THERMAL SCIENCE

International Scientific Journal

Jiaxu Wang

,

Lijuan HeORCID

,

Chenlei Zhao

,

Siwei Chen

,

Yazhuo Li

ADVANCES IN PREDICTING MICROCHANNEL HEAT SINK PERFORMANCE BASED ON CFD SIMULATION DATA IN MACHINE LEARNING

ABSTRACT
In the context of global device miniaturization trend, there is an urgent need for heat dissipation in electronic devices, and microchannel heat sinks have attracted much attention due to their advantages of small size and high heat transfer capacity. This paper firstly introduces the application of Computational fluid dynamics simulation methods in microchannel research and various design cases, then elaborates the knowledge related to Machine Learning, including its development history, main tasks and common algorithms, and analyzes its performance in predicting the performance coefficients of microchannels. Finally, we discuss the feature importance analysis technique, point out that there are differences in the evaluation of feature importance in different models, and introduce the new SHapley Additive exPlanations technique and its limitations, and finally conclude: Computational fluid dynamics simulation is an important tool for microchannel simulation research, and then when predicting the performance parameters based on the obtained data, it is necessary to select appropriate Machine learning algorithms and extend the data set to improve the prediction accuracy, while the feature importance analysis helps to understand the input-output relationship, which should be combined with physics and ML to improve the analysis method for the optimal design of microchannel heat sinks.
KEYWORDS
microchannel heat sink, computational fluid dynamics, machine learning, Feature importance analysis
PAPER SUBMITTED: 2025-10-29
PAPER REVISED: 2025-12-19
PAPER ACCEPTED: 2025-12-21
PUBLISHED ONLINE: 2026-02-08
DOI REFERENCE: https://doi.org/10.2298/TSCI251029011W
REFERENCES
[1] Alfaryjat A, Miron L, Pop H, et al. Experimental investigation of thermal and pressure performance in computer cooling systems using different types of nanofluids[J]. Nanomaterials, 2019, 9(9): 1231
[2] Pop E. Energy Dissipation and Transport in Nanoscale Devices [J]. Nano Research, 2010, 3: 147-169
[3] Bhandari P, Rawat K S, Prajapati Y K, et al. Design modifications in micro pin fin configuration of microchannel heat sink for single phase liquid flow: A review[J]. Journal of Energy Storage, 2023, 66: 107548
[4] Zimparov V. Energy conservation through heat transfer enhancement techniques[J]. International Journal of Energy Research, 2002, 26(7): 675-696
[5] Dwivedi A, Khan M M, Pali H S. A comprehensive review of thermal enhancement techniques in microchannel heat exchangers and heat sinks[J]. Journal of Thermal Analysis and Calorimetry, 2023, 148(23): 13189-13231
[6] Rabiei S, Khosravi R, Bahiraei M, Raziei M, Hosseini A A, Thermal and hydraulic characteristics of a hybrid nanofluid containing graphene sheets decorated with platinum through a new wavy cylindrical microchannel, Appl.Therm. Eng. 181 (2020), 115981
[7] Zunlong J, Zhichao Z, et al. Analysis and desigh of microchannel structure on microchannel heat sink[J]. Cryogenics & Superconductivity, 2013, 41(12): 63-69
[8] Song G, Chen H, Zhang Y, et al. Reviews: applications of optimization algorithm for microchannel and microchannel heat sink on heat transfer[J]. International Journal of Heat and Fluid Flow, 2024, 108: 109451
[9] Russell S J, Norvig P. Artificial intelligence: a modern approach[M]. pearson, 2016
[10] Abioye S O, Oyedele L O, Akanbi L, et al. Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges[J]. Journal of Building Engineering, 2021, 44: 103299
[11] Sarker I H. Machine learning: Algorithms, real-world applications and research directions[J]. SN computer science, 2021, 2(3): 160
[12] Butler K T, Davies D W, Cartwright H, et al. Machine learning for molecular and materials science[J]. Nature, 2018, 559(7715): 547-555
