Machine learning in flow boiling: predicting bubble lift-off diameter despite data limitations

Year 2025, Volume: 11 Issue: 4, 1094 - 1118, 31.07.2025

Atta Heydarpour Tabrizi Mousa Mohammadpourfard , Mostafa Mohammadpourfard

Abstract

This study concentrates on applying machine learning techniques to flow boiling in order to predict the bubble lift-off diameter. This prediction is critical because the diameter plays a key role in understanding boiling dynamics and calculating heat transfer rates. Additionally, accurately predicting this diameter is essential for optimizing thermal systems and enhancing energy efficiency. By evaluating the performance of three different machine learning algorithms: M5 tree, multilinear regression, and random forest, we aimed to assess their effectiveness in providing reliable predictions even with limited experimental data. This research is essential as it demonstrates the potential of machine learning to enhance predictive accuracy in scenarios where obtaining extensive datasets is challenging. Our findings show that these machine-learning techniques are effective for accurate predictions. The results show that the coefficient of determination ranged from 0.64 to 0.94, indicating how well the models fit the data. The root mean square error was between 0.009 and 0.02, and the mean absolute error ranged from 0.0004 to 0.02. Based on the findings, it can be inferred that the machine learning algorithms used in this study are reliable for predicting bubble lift-off diameter. This reliability also extends to other experimental parameters, suggesting that these techniques can be effectively applied in various contexts with limited data. This study demonstrates the potential of machine learning to predict experimental parameters and advances previous research by identifying key factors that influence bubble lift-off diameter.

