Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact
This paper examines the mixed convective heat transfer (HTR) of nanofluid (NFD) flow in a rectangular enclosure with the upper moving wall numerically. The lower wall has a high temperature and a number of semi-circular obstacles with the same temperature are installed on it. The upper moving wall h...
Published in: | Engineering Analysis with Boundary Elements |
---|---|
Main Author: | |
Format: | Retracted |
Language: | English |
Published: |
Elsevier Ltd
2023
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140908788&doi=10.1016%2fj.enganabound.2022.09.023&partnerID=40&md5=80bde90a16a2aa4bfe9b1168e9dab5e0 |
id |
2-s2.0-85140908788 |
---|---|
spelling |
2-s2.0-85140908788 Hai T.; Dhahad H.A.; Ali M.A.; Goyal V.; Almojil S.F.; Almohana A.I.; Alali A.F.; Almoalimi K.T.; Qasim Ahmed Alyousuf F. Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact 2023 Engineering Analysis with Boundary Elements 146 10.1016/j.enganabound.2022.09.023 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140908788&doi=10.1016%2fj.enganabound.2022.09.023&partnerID=40&md5=80bde90a16a2aa4bfe9b1168e9dab5e0 This paper examines the mixed convective heat transfer (HTR) of nanofluid (NFD) flow in a rectangular enclosure with the upper moving wall numerically. The lower wall has a high temperature and a number of semi-circular obstacles with the same temperature are installed on it. The upper moving wall has a low temperature and the other two walls are insulated. The enclosure can change from horizontal to vertical. Radiation HTR is considered in the enclosure and there is a magnetic field (MGF) that can change the angle from horizontal to vertical affecting the NFD. This study is carried out for different angles of the enclosure and MGF from horizontal to vertical for radiation parameters (RDP) of 0 to 3 and a constant MGF with Hartmann number of 20 and Richardson number of 10. The aim is to estimate the Nusselt number (Nu), entropy generation (ETG), and Bejan number (Be). The SIMPLE algorithm is utilized using FORTRAN software, and optimization is done using artificial intelligence to find the maximum and minimum output values. The results demonstrate that the maximum value of Nu and Bes corresponds to the MGF angle and enclosure angle of 90°. The minimum value of the Nu and the maximum amount of ETG corresponds to the horizontal MGF and horizontal enclosure when the RDP is 1.5. An increment in the RDP enhances the amount of Nu. The maximum amount of ETG, i.e. 12.87, corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. It was also found that most environmental impacts, and hence values for different environmental factors, arise from the production of nanoparticles; thus, it is a significant contributor to environmental impacts. © 2022 Elsevier Ltd Elsevier Ltd 9557997 English Retracted |
author |
Hai T.; Dhahad H.A.; Ali M.A.; Goyal V.; Almojil S.F.; Almohana A.I.; Alali A.F.; Almoalimi K.T.; Qasim Ahmed Alyousuf F. |
spellingShingle |
Hai T.; Dhahad H.A.; Ali M.A.; Goyal V.; Almojil S.F.; Almohana A.I.; Alali A.F.; Almoalimi K.T.; Qasim Ahmed Alyousuf F. Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
author_facet |
Hai T.; Dhahad H.A.; Ali M.A.; Goyal V.; Almojil S.F.; Almohana A.I.; Alali A.F.; Almoalimi K.T.; Qasim Ahmed Alyousuf F. |
author_sort |
Hai T.; Dhahad H.A.; Ali M.A.; Goyal V.; Almojil S.F.; Almohana A.I.; Alali A.F.; Almoalimi K.T.; Qasim Ahmed Alyousuf F. |
title |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
title_short |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
title_full |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
title_fullStr |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
title_full_unstemmed |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
title_sort |
Utilization of machine learning and neural networks to optimize the enclosure angle, magnetic field, and radiation parameter for mixed convection of hybrid nanofluid flow next to assess environmental impact |
publishDate |
2023 |
container_title |
Engineering Analysis with Boundary Elements |
container_volume |
146 |
container_issue |
|
doi_str_mv |
10.1016/j.enganabound.2022.09.023 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140908788&doi=10.1016%2fj.enganabound.2022.09.023&partnerID=40&md5=80bde90a16a2aa4bfe9b1168e9dab5e0 |
description |
This paper examines the mixed convective heat transfer (HTR) of nanofluid (NFD) flow in a rectangular enclosure with the upper moving wall numerically. The lower wall has a high temperature and a number of semi-circular obstacles with the same temperature are installed on it. The upper moving wall has a low temperature and the other two walls are insulated. The enclosure can change from horizontal to vertical. Radiation HTR is considered in the enclosure and there is a magnetic field (MGF) that can change the angle from horizontal to vertical affecting the NFD. This study is carried out for different angles of the enclosure and MGF from horizontal to vertical for radiation parameters (RDP) of 0 to 3 and a constant MGF with Hartmann number of 20 and Richardson number of 10. The aim is to estimate the Nusselt number (Nu), entropy generation (ETG), and Bejan number (Be). The SIMPLE algorithm is utilized using FORTRAN software, and optimization is done using artificial intelligence to find the maximum and minimum output values. The results demonstrate that the maximum value of Nu and Bes corresponds to the MGF angle and enclosure angle of 90°. The minimum value of the Nu and the maximum amount of ETG corresponds to the horizontal MGF and horizontal enclosure when the RDP is 1.5. An increment in the RDP enhances the amount of Nu. The maximum amount of ETG, i.e. 12.87, corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. corresponds to the enclosure with an angle of 45° for the horizontal MGF and the absence of RDP. It was also found that most environmental impacts, and hence values for different environmental factors, arise from the production of nanoparticles; thus, it is a significant contributor to environmental impacts. © 2022 Elsevier Ltd |
publisher |
Elsevier Ltd |
issn |
9557997 |
language |
English |
format |
Retracted |
accesstype |
|
record_format |
scopus |
collection |
Scopus |
_version_ |
1809677779831095296 |