Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer
Membrane desalination (MD) is an efficient process for desalinating saltwater, combining the uniqueness of both thermal and separation distillation configurations. In this context, the optimization strategies and sizing methodologies are developed from the balance of the system’s energy demand. Ther...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-01-01
|
Series: | Alexandria Engineering Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016823011067 |
_version_ | 1797347804594569216 |
---|---|
author | Mohamed Abd Elaziz Mohamed E. Zayed H. Abdelfattah Ahmad O. Aseeri Elsayed M. Tag-eldin Manabu Fujii Ammar H. Elsheikh |
author_facet | Mohamed Abd Elaziz Mohamed E. Zayed H. Abdelfattah Ahmad O. Aseeri Elsayed M. Tag-eldin Manabu Fujii Ammar H. Elsheikh |
author_sort | Mohamed Abd Elaziz |
collection | DOAJ |
description | Membrane desalination (MD) is an efficient process for desalinating saltwater, combining the uniqueness of both thermal and separation distillation configurations. In this context, the optimization strategies and sizing methodologies are developed from the balance of the system’s energy demand. Therefore, robust prediction modeling of the thermodynamic behavior and freshwater production is crucial for the optimal design of MD systems. This study presents a new advanced machine-learning model to obtain the permeate flux of a tubular direct contact membrane distillation unit. The model was established by optimizing a long-short-term memory (LSTM) model by an election-based optimization algorithm (EBOA). The model inputs were the temperatures of permeate and the feed flow, and the rate and salinity of the feed flow. The optimized model was compared with other optimized LSTM models by sine–cosine optimization algorithm (SCA), artificial ecosystem optimizer (AEO), and grey wolf optimization algorithm (GWO). All models were trained, tested, and evaluated using different accuracy measures. LSTM-EBOA outperformed other models in predicting the permeate flux based on different accuracy measures. LSTM-EBOA had the highest coefficient of determination of 0.998 and 0.988 and the lowest root mean square error of 1.272 and 4.180 for training and test, respectively. It can be recommended that this paper provide a useful pathway for sizing parameters selection and predicting the performance of MD systems that makes an optimally designed model for predicting the freshwater production rates without costly experiments. |
first_indexed | 2024-03-08T11:54:11Z |
format | Article |
id | doaj.art-34e4687bde4341d7b195e0a379d5a606 |
institution | Directory Open Access Journal |
issn | 1110-0168 |
language | English |
last_indexed | 2024-03-08T11:54:11Z |
publishDate | 2024-01-01 |
publisher | Elsevier |
record_format | Article |
series | Alexandria Engineering Journal |
spelling | doaj.art-34e4687bde4341d7b195e0a379d5a6062024-01-24T05:17:29ZengElsevierAlexandria Engineering Journal1110-01682024-01-0186690703Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizerMohamed Abd Elaziz0Mohamed E. Zayed1H. Abdelfattah2Ahmad O. Aseeri3Elsayed M. Tag-eldin4Manabu Fujii5Ammar H. Elsheikh6Department of Mathematics, Faculty of Science, Zagazig University, Zagazig, 44519, Egypt; College of Information Technology, United Arab Emirates University, P.O. Box: 15551, Al Ain, United Arab Emirates; Department of Electrical and Computer Engineering, Lebanese American University, Byblos 13-5053, Lebanon; Corresponding author at: Department of Mathematics, Faculty of Science, Zagazig University, Zagazig, 44519, Egypt.Faculty of Engineering, Tanta University, Tanta 31521, Egypt; Interdisciplinary Research Center for Renewable Energy and Power Systems, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaDepartment of Electrical, Faculty of Technology and Education, Suez University, P.O.Box: 43221, Suez, EgyptDepartment of Computer Science, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj 11942, Saudi ArabiaFaculty of Engineering and Technology, Future University in Egypt, New Cairo 11835, EgyptTokyo Institute of Technology, 2-12-1-M1-4, Ookayama, Meguro-ku, Tokyo 152-8552, JapanFaculty of Engineering, Tanta University, Tanta 31521, Egypt; Tokyo Institute of Technology, 2-12-1-M1-4, Ookayama, Meguro-ku, Tokyo 152-8552, Japan; Department of Industrial and Mechanical Engineering, Lebanese American University, Byblos, Lebanon; Corresponding author at: Faculty of Engineering, Tanta University, Tanta 31521, Egypt.Membrane desalination (MD) is an efficient process for desalinating saltwater, combining the uniqueness of both thermal and separation distillation configurations. In this context, the optimization strategies and sizing methodologies are developed from the balance of the system’s energy demand. Therefore, robust prediction modeling of the thermodynamic behavior and freshwater production is crucial for the optimal design of MD systems. This study presents a new advanced machine-learning model to obtain the permeate flux of a tubular direct contact membrane distillation unit. The model was established by optimizing a long-short-term memory (LSTM) model by an election-based optimization algorithm (EBOA). The model inputs were the temperatures of permeate and the feed flow, and the rate and salinity of the feed flow. The optimized model was compared with other optimized LSTM models by sine–cosine optimization algorithm (SCA), artificial ecosystem optimizer (AEO), and grey wolf optimization algorithm (GWO). All models were trained, tested, and evaluated using different accuracy measures. LSTM-EBOA outperformed other models in predicting the permeate flux based on different accuracy measures. LSTM-EBOA had the highest coefficient of determination of 0.998 and 0.988 and the lowest root mean square error of 1.272 and 4.180 for training and test, respectively. It can be recommended that this paper provide a useful pathway for sizing parameters selection and predicting the performance of MD systems that makes an optimally designed model for predicting the freshwater production rates without costly experiments.http://www.sciencedirect.com/science/article/pii/S1110016823011067Machine learning-aided modelingDirect contact membrane distillationLong-short term memoryElection-based optimization algorithmFreshwater production prediction |
spellingShingle | Mohamed Abd Elaziz Mohamed E. Zayed H. Abdelfattah Ahmad O. Aseeri Elsayed M. Tag-eldin Manabu Fujii Ammar H. Elsheikh Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer Alexandria Engineering Journal Machine learning-aided modeling Direct contact membrane distillation Long-short term memory Election-based optimization algorithm Freshwater production prediction |
title | Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer |
title_full | Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer |
title_fullStr | Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer |
title_full_unstemmed | Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer |
title_short | Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer |
title_sort | machine learning aided modeling for predicting freshwater production of a membrane desalination system a long short term memory coupled with election based optimizer |
topic | Machine learning-aided modeling Direct contact membrane distillation Long-short term memory Election-based optimization algorithm Freshwater production prediction |
url | http://www.sciencedirect.com/science/article/pii/S1110016823011067 |
work_keys_str_mv | AT mohamedabdelaziz machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT mohamedezayed machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT habdelfattah machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT ahmadoaseeri machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT elsayedmtageldin machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT manabufujii machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer AT ammarhelsheikh machinelearningaidedmodelingforpredictingfreshwaterproductionofamembranedesalinationsystemalongshorttermmemorycoupledwithelectionbasedoptimizer |