Machine Learning-Driven Prediction and Analysis of Magnetohydrodynamic (MHD) Natural Convection in Nanofluid-Filled Trapezoidal Cavities with Variable Obstacle Shapes, Wall Corrugations, and Inclination Angles
This study proposes a machine learning-enhanced framework to predict and analyze magnetohydrodynamic (MHD) natural convection within nanofluid-filled trapezoidal cavities featuring variable obstacle shapes, wall corrugations, and inclination angles. A comprehensive dataset was generated through Finite Element Method (FEM) simulations covering a wide parametric range, including Rayleigh numbers (103 - 106) and Hartmann numbers (0 - 50), for Cu-H2O nanofluids. Key thermal performance metrics Nusselt number (Nu), entropy generation (ST), and Ecological Coefficient of Performance (ECOP), were extracted and used to train supervised machine learning models: Support Vector Regression (SVR), Decision Tree (DT), and Random Forest (RF). Among them, the RF model achieved superior performance, yielding R2 scores of 0.991 (Nu), 0.982 (St), and 0.989 (ECOP), with mean prediction errors under 1.5%. The results show excellent agreement between FEM and ML outputs across diverse configurations, including different obstacle geometries (star, square, triangular), wall undulations (sinusoidal, square, triangular), and inclination angles (15？, 30？, 45？). The integration of ML significantly reduced computational cost while preserving high accuracy, thus demonstrating its viability for rapid prediction and optimization. This hybrid FEM-ML methodology offers a powerful tool for real-time thermal system analysis and design in advanced MHD nanofluid applications.
References
[1]
Hidki, R., El Moutaouakil, L., Charqui, Z., Boukendil, M. and Zrikem, Z. (2021) Natural Convection in a Square Cavity Containing Two Heat-Generating Cylinders with Different Geometries. MaterialsToday: Proceedings, 45, 7415-7423. https://doi.org/10.1016/j.matpr.2021.01.626
[2]
Cao, Y., Ayed, H., Jarad, F., Togun, H., Alias, H., Issakhov, A., etal. (2021) MHD Natural Convection Nanofluid Flow in a Heat Exchanger: Effects of Brownian Motion and Thermophoresis for Nanoparticles Distribution. CaseStudiesinThermalEngineering, 28, Article ID: 101394. https://doi.org/10.1016/j.csite.2021.101394
[3]
Zheng, J., Zhang, L., Yu, H., Wang, Y. and Zhao, T. (2021) Study on Natural Convection Heat Transfer in a Closed Cavity with Hot and Cold Tubes. ScienceProgress, 104, 1-25. https://doi.org/10.1177/00368504211020965
[4]
Ibrahim, M.N.J., Hammoodi, K.A., Abdulsahib, A.D. and Flayyih, M.A. (2022) Study of Natural Convection Inside Inclined Nanofluid Cavity with Hot Inner Bodies (Circular and Ellipse Cylinders). InternationalJournalofHeatandTechnology, 40, 699-705. https://doi.org/10.18280/ijht.400306
[5]
Tasnim, S., Mitra, A., Saha, H., Islam, M.Q. and Saha, S. (2023) MHD Conjugate Natural Convection and Entropy Generation of a Nanofluid Filled Square Enclosure with Multiple Heat-Generating Elements in the Presence of Joule Heating. ResultsinEngineering, 17, Article ID: 100993. https://doi.org/10.1016/j.rineng.2023.100993
