Yapay zekâ destekli nanoakışkan modellemesi: Termal iletkenlik ve viskozite için stabiliteye bağlı korelasyon geliştirilmesi

Year 2024, Volume: 13 Issue: 3, 932 - 938, 15.07.2024

Fevzi Şahin

https://doi.org/10.28948/ngumuh.1455986

Abstract

Nanoakışkan çalışmalarında sonuçların deneysel çalışmalara bağlı olması, son yıllarda yapay zeka tabanlı modelleme çalışmaları ile aşılmaya çalışılmaktadır. Yapılan modelleme çalışmalarında nanoakışkanların temel termal özellikleri olan ısıl iletkenlik ve viskozite üzerine yoğunlaşılmış ve nanoakışkanlar için gerekli olan en önemli özelliklerden olan stabilitenin çoğu zaman ihmal edildiği görülmektedir. Bu çalışmada TiO2 nanoakışkanı için deneysel olarak ortaya konmuş veriler kullanılarak ısıl iletkenlik ve viskozite değerleri YSA ile modellenmiştir. YSA modelinin performans ölçütleri olan MSE, R değerleri sırasıyla 4,2484E-06 ve 0.99982’dir. Ağ sonuçlarında sıcaklık, kütlesel oran ve stabiliteyi doğrudan etkileyen pH değerine bağlı olarak bir model geliştirilmiştir. Model sonuçları kullanılarak ısıl iletkenlik ve viskozite özellikleri için sıcaklık, kütlesel oran ve pH değişkenlerine bağlı olarak korelasyonlar geliştirilmiştir. Ortaya konulan korelasyonların ısıl iletkenlik için deneysel değerlerden sapma oranları ± % 3,5 aralığında iken viskozite için bu oran ± % 9 aralığın elde edilmiştir.

Keywords

Nanoakışkan, ısıl iletkenlik, viskozite, stabilite, Yapay sinir ağları

Artificial intelligence-assisted nanofluid modeling: Developing stability-based correlation for thermal conductivity and viscosity

Abstract

In recent years, artificial intelligence-based modeling studies have been attempted to overcome the reliance on experimental results in nanofluid research. These modeling studies have mainly focused on the fundamental thermal properties of nanofluids, namely thermal conductivity and viscosity, while stability, which is one of the most important properties for nanofluids, has often been neglected. In this study, experimental data for TiO2 nanofluid has been utilized to model thermal conductivity and viscosity values using Artificial Neural Networks (ANNs). The performance metrics of the ANN model, MSE (Mean Squared Error), and R (Correlation Coefficient), are 4,2484E-06 and 0,99982, respectively. Using the model results, correlations have been established temperature, mass ratio, and pH variables for the thermal conductivity and viscosity properties of nanofluids. The deviation rates of the proposed correlations from the experimental values are within the range of ± 3,5% for thermal conductivity and ± 9% for viscosity.

Keywords

Nanofluid, thermal conductivity, viscosity, stability, Artificial neural networks