Keywords

Bubble Size , Machine Learning Techniques , Predictive Model , Regression Model

References

• 1. Hoang NH, Chu IC, Euh DJ, Song CH. A mechanistic model for predicting the maximum diameter of vapor bubbles in a subcooled boiling flow. Inter J Heat Mass Transf 2016;94:174–179.[CrossRef]
• 2. Situ R, Hibiki T, Ishii M, Mori M. Bubble lift-off size in forced convective subcooled boiling flow. Intern J Heat Mass Transf 2005;48:5536–5548. [CrossRef]
• 3. Cho YJ, Yum SB, Lee JH, Park GC. Development of bubble departure and lift-off diameter models in low heat flux and low flow velocity conditions. Intern J Heat Mass Transf 2011;54:3234–3244. [CrossRef]
• 4. Levy S. Forced convection subcooled boiling—prediction of vapor volumetric fraction. Intern J Heat Mass Transf 1967;10:951–965. [CrossRef]
• 5. Staub FW. The void fraction in subcooled boiling—prediction of the initial point of net vapor generation. J Heat Transf 1968;90:151–157. [CrossRef]
• 6. Zeng LZ, Klausner JF, Bernhard DM, Mei R. A unified model for the prediction of bubble detachment diameters in boiling systems—II. Flow boiling. Intern J Heat Mass Transf 1993;36:2271–2279. [CrossRef]
• 7. Hosseinzadeh K, Moghaddam MA, Hatami M, Ganji DD, Ommi F. Experimental and numerical study for the effect of aqueous solution on heat transfer characteristics of two phase close thermosyphon. Intern Commun Heat Mass Transf 2022;135:106129. [CrossRef]
• 8. Hosseinzadeh K, Ganji DD, Ommi F. Effect of SiO2 super-hydrophobic coating and self-rewetting fluid on two phase closed thermosyphon heat transfer characteristics: An experimental and numerical study. J Mol Liq 2020;315:113748. [CrossRef]
• 9. Prodanovic V, Fraser D, Salcudean M. Bubble behavior in subcooled flow boiling of water at low pressures and low flow rates. Intern J Multip Flow 2002;28:1–19. [CrossRef]
• 10. Chu IC, No HC, Song CH. Bubble lift-off diameter and nucleation frequency in vertical subcooled boiling flow. J Nuc Sci Technol 2011;48:936–949. [CrossRef]
• 11. Ünal HC. Maximum bubble diameter, maximum bubble-growth time and bubble-growth rate during the subcooled nucleate flow boiling of water up to 17.7 MN/m2. Intern J Heat Mass Transf 1976;19:643–649. [CrossRef]
• 12. Mehdi S, Borumand M, Hwang G. Accurate and robust predictions of pool boiling heat transfer with micro-structured surfaces using probabilistic machine learning models. Intern J Heat Mass Transf 2024;226:125487. [CrossRef]
• 13. Bard A, Qiu Y, Kharangate CR, French R. Consolidated modeling and prediction of heat transfer coefficients for saturated flow boiling in mini/micro-channels using machine learning methods. App Therm Eng 2022;210:118305. [CrossRef]
• 14. Qiu Y, Garg D, Kim SM, Mudawar I, Kharangate CR. Machine learning algorithms to predict flow boiling pressure drop in mini/micro-channels based on universal consolidated data. Intern J Heat Mass Transf 2021;178:121607. [CrossRef]
• 15. He Y, Hu C, Li H, Hu X, Tang D. Reliable predictions of bubble departure frequency in subcooled flow boiling: A machine learning-based approach. Intern J Heat Mass Transf 2022;195:123217. [CrossRef]
• 16. Zhang J, Zhong D, Shi H, Meng J, Chen L. Machine learning prediction of critical heat flux on downward facing surfaces. Intern J Heat Mass Transf 2022;191:122857. [CrossRef]
• 17. Cabarcos A, Paz C, Suarez E, Vence J. Application of supervised learning algorithms for temperature prediction in nucleate flow boiling. App Therm Eng 2024;240:122155. [CrossRef]
• 18. Klausner JF, Mei R, Bernhard DM, Zeng LZ. Vapor bubble departure in forced convection boiling. Intern J Heat Mass Transf 1993;36:651–662. [CrossRef]
• 19. Okawa T, Kaiho K, Sakamoto S, Enoki K. Observation and modelling of bubble dynamics in isolated bubble regime in subcooled flow boiling. Nuc Eng Des 2018;335:400–408. [CrossRef]
• 20. Basu N. Modeling and experiments for wall heat flux partitioning during subcooled flow boiling of water at low pressures. (ProQuest Dissertations & Theses). Los Angeles: University of California; 2003. Report No: 3081174. [CrossRef]
• 21. Quinlan JR. Learning With Continuous Classes. Proceedings of Australian Joint Conference on Artificial Intelligence, 16-18 November 1992. Hobart: Scientific Research; 1992. s. 343–348.
• 22. Feng Y, Hao W, Li H, Cui N, Gong D, Gao D. Machine learning models to quantify and map daily global solar radiation and photovoltaic power. Renew Sustain Energy Review 2020;118:109393. [CrossRef]
• 23. Fan J, Ma X, Wu L, Zhang F, Yu X, Zeng W. Light gradient boosting machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data. Agricult Water Manag 2019;225:105758. [CrossRef]