[6]
Boulahia, Z., Wakif, A. and Sehaqui, R. (2016) Numerical Study of Mixed Convection of the Nanofluids in Two-Sided Lid-Driven Square Cavity with a Pair of Triangular Heating Cylinders. JournalofEngineering, 2016, Article ID: 8962091. https://doi.org/10.1155/2016/8962091
[7]
Ali, A., Ayaz, M., Ahmad, Z. and Marei, A.M. (2025) Analysis of Entropy Generation in Magnetohydrodynamic Convective Flow of Nanofluids within a Wavy Trapezoidal Enclosure: A Brinkmann-Forchheimer Model Using Finite Element Method. CaseStudiesinThermalEngineering, 73, 106719. https://doi.org/10.1016/j.csite.2025.106719
[8]
Nadeem, S., Arif, M., Ullah, I. and Alzabut, J. (2025) MHD Natural Convection of Nanofluid Flow Using a Corrugated Permeable Medium within Corrugated Circular Cavity. JournalofThermalAnalysisandCalorimetry, 150, 5697-5724. https://doi.org/10.1007/s10973-025-14032-y
[9]
Dogonchi, A.S., Sadeghi, M.S., Ghodrat, M., Chamkha, A.J., Elmasry, Y. and Alsulami, R. (2021) Natural Convection and Entropy Generation of a Nanoliquid in a Crown Wavy Cavity: Effect of Thermo-Physical Parameters and Cavity Shape. CaseStudiesinThermalEngineering, 27, Article ID: 101208. https://doi.org/10.1016/j.csite.2021.101208
[10]
Alnajem, M.H.S., Alsabery, A.I. and Hashim, I. (2019) Entropy Generation and Natural Convection in a Wavy-Wall Cavity Filled with a Nanofluid and Containing an Inner Solid Cylinder. IOPConferenceSeries: MaterialsScienceandEngineering, 518, Article ID: 032044. https://doi.org/10.1088/1757-899x/518/3/032044
[11]
Chowdhury, K. and Alim, M.A. (2023) Mixed Convection in a Double Lid-Driven Wavy Shaped Cavity Filled with Nanofluid Subject to Magnetic Field and Internal Heat Source. JournalofAppliedMathematics, 2023, Article ID: 7117186. https://doi.org/10.1155/2023/7117186
[12]
Boulahia, Z., Wakif, A., Chamkha, A.J., Amanulla, C.H. and Sehaqui, R. (2018) Effects of Wavy Wall Amplitudes on Mixed Convection Heat Transfer in a Ventilated Wavy Cavity Filled by Copper-Water Nanofluid Containing a Central Circular Cold Body. JournalofNanofluids, 8, 1170-1178. https://doi.org/10.1166/jon.2019.1654
[13]
Khatun, S., Kundu, R., Islam, S., Aktary, R. and Kumar, D. (2025) Sensitivity Analysis on Natural Convective Trapezoidal Cavity Containing Hybrid Nanofluid with Magnetic Effect: Numerical and Statistical Approach. Heliyon, 11, e41508. https://doi.org/10.1016/j.heliyon.2024.e41508
[14]
Selimefendigil, F. (2017) Natural Convection in a Trapezoidal Cavity with an Inner Conductive Object of Different Shapes and Filled with Nanofluids of Different Nanoparticle Shapes. IranianJournalofScienceandTechnology, TransactionsofMechanicalEngineering, 42, 169-184. https://doi.org/10.1007/s40997-017-0083-3
[15]
Mohammed, A.A., Thaer, M. and Yahya, D.Q. (2022) Mixed Convection Heat Transfer of Al2O₃-H2O Nanofluid in a Trapezoidal Lid-Driven Cavity at Different Angles of Inclination. Texas Journal of Engineering and Technology, 11, 20-30.