[13] Shailaja K, Seetharamulu B, Jabbar M A. Machine learning in healthcare: A review[C]//2018 Second international conference on electronics, communication and aerospace technology (ICECA). IEEE, 2018: 910-914
[14] Liakos K G, Busato P, Moshou D, et al. Machine Learning in Agriculture: A Review. Sensors (Special Issue" Sensors in Agriculture 2018")[EB/OL].(2018)
[15] Kwon B, Ejaz F, Hwang L K. Machine learning for heat transfer correlations[J]. International Communications in Heat and Mass Transfer, 2020, 116: 104694
[16] Krishnayatra G, Tokas S, Kumar R. Numerical heat transfer analysis & predicting thermal performance of fins for a novel heat exchanger using machine learning[J]. Case Studies in Thermal Engineering, 2020, 21: 100706
[17] Kumar N, Zhang L, Nayar S. What is a good nearest neighbors algorithm for finding similar patches in images?[C]//Computer Vision-ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part II 10. Springer Berlin Heidelberg, 2008: 364-378
[18] Gao J, Hu Z, Yang Q, et al. Fluid flow and heat transfer in microchannel heat sinks: Modelling review and recent progress[J]. Thermal Science and Engineering Progress, 2022, 29: 101203
[19] Tamura Y, Van Phuc P. Development of CFD and applications: Monologue by a non-CFD-expert[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2015, 144: 3-13
[20] Cappello G. A CFD Model for the Rate of Heat Release Predictions in the CFD Calorimeter[M]. Drexel University, 2023
[21] Li W, Mao N, He T, et al. CFD simulation of novel adaptive pin-fins microchannel heat sink to improve thermal management of electronic chips[J]. Applied Thermal Engineering, 2024, 252: 123667
[22] Montazeri F, Tavakoli M R, Salimpour M R. Improving thermal performance of rectangular microchannel heat sinks using porous layer: CFD simulation and optimization[J]. Journal of Applied Fluid Mechanics, 2023, 16(8): 1574-1586
[23] Wang F Z, Animasaun I L, Muhammad T, et al. Recent advancements in fluid dynamics: drag reduction, lift generation, computational fluid dynamics, turbulence modelling, and multiphase flow[J]. Arabian Journal for Science and Engineering, 2024, 49(8): 10237-10249
[24] Majchrzak M, Marciniak-Lukasiak K, Lukasiak P. A survey on the application of machine learning in turbulent flow simulations[J]. Energies, 2023, 16(4): 1755
[25] Patidar K C. On the use of nonstandard finite difference methods[J]. Journal of Difference Equations and Applications, 2005, 11(8): 735-758
[26] Jaśkowiec J, Milewski S. Coupling finite element method with meshless finite difference method in thermomechanical problems[J]. Computers & Mathematics with Applications, 2016, 72(9): 2259-2279
[27] Xu J, Fu H, Luk W, et al. Optimizing finite volume method solvers on Nvidia GPUs[J]. IEEE Transactions on Parallel and Distributed Systems, 2019, 30(12): 2790-2805
[28] Shakibaeinia A, Zarrati A R. Computational Fluid Mechanics and Hydraulics[J]. Water, 2022, 14(24): 3985
[29] Talele V, Vadaje Y. An ANN-based data-predictive approach for comparative study between CFD finite difference and finite volume method[J]. International Journal of Modern Physics C, 2022, 33(10): 2250139
[30] Feng Z, Luo X, Guo F, et al. Numerical investigation on laminar flow and heat transfer in rectangular microchannel heat sink with wire coil inserts[J]. Applied Thermal Engineering, 2017, 116: 597-609
[31] Liu H, Qi D, Shao X, et al. An experimental and numerical investigation of heat transfer enhancement in annular microchannel heat sinks[J]. International Journal of Thermal Sciences, 2019, 142: 106-120
[32] Lu G, Zhai X, Analysis on heat transfer and pressure drop of a microchannel heat sink with dimples and vortex generators, Int. J. Therm. Sci. 145 (2019), 105986
[33] Ling W, Zhou W, Liu C, Zhou F, Yuan D, Huang J, Structure and geometric dimension optimization of interlaced microchannel for heat transfer performance enhancement, Appl. Therm. Eng. 170 (2020), 115011
