Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks

Accurately predicting thermo-physical properties (TPPs) of MXene/graphene-based nanofluids is crucial for photovoltaic/thermal solar systems, driving focused research on developing precise TPP predictive models. This study presents optimized multi-layer perceptron neural network (MLPNN) models, leve...

Full description

Saved in:
Bibliographic Details
Main Authors: Dheyaa J. jasim, Husam Rajab, As'ad Alizadeh, Kamal Sharma, Mohsen Ahmed, Murizah Kassim, S. AbdulAmeer, Adil A. Alwan, Soheil Salahshour, Hamid Maleki
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024011137
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846115899062353920
author Dheyaa J. jasim
Husam Rajab
As'ad Alizadeh
Kamal Sharma
Mohsen Ahmed
Murizah Kassim
S. AbdulAmeer
Adil A. Alwan
Soheil Salahshour
Hamid Maleki
author_facet Dheyaa J. jasim
Husam Rajab
As'ad Alizadeh
Kamal Sharma
Mohsen Ahmed
Murizah Kassim
S. AbdulAmeer
Adil A. Alwan
Soheil Salahshour
Hamid Maleki
author_sort Dheyaa J. jasim
collection DOAJ
description Accurately predicting thermo-physical properties (TPPs) of MXene/graphene-based nanofluids is crucial for photovoltaic/thermal solar systems, driving focused research on developing precise TPP predictive models. This study presents optimized multi-layer perceptron neural network (MLPNN) models, leveraging Bayesian optimization to refine architectural and training hyperparameters, including hidden layers, neurons, activation functions, standardization, and regularization terms. A comparative analysis of Bayesian acquisition functions—the probability of improvement (POI), lower confidence bound (LCB), expected improvement (EI), expected improvement plus (EIP), expected improvement per second plus (EIPSP), and expected improvement per second (EIPS)—demonstrated that the POI-MLPNN achieves the most accurate results, as evidenced by the lowest MAPE of 1.0923 % and exceptional consistency with an R-value of 0.99811. The EI-MLPNN and EIP-MLPNN models recorded the same outputs. The EI/EIP-MLPNN (R = 0.99668) model excels in consistency over LCB-MLPNN (R = 0.99529) and EIPSP-MLPNN (R = 0.99667). The optimized models offer a reliable, cost-efficient alternate for experimental and computational TPP analyses. Leveraging insights from these models enables better control over nanofluid TPPs in solar systems, enhancing energy conversion efficiency.
format Article
id doaj-art-a18984dd6a1a49d98b1cc15c1670db42
institution Kabale University
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-a18984dd6a1a49d98b1cc15c1670db422024-12-19T10:57:07ZengElsevierResults in Engineering2590-12302024-12-0124102858Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networksDheyaa J. jasim0Husam Rajab1As'ad Alizadeh2Kamal Sharma3Mohsen Ahmed4Murizah Kassim5S. AbdulAmeer6Adil A. Alwan7Soheil Salahshour8Hamid Maleki9Department of Petroleum Engineering, Al-Amarah University College, Maysan, IraqCollege of Engineering, Mechanical Engineering Department, Alasala University, King Fahad Bin Abdulaziz Rd., P.O.Box: 12666, Amanah, 31483, Dammam, Kingdom of Saudi ArabiaDepartment of Civil Engineering, College of Engineering, Cihan University-Erbil, Erbil, IraqInstitute of Engineering and Technology, GLA University, Mathura, U.P. 281406, IndiaImam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Eastern Province, Kingdom of Saudi ArabiaInstitute for Big Data Analytics and Artificial Intelligence (IBDAAI), Universiti Teknologi MARA, 40450, Shah Alam, Selangor, Malaysia; School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA, 40450, Shah Alam, Selangor, MalaysiaDepartment of Automobile Engineering, College of Engineering, Al-Musayab, University of Babylon, Iraq; Ahl Al Bayt University, Kerbala, IraqCollege of Technical Engineering, National University of Science and Technology, Dhi Qar, 64001, IraqFaculty of Engineering and Natural Sciences, Istanbul Okan University, Istanbul, Turkey; Faculty of Engineering and Natural Sciences, Bahcesehir University, Istanbul, Turkey; Department of Computer Science and Mathematics, Lebanese American University, Beirut, LebanonRenewable Energy Research Group, Isfahan, Iran; Corresponding author.Accurately predicting thermo-physical properties (TPPs) of MXene/graphene-based nanofluids is crucial for photovoltaic/thermal solar systems, driving focused research on developing precise TPP predictive models. This study presents optimized multi-layer perceptron neural network (MLPNN) models, leveraging Bayesian optimization to refine architectural and training hyperparameters, including hidden layers, neurons, activation functions, standardization, and regularization terms. A comparative analysis of Bayesian acquisition functions—the probability of improvement (POI), lower confidence bound (LCB), expected improvement (EI), expected improvement plus (EIP), expected improvement per second plus (EIPSP), and expected improvement per second (EIPS)—demonstrated that the POI-MLPNN achieves the most accurate results, as evidenced by the lowest MAPE of 1.0923 % and exceptional consistency with an R-value of 0.99811. The EI-MLPNN and EIP-MLPNN models recorded the same outputs. The EI/EIP-MLPNN (R = 0.99668) model excels in consistency over LCB-MLPNN (R = 0.99529) and EIPSP-MLPNN (R = 0.99667). The optimized models offer a reliable, cost-efficient alternate for experimental and computational TPP analyses. Leveraging insights from these models enables better control over nanofluid TPPs in solar systems, enhancing energy conversion efficiency.http://www.sciencedirect.com/science/article/pii/S2590123024011137Solar energy conversionPVT solar panelsArtificial neural networkMachine learningMXeneGraphene
spellingShingle Dheyaa J. jasim
Husam Rajab
As'ad Alizadeh
Kamal Sharma
Mohsen Ahmed
Murizah Kassim
S. AbdulAmeer
Adil A. Alwan
Soheil Salahshour
Hamid Maleki
Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
Results in Engineering
Solar energy conversion
PVT solar panels
Artificial neural network
Machine learning
MXene
Graphene
title Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
title_full Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
title_fullStr Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
title_full_unstemmed Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
title_short Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks
title_sort enhancing solar energy conversion efficiency thermophysical property predicting of mxene graphene hybrid nanofluids via bayesian optimized artificial neural networks
topic Solar energy conversion
PVT solar panels
Artificial neural network
Machine learning
MXene
Graphene
url http://www.sciencedirect.com/science/article/pii/S2590123024011137
work_keys_str_mv AT dheyaajjasim enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT husamrajab enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT asadalizadeh enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT kamalsharma enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT mohsenahmed enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT murizahkassim enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT sabdulameer enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT adilaalwan enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT soheilsalahshour enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks
AT hamidmaleki enhancingsolarenergyconversionefficiencythermophysicalpropertypredictingofmxenegraphenehybridnanofluidsviabayesianoptimizedartificialneuralnetworks