interval for the relative average error as obtained from different sampling techniques.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Energies<br> License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/en12101906" target="_blank">https://dx.doi.org/10.3390/en12101906</a></p>2019-05-18T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.3390/en12101906https://figshare.com/articles/journal_contribution/Impact_of_Sampling_Technique_on_the_Performance_of_Surrogate_Models_Generated_with_Artificial_Neural_Network_ANN_A_Case_Study_for_a_Natural_Gas_Stabilization_Unit/25406680CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/254066802019-05-18T03:00:00Z
spellingShingle Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
Mohamed Ibrahim (3465677)
Engineering
Control engineering, mechatronics and robotics
Electrical engineering
Electronics, sensors and digital hardware
Environmental engineering
surrogate model
sampling technique
stabilization unit
process simulation
process systems engineering (PSE)
status_str publishedVersion
title Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
title_full Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
title_fullStr Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
title_full_unstemmed Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
title_short Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
title_sort Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
topic Engineering
Control engineering, mechatronics and robotics
Electrical engineering
Electronics, sensors and digital hardware
Environmental engineering
surrogate model
sampling technique
stabilization unit
process simulation
process systems engineering (PSE)