[34] Peng M, Chen L, Ji W, et al. Numerical study on flow and heat transfer in a multi-jet microchannel heat sink[J]. International Journal of Heat and Mass Transfer, 2020, 157: 119982
[35] Lin L, Zhao J, Lu G, et al. Heat transfer enhancement in microchannel heat sink by wavy channel with changing wavelength/amplitude[J]. International Journal of Thermal Sciences, 2017, 118: 423-434
[36] Hasis F B A, Krishna P M M, Aravind G P, et al. Thermo hydraulic performance analysis of twisted sinusoidal wavy microchannels[J]. International Journal of Thermal Sciences, 2018, 128: 124-136
[37] Lei Y, Chen Z. Cooling heat transfer and pressure drop of supercritical CO2 in wavy microchannels with consistent and opposite crests and troughs[J]. International Journal of 26 Refrigeration, 2020, 109: 64-81
[38] Sreehari D, Sharma A K. On thermal performance of serpentine silicon microchannels[J]. International Journal of Thermal Sciences, 2019, 146: 106067
[39] Lin Y, Luo Y, Li W, et al. Enhancement of flow boiling heat transfer in microchannel using micro-fin and micro-cavity surfaces[J]. International Journal of Heat and Mass Transfer, 2021, 179: 121739
[40] Zheng C, Zhang M, Qiu S, et al. Numerical simulation and experimental investigation of gas-liquid two-phase flow in a complex microchannel[J]. Chemical Engineering Science, 2021, 230: 116198
[41] Qaderi A, Jamaati J, Bahiraei M. CFD simulation of combined electroosmotic-pressure driven micro-mixing in a microchannel equipped with triangular hurdle and zeta-potential heterogeneity[J]. Chemical Engineering Science, 2019, 199: 463-477
[42] Hosseinpour V, Kazemeini M, Rashidi A. Develo** a metamodel based upon the DOE approach for investigating the overall performance of microchannel heat sinks utilizing a variety of internal fins[J]. International Journal of Heat and Mass Transfer, 2020, 149: 119219
[43] Bayrak E, Olcay A B, Serincan M F. Numerical investigation of the effects of geometric structure of microchannel heat sink on flow characteristics and heat transfer performance[J]. International journal of thermal sciences, 2019, 135: 589-600
[44] Burk B E, Grumstrup T P, Bevis T A, et al. Computational examination of two-phase microchannel heat transfer correlations with conjugate heat spreading[J]. International Journal of Heat and Mass Transfer, 2019, 132: 68-79
[45] El-Genk M S, Pourghasemi M. Nusselt number and development length correlations for laminar flows of water and air in microchannels[J]. International Journal of Heat and Mass Transfer, 2019, 133: 277-294
[46] Abdollahi A, Norris S E, Sharma R N. Fluid flow and heat transfer of liquid-liquid Taylor flow in square microchannels[J]. Applied Thermal Engineering, 2020, 172: 115123
[47] Wang M, Zhang W, et al. Improved thermal-hydraulic performance of a microchannel with hierarchical honeycomb porous ribs[J]. The Canadian Journal of Chemical Engineering, 2023, 101(2): 1083-1094
[48] LORI M S, VAFAI K. Heat transfer and fluid flow analysis of microchannel heat sinks with periodic vertical porous ribs[J]. Applied Thermal Engineering, 2022, 205:118059
[49] Wang C S, Shen P Y, Liou T M. Evaluation of porous rib and flow pulsation on microchannel thermal performance using a novel thermal lattice Boltzmann method[J]. International Journal of Thermal Sciences, 2022, 172: 107345
[50] Kose H A, Yildizeli A, Cadirci S. Parametric study and optimization of microchannel heat sinks with various shapes[J]. Applied Thermal Engineering, 2022, 211: 118368
[51] Kumar K, Kumar P. Effect of groove depth on hydrothermal characteristics of the rectangular microchannel heat sink[J]. International Journal of Thermal Sciences, 2021, 161: 106730
[52] Ali A Y M, Abo-Zahhad E M, Elkady M F, et al. Temperature uniformity enhancement of densely packed high concentrator photovoltaic module using four quadrants microchannel heat sink[J]. Solar Energy, 2020, 202: 446-464
[53] Ding Y, Jia L, Yin L, et al. Theoretical investigation on convective condensation annular flow of R410a inside rectangular microchannel[J]. International Journal of Heat and Mass Transfer, 2019, 131: 698-708
