Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant

This study focuses on enhancing heat and mass transfer in an electronic cooling system such as a rectangular cavity that contains equidistant heated chips along the bottom wall. The cavity of the present study is filled with ethylene glycol (30:70) based hybrid nano coolants of different volume frac...

Full description

Saved in:
Bibliographic Details
Main Authors: Tawsif Mahmud, Jiaul Haque Saboj, Preetom Nag, Goutam Saha, Bijan K. Saha
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:International Journal of Thermofluids
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266620272400363X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109130974429184
author Tawsif Mahmud
Jiaul Haque Saboj
Preetom Nag
Goutam Saha
Bijan K. Saha
author_facet Tawsif Mahmud
Jiaul Haque Saboj
Preetom Nag
Goutam Saha
Bijan K. Saha
author_sort Tawsif Mahmud
collection DOAJ
description This study focuses on enhancing heat and mass transfer in an electronic cooling system such as a rectangular cavity that contains equidistant heated chips along the bottom wall. The cavity of the present study is filled with ethylene glycol (30:70) based hybrid nano coolants of different volume fractions (ϕ) of Multi-walled Carbon Nanotube (MWCNT), Aluminum Oxide (Al2O3), and Copper Oxide (CuO). The set of equations controlling the thermo-solutal natural convection within the enclosure is simulated using the Galerkin weighted residual finite element method (FEM). The study has shown a good agreement of numerical results with different experimental reports within the framework of the present study. A solution space is constructed based on governing parameters such as Rayleigh number, buoyancy ratio, and Lewis number. A hybrid nano-coolant containing ϕMWCNT = 1.5 %, ϕCuO = 0.5 %, and ϕAl2O3 = 2 % showed a 3.11% improvement in heat transfer rate compared to the base fluid, highlighting its potential for thermal management applications. This study also investigates various machine learning models for predicting the heat and mass transfer rate, and an error analysis is conducted on the K-Nearest Neighbour Regressor, Random Forest Regressor, Decision Tree Regressor, and ANN model. The ANN model with 6-50-100-50-2 architecture showcases the best fit with the mean squared error of 0.8923 and an R² value of 99.96 % on testing data. The ANN model exhibits its capability to predict heat transfer and mass transfer rates within the error ranges from 1–2 % and 2–3 %, respectively, even at a strong thermal buoyancy force (Ra = 10⁵). This accuracy showcases a novel use of ANN to efficiently predict thermo-fluidic transport behaviors of hybrid nanofluids, offering a faster alternative to resource-intensive simulations. The present study opens new possibilities for real-time, cost-effective cooling solutions, particularly in microelectronics and renewable energy, while maintaining high prediction accuracy by integrating machine learning with the nanotechnology approach.
format Article
id doaj-art-1e8ac9aad27c496e907ae90eca8fb165
institution OA Journals
issn 2666-2027
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series International Journal of Thermofluids
spelling doaj-art-1e8ac9aad27c496e907ae90eca8fb1652025-08-20T02:38:10ZengElsevierInternational Journal of Thermofluids2666-20272024-11-012410092310.1016/j.ijft.2024.100923Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolantTawsif Mahmud0Jiaul Haque Saboj1Preetom Nag2Goutam Saha3Bijan K. Saha4Department of Mathematics & Physics, North South University (NSU), Dhaka, 1229, Bangladesh; Center of Applied & Computational Sciences (CACS), NSU, Dhaka, 1229, BangladeshDepartment of Mathematics & Physics, North South University (NSU), Dhaka, 1229, Bangladesh; Center of Applied & Computational Sciences (CACS), NSU, Dhaka, 1229, BangladeshDepartment of Mathematics & Physics, North South University (NSU), Dhaka, 1229, Bangladesh; Center of Applied & Computational Sciences (CACS), NSU, Dhaka, 1229, Bangladesh; Corresponding author at: Department of Mathematics & Physics, North South University (NSU), Dhaka, 