References

• S. Özerinç, S. Kakaç and A.G. Yazıcıoǧlu, Enhanced thermal conductivity of nanofluids: A state-of-the-art review, Microfluidics and Nanofluidics, 8, 145–170, 2010. https://doi.org/10.1007/s10404-009-0524-4
• F. Sahin and O. Genc, Experimentally determining the thermal properties of NiFe2O4 magnetic nanofluid under suitable stability conditions: Proposal the new correlation for thermophysical properties, Powder Technology, 427, 118706, 2023. https://doi.org/10.1016/j.powtec.2023.118706.
• W. Ajeeb, R.R.S. Thieleke da Silva and S.M.S. Murshed, Experimental investigation of heat transfer performance of Al2O3 nanofluids in a compact plate heat exchanger, Applied Thermal Engineering, 218, 119321, 2023. https://doi.org/10.1016/J.APPLTHERMALENG.2022.119321.
• F. Sahin, O. Genc, M. Gökcek and A.B. Çolak, From experimental data to predictions: Artificial intelligence supported new mathematical approaches for estimating thermal conductivity, viscosity and zeta potential in Fe3O4-water magnetic nanofluids, Powder Technology, 430 118974, 2023. https://doi.org/10.1016/J.POWTEC.2023.118974.
• L. Li, Y. Zhai, Y. Jin, J. Wang, H. Wang and M. Ma, Stability, thermal performance and artificial neural network modeling of viscosity and thermal conductivity of Al2O3-ethylene glycol nanofluids, Powder Technology, 363, 360–368, 2020. https://doi.org/10.1016/j.powtec.2020.01.006.
• F. Sahin, M. Kapusuz, L. Namli and H. Ozcan, Determination of the Optimum Stability Conditions in Al2O3 Nanofluids with Artificial Neural Networks, International Journal of Thermophysics, 41, 1–20, 2020. https://doi.org/10.1007/s10765-020-02625-8.
• F. Sahin and L. Namlı, Nanoakışkanlarda Kararlılığın Isı Transferini İyileştirme Açısından Önemi, Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 7, 880–898, 2018. https://doi.org/10.28948/ngumuh.445339.
• F. Sahin, M. Kapusuz, L. Namli and H. Ozcan, Determination of the Optimum Stability Conditions in Al2O3 Nanofluids with Artificial Neural Networks, International Journal of Thermophysics, 41, 1–20, 2020. https://doi.org/10.1007/s10765-020-02625-8.
• X. Zhang and J. Li, A review of uncertainties in the study of heat transfer properties of nanofluids, Heat and Mass Transfer, 59(4), 621–653, 2022. https://doi.org/10.1007/S00231-022-03276-1.
• M. Hassanpour, B. Vaferi and M.E. Masoumi, Estimation of pool boiling heat transfer coefficient of alumina water-based nanofluids by various artificial intelligence (AI) approaches, Applied Thermal Engineering, 128, 1208–1222, 2018. https://doi.org/10.1016/j.applthermaleng.2017.09.066.
• G.A. Longo, C. Zilio, L. Ortombina and M. Zigliotto, Application of Artificial Neural Network (ANN) for modeling oxide-based nanofluids dynamic viscosity, International Communications in Heat and Mass Transfer, 83, 8–14, 2017. https://doi.org/10.1016/j.icheatmasstransfer.2017.03.003.
• A. Alirezaie, S. Saedodin, M.H. Esfe and S.H. Rostamian, Investigation of rheological behavior of MWCNT (COOH-functionalized)/MgO - Engine oil hybrid nanofluids and modelling the results with artificial neural networks, Journal of Molecular Liquids, 241, 173–181, 2017. https://doi.org/10.1016/j.molliq.2017.05.121.
• M. Hemmat Esfe, Designing a neural network for predicting the heat transfer and pressure drop characteristics of Ag/water nanofluids in a heat exchanger, Applied Thermal Engineering, 126, 559–565, 2017. https://doi.org/10.1016/j.applthermaleng.2017.06.046.
• M.H. Esfe, D. Toghraie and F. Amoozadkhalili, Optimization and design of ANN with Levenberg-Marquardt algorithm to increase the accuracy in predicting the viscosity of SAE40 oil-based hybrid nano-lubricant, Powder Technology, 415, 118097, 2023. https://doi.org/10.1016/J.POWTEC.2022.118097.
• F. Sahin, O. Genc, M. Gökcek and A.B. Çolak, An experimental and new study on thermal conductivity and zeta potential of Fe3O4/water nanofluid: Machine learning modeling and proposing a new correlation, Powder Technology, 420, 118388, 2023. https://doi.org/10.1016/J.POWTEC.2023.118388.
• M. Hemmat Esfe, F. Amoozadkhalili and D. Toghraie, Determining the optimal structure for accurate estimation of the dynamic viscosity of oil-based hybrid nanofluid containing MgO and MWCNTs nanoparticles using multilayer perceptron neural networks with Levenberg-Marquardt Algorithm, Powder Technology, 415, 118085, 2023. https://doi.org/10.1016/J.POWTEC.2022.118085.
• M. Hemmat Esfe and S. Saedodin, An experimental investigation and new correlation of viscosity of ZnO-EG nanofluid at various temperatures and different solid volume fractions, Experimental Thermal and Fluid Science, 55, 1–5, 2014. https://doi.org/10.1016/j.expthermflusci.2014.02.011.
• S.M.S. Murshed, K.C. Leong and C. Yang, Enhanced thermal conductivity of TiO2—water based nanofluids, International Journal of Thermal Sciences, 44, 367–373, 2005. https://doi.org/10.1016/j.ijthermalsci.2004.12.005.
• M. Hojjat, S.G. Etemad, R. Bagheri and J. Thibault, Thermal conductivity of non-Newtonian nanofluids: Experimental data and modeling using neural network, International Journal of Heat and Mass Transfer, 54, 1017–1023, 2011. https://doi.org/10.1016/J.IJHEATMASSTRANSFER.2010.11.039.
• K.M. Yashawantha and A.V. Vinod, ANN modelling and experimental investigation on effective thermal conductivity of ethylene glycol:water nanofluids, Journal of Thermal Analysis and Calorimetry, 145, 609–630, 2021. https://doi.org/10.1007/S10973-020-09756-Y/FIGURES/24.
• W. He, B. Ruhani, D. Toghraie, N. Izadpanahi, N.N. Esfahani, A. Karimipour and M. Afrand, Using of Artificial Neural Networks (ANNs) to predict the thermal conductivity of Zinc Oxide–Silver (50%–50%)/Water hybrid Newtonian nanofluid, International Communications in Heat and Mass Transfer, 116, 104645, 2020. https://doi.org/10.1016/J.ICHEATMASSTRANSFER.2020.104645.
• M. Amani, P. Amani, A. Kasaeian, O. Mahian, I. Pop and S. Wongwises, Modeling and optimization of thermal conductivity and viscosity of MnFe2O4 nanofluid under magnetic field using an ANN, Scientific Reports, 7:1, 1–13, 2017. https://doi.org/10.1038/s41598-017-17444-5.
• K. Verma, R. Agarwal, R.K. Duchaniya and R. Singh, Measurement and Prediction of Thermal Conductivity of Nanofluids Containing TiO2 Nanoparticles, Journal of Nanoscience and Nanotechnology, 17, 1068–1075, 2017. https://doi.org/10.1166/JNN.2017.12584.
• M. Tahani, M. Vakili and S. Khosrojerdi, Experimental evaluation and ANN modeling of thermal conductivity of graphene oxide nanoplatelets/deionized water nanofluid, International Communications in Heat and Mass Transfer, 76, 358–365, 2016. https://doi.org/10.1016/J.ICHEATMASSTRANSFER.2016.06.003.
• A.B. Çolak, Developing optimal artificial neural network (ann) to predict the specific heat of water-based yttrium oxide (Y2O3) nanofluid according to the experimental data and proposing new correlation, Heat Transfer Research, 51, 1565–1586, 2020. https://doi.org/10.1615/HEATTRANSRES.2020034724.
• H. Zhang, S. Qing, Y. Zhai, X. Zhang and A. Zhang, The changes induced by pH in TiO2/water nanofluids: Stability, thermophysical properties and thermal performance, Powder Technology, 377, 748–759, 2020. https://doi.org/10.1016/j.powtec.2020.09.004.