[54] Ma H, Duan Z, Ning X, et al. Numerical investigation on heat transfer behavior of thermally develo** flow inside rectangular microchannels[J]. Case Studies in Thermal Engineering, 2021, 24: 100856
[55] Lan Y, Feng Z, Huang K, et al. Effects of truncated and offset pin-fins on hydrothermal performance and entropy generation in a rectangular microchannel heat sink with variable fluid properties[J]. International Communications in Heat and Mass Transfer, 2021, 124: 105258
[56] Yang M, Cao B Y. Numerical study on flow and heat transfer of a hybrid microchannel cooling scheme using manifold arrangement and secondary channels[J]. Applied Thermal Engineering, 2019, 159: 113896
[57] McCulloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J]. The bulletin of mathematical biophysics, 1943, 5: 115-133
[58] Samuel A L. Some studies in machine learning using the game of checkers[J]. IBM Journal of research and development, 1959, 3(3): 210-229
[59] Hebb D O. The organization of behavior: A neuropsychological theory[M]. Psychology press, 2005
[60] Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE transactions on information theory, 1967, 13(1): 21-27
[61] Ho T K. Proceedings of 3rd international conference on document analysis and recognition[C].Proceedings of 3rd international conference on document analysis and recognition. 1995
[62] Fradkov A L. Early history of machine learning[J]. IFAC-PapersOnLine, 2020, 53(2): 1385-1390
[63] Tiruneh S A, Vu T T T, Rolnik D L, et al. Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review[J]. Current Hypertension Reports, 2024, 26(7): 309-323
[64] Lou Q, Deng Z, **ao Z, et al. Multilabel takagi-sugeno-kang fuzzy system[J]. IEEE Transactions on Fuzzy Systems, 2021, 30(9): 3410-3425
[65] Solomon D H, Guan H, Johansson F D, et al. Assessing clusters of comorbidities in rheumatoid arthritis: a machine learning approach[J]. Arthritis Research & Therapy, 2023, 25(1): 224
[66] Salehi H, Burgueño R. Emerging artificial intelligence methods in structural engineering[J]. Engineering structures, 2018, 171: 170-189
[67] Palansooriya K N, Li J, Dissanayake P D, et al. Prediction of soil heavy metal immobilization by biochar using machine learning[J]. Environmental science & technology, 2022, 56(7): 4187-4198
[68] Mari Selvam S, Balasubramanian P. Influence of biomass composition and microwave pyrolysis conditions on biochar yield and its properties: a machine learning approach[J]. BioEnergy Research, 2023, 16(1): 138-150
[69] Hearst M A, Dumais S T, Osuna E, et al. Support vector machines[J]. IEEE Intelligent Systems and their applications, 1998, 13(4): 18-28
[70] Smola A J, Schölkopf B. A tutorial on support vector regression[J]. Statistics and computing, 2004, 14: 199-222
[71] Awad M, Khanna R. Efficient learning machines: theories, concepts, and applications for engineers and system designers[M]. Springer nature, 2015
[72] Bishop C M, Nasrabadi N M. Pattern recognition and machine learning[M]. New York: springer, 2006
[73] Salehi K, Rahmani M, Atashrouz S. Machine learning assisted predictions for hydrogen storage in metal-organic frameworks[J]. International Journal of Hydrogen Energy, 2023, 48(85): 33260-33275
[74] Tafarroj M M, Mahian O, Kasaeian A, et al. Artificial neural network modeling of nanofluid flow in a microchannel heat sink using experimental data[J]. International Communications in Heat and Mass Transfer, 2017, 86: 25-31
[75] Zhou L, Garg D, Qiu Y, et al. Machine learning algorithms to predict flow condensation heat transfer coefficient in mini/micro-channel utilizing universal data[J]. International Journal of Heat and Mass Transfer, 2020, 162: 120351
[76] Mitchell M. An introduction to genetic algorithms[M]. MIT press, 1998
[77] Qaderi A, Jamaati J, Bahiraei M. CFD simulation of combined electroosmotic-pressure driven micro-mixing in a microchannel equipped with triangular hurdle and zeta-potential heterogeneity[J]. Chemical Engineering Science, 2019, 199: 463-477