1229, Bangladesh.Department of Mathematics, University of Dhaka, Dhaka, 1000, BangladeshDepartment of Mathematics, University of Barishal, Barishal, 8254, BangladeshThis study focuses on enhancing heat and mass transfer in an electronic cooling system such as a rectangular cavity that contains equidistant heated chips along the bottom wall. The cavity of the present study is filled with ethylene glycol (30:70) based hybrid nano coolants of different volume fractions (ϕ) of Multi-walled Carbon Nanotube (MWCNT), Aluminum Oxide (Al2O3), and Copper Oxide (CuO). The set of equations controlling the thermo-solutal natural convection within the enclosure is simulated using the Galerkin weighted residual finite element method (FEM). The study has shown a good agreement of numerical results with different experimental reports within the framework of the present study. A solution space is constructed based on governing parameters such as Rayleigh number, buoyancy ratio, and Lewis number. A hybrid nano-coolant containing ϕMWCNT = 1.5 %, ϕCuO = 0.5 %, and ϕAl2O3 = 2 % showed a 3.11% improvement in heat transfer rate compared to the base fluid, highlighting its potential for thermal management applications. This study also investigates various machine learning models for predicting the heat and mass transfer rate, and an error analysis is conducted on the K-Nearest Neighbour Regressor, Random Forest Regressor, Decision Tree Regressor, and ANN model. The ANN model with 6-50-100-50-2 architecture showcases the best fit with the mean squared error of 0.8923 and an R² value of 99.96 % on testing data. The ANN model exhibits its capability to predict heat transfer and mass transfer rates within the error ranges from 1–2 % and 2–3 %, respectively, even at a strong thermal buoyancy force (Ra = 10⁵). This accuracy showcases a novel use of ANN to efficiently predict thermo-fluidic transport behaviors of hybrid nanofluids, offering a faster alternative to resource-intensive simulations. The present study opens new possibilities for real-time, cost-effective cooling solutions, particularly in microelectronics and renewable energy, while maintaining high prediction accuracy by integrating machine learning with the nanotechnology approach.http://www.sciencedirect.com/science/article/pii/S266620272400363XHeated chipsThermo-solutal convectionArtificial neural network (ANN)Hybrid nano-coolantRegressor model
spellingShingle Tawsif Mahmud
Jiaul Haque Saboj
Preetom Nag
Goutam Saha
Bijan K. Saha
Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
International Journal of Thermofluids
Heated chips
Thermo-solutal convection
Artificial neural network (ANN)
Hybrid nano-coolant
Regressor model
title Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
title_full Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
title_fullStr Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
title_full_unstemmed Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
title_short Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
title_sort artificial neural network ann approach in predicting the thermo solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant
topic Heated chips
Thermo-solutal convection
Artificial neural network (ANN)
Hybrid nano-coolant
Regressor model
url http://www.sciencedirect.com/science/article/pii/S266620272400363X
work_keys_str_mv AT tawsifmahmud artificialneuralnetworkannapproachinpredictingthethermosolutaltransportratefrommultipleheatedchipswithinanenclosurefilledwithhybridnanocoolant
AT jiaulhaquesaboj artificialneuralnetworkannapproachinpredictingthethermosolutaltransportratefrommultipleheatedchipswithinanenclosurefilledwithhybridnanocoolant
AT preetomnag artificialneuralnetworkannapproachinpredictingthethermosolutaltransportratefrommultipleheatedchipswithinanenclosurefilledwithhybridnanocoolant
AT goutamsaha artificialneuralnetworkannapproachinpredictingthethermosolutaltransportratefrommultipleheatedchipswithinanenclosurefilledwithhybridnanocoolant
AT bijanksaha artificialneuralnetworkannapproachinpredictingthethermosolutaltransportratefrommultipleheatedchipswithinanenclosurefilledwithhybridnanocoolant