[16]
Mejbel, A., Abdulkadhim, A., Hamzah, R., Hamzah, H. and Ali, F. (2020) Natural Convection Heat Transfer for Adiabatic Circular Cylinder Inside Trapezoidal Enclosure Filled with Nanofluid Superposed Porous-Nanofluid Layer. FMETransactions, 48, 82-89. https://doi.org/10.5937/fmet2001082m
[17]
Abdelmalek, Z., Tayebi, T., Dogonchi, A.S., Chamkha, A.J., Ganji, D.D. and Tlili, I. (2020) Role of Various Configurations of a Wavy Circular Heater on Convective Heat Transfer within an Enclosure Filled with Nanofluid. InternationalCommunicationsinHeatandMassTransfer, 113, Article ID: 104525. https://doi.org/10.1016/j.icheatmasstransfer.2020.104525
[18]
Sheikhzadeh, G.A., Nikfar, M. and Fattahi, A. (2012) Numerical Study of Natural Convection and Entropy Generation of Cu-Water Nanofluid around an Obstacle in a Cavity. JournalofMechanicalScienceandTechnology, 26, 3347-3356. https://doi.org/10.1007/s12206-012-0805-9
[19]
Ali, M.M., Alim, M.A., Akhter, R. and Ahmed, S.S. (2017) MHD Natural Convection Flow of CuO/Water Nanofluid in a Differentially Heated Hexagonal Enclosure with a Tilted Square Block. InternationalJournalofAppliedandComputationalMathematics, 3, 1047-1069. https://doi.org/10.1007/s40819-017-0400-y
[20]
Akram, M., Benhanifia, K., Brahim, M., Rahmani, L., Ansari, A.Z., Eid, M.R., etal. (2024) Natural Convection and Flow Patterns of Cu-Water Nanofluids in Hexagonal Cavity: A Novel Thermal Case Study. OpenPhysics, 22, Article ID: 20240041. https://doi.org/10.1515/phys-2024-0041
[21]
Munshi, M.J.H., Bhuiyan, A.H. and Alim, M.A. (2015) A Numerical Study of Natural Convection in a Square Enclosure with Non-Uniformly Heated Bottom Wall and Square Shape Heated Block. AmericanJournalofEngineeringResearch (AJER), 4, 124-137.
[22]
Chowdhury, K., Alim, A. and Hossen, M. (2020) Natural Convection in a Partially Heated and Cooled Square Enclosure Containing a Diamond Shaped Heated Block. InternationalJournalofFluidMechanics&ThermalSciences, 6, 1-8. https://doi.org/10.11648/j.ijfmts.20200601.11
[23]
Saha, B.K., Jihan, J.I., Barai, G., Moon, N.J., Saha, G. and Saha, S.C. (2025) Exploring Natural Convection and Heat Transfer Dynamics of Al2O3-H2O Nanofluid in a Modified Tooth-Shaped Cavity Configuration. InternationalJournalofThermofluids, 25, Article ID: 101005. https://doi.org/10.1016/j.ijft.2024.101005
[24]
Sompong, P. and Witayangkurn, S. (2013) Natural Convection in a Trapezoidal Enclosure with Wavy Top Surface. JournalofAppliedMathematics, 2013, Article ID: 840632. https://doi.org/10.1155/2013/840632
[25]
Suresh Reddy, E. and Panda, S. (2022) Heat Transfer of MHD Natural Convection Casson Nanofluid Flows in a Wavy Trapezoidal Enclosure. TheEuropeanPhysicalJournalSpecialTopics, 231, 2733-2747. https://doi.org/10.1140/epjs/s11734-022-00609-3
[26]
Alomari, M.A., Al-Farhany, K., Hashem, A.L., Al-Dawody, M.F., Redouane, F. and Olayemi, O.A. (2021) Numerical Study of MHD Natural Convection in Trapezoidal Enclosure Filled with (50%MgO-50%Ag/Water) Hybrid Nanofluid: Heated Sinusoidal from Below. InternationalJournalofHeatandTechnology, 39, 1271-1279. https://doi.org/10.18280/ijht.390425
[27]
Rahaman, M.M., Bhowmick, S. and Saha, S.C. (2025) Thermal Performance and Entropy Generation of Unsteady Natural Convection in a Trapezoid-Shaped Cavity. Processes, 13, Article 921. https://doi.org/10.3390/pr13030921
[28]
Alshayji, A., Alzuabi, M.K. and Aljuwayhel, N.F. (2025) Numerical Investigation of Nanofluid Free Convection in a Rectangular Cavity Using Variable Properties. JournalofThermalAnalysisandCalorimetry, 150, 6519-6538. https://doi.org/10.1007/s10973-025-14197-6
[29]
El hadoui, B. and Kaddiri, M. (2025) Optimizing Nanofluid-Enhanced Mixed Convection in Inclined Rectangular Chambers. JournalofThermalAnalysisandCalorimetry, 150, 12717-12733. https://doi.org/10.1007/s10973-025-14491-3
[30]
Uddin, M.J., Al Kalbani, K.S., Rahman, M.M., Alam, M.S., Al-Salti, N. and Eltayeb, I.A. (2016) Fundamentals of Nanofluids: Evolution, Applications and New Theory. International Journal of Biomathematics and Systems Biology, 2, 1-32.
