Modeling and optimization of thermal conductivity and viscosity of water-based hybrid nanofluids containing graphene oxide combined with silicon dioxide (Go-SiO2, 50:50) using MLP & GA

Sabouni, Hamid Reza; Mokhtarian, Ali; Rahimi, Mojtaba

doi:10.66224/CNJ.4.1.803

Modeling and optimization of thermal conductivity and viscosity of water-based hybrid nanofluids containing graphene oxide combined with silicon dioxide (Go-SiO2, 50:50) using MLP & GA

Document Type : Original Article

Authors

Hamid Reza Sabouni ¹

Ali Mokhtarian ¹

Mojtaba Rahimi ²

¹ Department of Mechanical Engineering, Kho.C., Islamic Azad University, Khomeinishahr, Iran

² Department of Petroleum Engineering, Kho.C., Islamic Azad University, Khomeinishahr, Iran; Stone Research Center, Kho.C., Islamic Azad University, Khomeinishahr, Iran

10.66224/CNJ.4.1.803

Abstract

In this study, architecture and training of two artificial neural networks (ANNs) were designed to predict the thermal conductivity (TC) and viscosity properties of nanofluids GO-SiO2 (50:50, Graphene Oxide and Silicon Dioxide)-based nanofluids. The nanofluid samples investigated comprised various weight fractions (0.1–1%) of a 50:50 mass-ratio mixture of graphene oxide (GO) and silicon dioxide (SiO₂) nanoparticles dispersed in the base fluid; their viscosity and thermal conductivity were measured at temperatures ranging from 30 to 60°C. For each ANN developed to predict either nanofluid viscosity or TC, the regression plots corresponding to the training, validation, and test datasets provided a clear demonstration of the network’s optimal performance. Specifically, the mean and maximum relative errors obtained for the test dataset were 0.3425% and 0.8359%, respectively, for viscosity prediction, and 0.2465% and 0.4069%, respectively, for TC prediction. Furthermore, following a sensitivity analysis of the networks, we found that the weight fraction exerts a more pronounced influence on nanofluid viscosity and TC than temperature. Subsequently, a genetic algorithm (GA) applied to the trained ANN models identified the optimal conditions as a weight fraction in the range of 0.1–1% and a temperature of 60°C.

Graphical Abstract

Keywords

Hybrid nanofluids

Weight fraction

Artificial neural network

Optimization

Genetic algorithm

[1] B. Gou, X. Song, Z. Wu, X. Chen, Effects of Silicon Dioxide/Graphene Oxide Hybrid Modification on Curing Kinetics of Epoxy Resin, ACS Omega. 7 (2022) 36551–36560, doi: https://doi.org/10.1021/acsomega.2c04505.

[2] P.K. Kanti, P. Paramasivam, V.V. Wanatasanappan, S. Dhanasekaran, P. Sharma, Experimental and explainable machine learning approach on thermal conductivity and viscosity of water based graphene oxide based mono and hybrid nanofluids, Sci. Rep. 14 (2024) 30967, doi: https://doi.org/10.1038/s41598-024-81955-1.

[3] Razzaq et al., Nanofluids for advanced applications: a comprehensive review on preparation methods, properties, and environmental impact, ACS Omega. 10 (2025) 5251–5282., doi: https://doi.org/10.1021/acsomega.4c10143.

[4] A. Shahsavar, S.A. Bagherzadeh, B. Mahmoudi, A. Hajizadeh, M. Afrand, T.K. Nguyen, Robust weighted least squares support vector regression algorithm to estimate the nanofluid thermal properties of water/graphene oxide–silicon carbide mixture, Physica A. 525 (2019) 1418–1428, doi: https://doi.org/10.1016/j.physa.2019.03.086.

[5] A.A. Mahyari, A. Karimipour, M. Afrand, Effects of dispersed added graphene oxide-silicon carbide nanoparticles to present a statistical formulation for the mixture thermal properties, Physica A. 521 (2019) 98–112, doi:

https://doi.org/10.1016/j.physa.2019.01.035.

[6] I. Kazemi, M. Sefid, M. Afrand, A novel comparative experimental study on rheological behavior of mono & hybrid nanofluids concerned graphene and silica nano-powders: Characterization, stability and viscosity measurements, Powder Technol. 366 (2020) 216–229, doi: https://doi.org/10.1016/j.powtec.2020.02.010.

[7] Q. Nguyen, R. Rizvandi, A. Karimipour, O. Malekahmadi, Q.-V. Bach, A novel correlation to calculate thermal conductivity of aqueous hybrid graphene oxide/silicon dioxide nanofluid: synthesis, characterizations, preparation, and artificial neural network modeling, Arab. J. Sci. Eng. 45 (2020) 9747–9758., doi: https://doi.org/10.1007/s13369-020-04885-w.

[8] M.N. Ahmad et al., Artificial intelligence model and correlation for characterization and viscosity measurements of mono & hybrid nanofluids concerned graphene oxide/silica, J. Therm. Anal. Calorim. 145 (2021) 2209–2224, doi: https://doi.org/10.1007/s10973-021-10687-5.

[9] M.M. Rashidi et al., Thermophysical properties of hybrid nanofluids and the proposed models: An updated comprehensive study, Nanomaterials. 11 (2021) 3084, doi: https://doi.org/10.3390/nano11113084

[10] G. Huminic, A. Vărdaru, A. Huminic, C. Fleacă, F. Dumitrache, I. Morjan, Water-based graphene oxide–silicon hybrid nanofluids—experimental and theoretical approach, Int. J. Mol. Sci. 23 (2022) 3056., doi: https://doi.org/10.3390/ijms23063056.

[11] L. Snoussi et al., Comparative analysis of machine learning techniques for estimating dynamic viscosity in various nanofluids for improving the efficiency of thermal and radiative systems, J. Radiat. Res. Appl. Sci. 18 (2025) 101205, doi: https://doi.org/10.1016/j.jrras.2024.101205.