• 24. Nieto PJG, Gonzalo EG, Menendez L, Prado LA. Predicting the critical superconducting temperature using the random forest, MLP neural network, M5 model tree and multivariate linear regression. Alex Eng J 2024;86:144–156. [CrossRef]
• 25. Fan J, Wang X, Zhang F, Ma X, Wu L. Predicting daily diffuse horizontal solar radiation in various climatic regions of China using support vector machine and tree-based soft computing models with local and extrinsic climatic data. J Clean Product 2020;248:119264. [CrossRef]
• 26. Adnan RM, Liang Z, Trajkovic S, Kermani MZ, Li B, Kisi O. Daily streamflow prediction using optimally pruned extreme learning machine. J Hydro 2019;577:123981. [CrossRef]
• 27. Makridakis S, Spiliotis E, Assimakopoulos V, Chen Z, Gaba A, Tsetlin I, et al. The M5 uncertainty competition: Results, findings and conclusions. Intern J Forecast 2022;38:1365–1385. [CrossRef]
• 28. Das KS, Samui P, Sabat AK. Prediction of field hydraulic conductivity of clay liners using an artificial neural network and support vector machine. Intern J Geomech 2012;12:606–611. [CrossRef]
• 29. Deisenroth MP, Faisal AA, Ong CS. Mathematics for machine learning. 1st ed. Cambridge: Cambridge University Press; 2020. p. 398. [CrossRef]
• 30. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. data mining, inference, and prediction. 2nd ed. New York: Springer; 2009. p. 200. [CrossRef]
• 31. Bishop CM. Pattern recognition and machine learning. 2nd ed. Cambridge: Springer; 2006. p. 645–678.
• 32. Xia Y. Correlation and association analyses in microbiome study integrating multiomics in health and disease. Prog Mol Biol Transl Sci 2020;171:309–491. [CrossRef]
• 33. Berry WD. Probit/Logit and Other Binary Models. In: Leonard KK, editors. Encyclopedia of Social Measurement. New York: Elsevier; 2005. p. 161–169. [CrossRef]
• 34. Huang S. Linear regression analysis. In: Tierney RJ, Rizvi F, Ercikan K, editors. International Encyclopedia of Education. 4th ed. Oxford: Elsevier; 2023. p. 548–557. [CrossRef]
• 35. Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geosci Model Dev 2014;7:1247–1250. [CrossRef]
• 36. Tabrizi AH, Aminfar H, Mohammadpourfard M, Zonouzi SA. Bubble lift-off diameter and frequency in ferrofluid subcooled flow boiling. Heat Transf Eng 2023;44:512–529. [CrossRef]
• 37. Ross SM. Linear Regression. In: Ross SM, editor. Introductory statistics. 3rd ed. Cambridge: Academic Press; 2010. p. 537–604. [CrossRef]
• 38. Tyagi K. Regression analysis. In: Pandey R, Khatri SK, Singh NK, Verma P, editors. Artificial intelligence and machine learning for edge computing. 1st ed. Cambridge: Academic Press; 2022. p. 53–63. [CrossRef]
• 39. Schneider P, Xhafa F, Anomaly detection: Concepts and methods. In: Schneider P, Xhafa F, editors. Anomaly detection and complex event processing over IoT data streams. 1st ed. Cambridge: Academic Press; 2022. p. 49–66. [CrossRef]
• 40. Refaeilzadeh P, Tang L, Liu H. Cross-Validation. In: Liu L, Özsu MT, editors. Encyclopedia of database systems. 1st ed. Boston: Springer US; 2009. p. 532–538. [CrossRef]
• 41. Holmes G, Hall M, Prank E. Generating Rule Sets from Model Trees. In: Foo N, editor. Advanced Topics in Artificial Intelligence. 1st ed. Berlin: Springer ;1999. p. 1–12. [CrossRef]
• 42. Parke J, Holford NHG, Charles BG. A procedure for generating bootstrap samples for the validation of nonlinear mixed-effects population models. Comput Method Prog Biomed 1999;59:19–29. [CrossRef]
• 43. Efron B. Bootstrap methods: Another look at the jackknife. In: Kotz S, Johnson NL, editors. Breakthroughs in statistics: Methodology and distribution. 1st ed. New York: Springer; 1992. p. 569–593. [CrossRef]
• 44. Efron B, Gong G. A leisurely look at the bootstrap, the jackknife, and cross-validation. Am Stat 1983;37:36–48. [CrossRef]
• 45. Efron B, Tibshirani R. Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy. Statist Sci 1986;1:54–75. [CrossRef]
• 46. Efron B, Tibshirani RJ. An introduction to the bootstrap. 1st ed. New York: Chapman and Hall/CRC; 1994. p. 456. [CrossRef]
• 47. Saarela M, Jauhiainen S. Comparison of feature importance measures as explanations for classification models. SN App Sci 2021;3:272. [CrossRef]
• 48. Dalkılıç AS. A review of flow boiling in mini and microchannel for enhanced geometries. J Therm Eng 2018;4:2037–2074. [CrossRef]
• 49. Koca A, Khalajı MN, Sepahyar S. Boiling heat transfer simulation in rectangular mili-channels. J Therm Eng 2021;7:1432–1447. [CrossRef]
• 50. Basnet M, Senthılkumar D, Yuvaraj R. Mathematical modelling of evaporation rate and heating of biodiesel blends of a single-component droplets. J Therm Eng 2023;9:1572–1584. [CrossRef]
• 51. Nakhjavani SH, Zadeh MAA. Flow boiling heat transfer characteristics of titanium oxide/water nanofluid (tio2/di water) in an annular heat exchanger. J Therm Eng 2020;6:592–603. [CrossRef]