[31]
Ali, M.M., Akhter, R. and Alim, M.A. (2020) MHD Natural Convection and Entropy Generation in a Grooved Enclosure Filled with Nanofluid Using Two-Component Non-Homogeneous Model. SNAppliedSciences, 2, Article No. 571. https://doi.org/10.1007/s42452-020-2319-x
[32]
Deep, S.S., Sultana, S., Haque, T., Rahman, M.T. and Saha, S. (2025) Coupled Fluid-Thermal Analysis of a Square Chamber with a Wavy Top Wall and an Internal Solid Elliptical/Circular Block. ApplicationsinEngineeringScience, 24, Article ID: 100268. https://doi.org/10.1016/j.apples.2025.100268
[33]
Parmar, K., Parmar, N., Parwani, A.K. and Tripathi, S. (2024) Experimental Studies and Machine Learning Approaches for Thermal Parameters Prediction and Data Analysis in Closed-Loop Pulsating Heat Pipes with Al2O3-Di Water Nanofluid. JournalofThermalAnalysisandCalorimetry, 150, 591-606. https://doi.org/10.1007/s10973-024-13859-1
[34]
Hussain, M., Lin, D., Waqas, H. and Al-Mdallal, Q.M. (2025) An Artificial Intelligence and Machine Learning-Driven CFD Simulation for Optimizing Thermal Performance of Blood-Integrated Ternary Nano-Fluid. EngineeringApplicationsofComputationalFluidMechanics, 19, Article ID: 2459664. https://doi.org/10.1080/19942060.2025.2459664
[35]
Godasiaei, S.H. and Kamali, H.A. (2025) Evaluating Machine Learning as an Alternative to CFD for Heat Transfer Modeling. MicrogravityScienceandTechnology, 37, Article No. 6. https://doi.org/10.1007/s12217-025-10163-x
[36]
Sharma, P., Ramesh, K., Parameshwaran, R. and Deshmukh, S.S. (2022) Thermal Conductivity Prediction of Titania-Water Nanofluid: A Case Study Using Different Machine Learning Algorithms. CaseStudiesinThermalEngineering, 30, Article ID: 101658. https://doi.org/10.1016/j.csite.2021.101658
[37]
Hussain, S.M., Nawaz, D., Attique, B., Haroon, M., Jamshed, W., Guedri, K., etal. (2025) Machine Learning Estimation of Heat and Mass Transfer Attributes of Thermal Radiative Williamson Nanofluid Flow via Nonlinear Stretchable Surface. JournalofRadiationResearchandAppliedSciences, 18, Article ID: 101581. https://doi.org/10.1016/j.jrras.2025.101581
[38]
Biswal, G. and Meshram, G.S. (2025) Machine Learning-Based Prediction of Nusselt Number for Vertical Helical Coils in Natural Convection Heat Transfer. InternationalCommunicationsinHeatandMassTransfer, 164, Article ID: 108983. https://doi.org/10.1016/j.icheatmasstransfer.2025.108983
[39]
Wang, R., Zeng, Z., Sadeq, A.M., Agrawal, M.K., Muhammad, T. and Rao, B.N. (2025) Predictive Performance Analysis of Machine Learning Models for Forced Convective Heat Transfer of a Flat-Plate in Counter-Rotating Cylinder Systems: A Comprehensive Evaluation. CaseStudiesinThermalEngineering, 74, Article ID: 106961. https://doi.org/10.1016/j.csite.2025.106961
[40]
Tanzim, R., Das, A., Zaman, S.N., Lia, T.A. and Sarwar, S.T. (2025) A Chromosome Inspired Fin Structure for Microchannel Heat Sinks: CFD Driven XGBR, ANN, and MLR Models for Thermal and Fluid Flow Prediction. InternationalCommunicationsinHeatandMassTransfer, 169, Article ID: 109763. https://doi.org/10.1016/j.icheatmasstransfer.2025.109763