[78] Baghban A, Kahani M, Nazari M A, et al. Sensitivity analysis and application of machine learning methods to predict the heat transfer performance of CNT/water nanofluid flows through coils[J]. International Journal of Heat and Mass Transfer, 2019, 128: 825-835
[79] Wen T, Zhu G, Jiao K, et al. Experimental study on the thermal and flow characteristics of ZnO/water nanofluid in mini-channels integrated with GA-optimized ANN prediction and CFD simulation[J]. International Journal of Heat and Mass Transfer, 2021, 178: 121617
[80] Hughes M T, Fronk B M, Garimella S. Universal condensation heat transfer and pressure drop model and the role of machine learning techniques to improve predictive capabilities[J]. International Journal of Heat and Mass Transfer, 2021, 179: 121712
[81] Kumar N, Zhang L, Nayar S. What is a good nearest neighbors algorithm for finding similar patches in images?[C].Computer Vision-ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part II 10, 2008: 364-378
[82] Chen T, Guestrin C. Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min[J]. 2016, 785-794
[83] Wu W, Wang Y, Zhao L, et al. Optimization of microchannel heat sinks with flexible vortex generators using GWO-SVR: A CFD and machine learning approach[J]. International Communications in Heat and Mass Transfer, 2025, 164: 108900
[84] Yang M， Yuan bin L, Xin gang Y. Investigation on the Performance Prediction of Microchannel Heat Sink Based on Machine Learning Approach[J]. Journal of Engineering Thermophysics, 2023, 44 (06): 1704-1708
[85] Jin R, Chen W, Sudjianto A. An Efficient Algorithm for Constructing Optimal Design of Computer Experiments [C].ASME 2003 International Design Engineer-ing Technical Conferences and Computers and Information in Engineering Conference, 2008: 545-554
[86] Takefuji Y. Enhancing feature importance analysis in battery research: a statistical methods perspective on machine learning limitations[J]. Energy Storage Materials, 2025, 78: 104242
[87] Lamens A, Bajorath J. Comparing Explanations of Molecular Machine Learning Models Generated with Different Methods for the Calculation of Shapley Values[J]. Molecular Informatics, 2025, 44(3): e202500067
[88] Takefuji Y. Reevaluating feature importance in gas-solid interaction predictions: A call for robust statistical methods[J]. Coordination Chemistry Reviews, 2025, 534: 216584
[89] Hosseini N, Tanzadehpanah H, Mansoori A, et al. Using a robust model to detect the association 29 between anthropometric factors and T2DM: machine learning approaches[J]. BMC Medical Informatics and Decision Making, 2025, 25(1): 49
[90] Dhingra H, Shetty R. Comparative Study of Machine Learning and Deep Learning Models for Early Prediction of Ovarian Cancer[J]. IEEE Access, 2025, 13: 87336-87349
[91] Alahmari T S, Farooq F. Novel approaches in prediction of tensile strain capacity of engineered cementitious composites using interpretable approaches[J]. Reviews on Advanced Materials Science, 2025, 64(1): 20250088
[92] Shanmugam M, Maganti L S. Machine learning-based thermal performance study of microchannel heat sink under non-uniform heat load conditions[J]. Applied Thermal Engineering, 2024, 253: 123769
[93] Lundberg S M, Lee S I. A unified approach to interpreting model predictions[J]. Advances in neural information processing systems, 2017, 30
[94] Sikirica A, Grbić L, Kranjević L. Machine learning based surrogate models for microchannel heat sink optimization[J]. Applied thermal engineering, 2023, 222: 119917
[95] Karniadakis G E, Kevrekidis I G, Lu L, et al. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6): 422-440
[96] Karagiorgi G, Kasieczka G, Kravitz S, et al. Machine learning in the search for new fundamental physics[J]. Nature Reviews Physics, 2022, 4(6): 399-412
PDF VERSION [DOWNLOAD]
Advances in predicting microchannel heat sink performance based on CFD simulation data in machine learning

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence