An artificial neural network-based numerical estimation of the boiling pressure drop of different refrigerants flowing in smooth and micro-fin tubes

Andaç Batur Çolak; Aykut Bacak; Nurullah Kayaci; Ahmet Selim Dalkilic

doi:10.1515/kern-2023-0087

Artikel

An artificial neural network-based numerical estimation of the boiling pressure drop of different refrigerants flowing in smooth and micro-fin tubes

Andaç Batur Çolak , Aykut Bacak , Nurullah Kayaci und Ahmet Selim Dalkilic

Veröffentlicht/Copyright: 29. Januar 2024

Veröffentlicht von

Veröffentlichen auch Sie bei De Gruyter Brill

Manuskript einreichen Informationen für Autor*innen

Aus der Zeitschrift Kerntechnik Band 89 Heft 1

Abstract

In thermal engineering implementations, heat exchangers need to have improved thermal capabilities and be smaller to save energy. Surface adjustments on tube heat exchanger walls may improve heat transfer using new manufacturing technologies. Since quantifying enhanced tube features is quite difficult due to the intricacy of fluid flow and heat transfer processes, numerical methods are preferred to create efficient heat exchangers. Recently, machine learning algorithms have been able to analyze flow and heat transfer in improved tubes. Machine learning methods may increase heat exchanger efficiency estimates using data. In this study, the boiling pressure drop of different refrigerants in smooth and micro-fin tubes is predicted using an artificial neural network-based machine learning approach. Two different numerical models are built based on the operating conditions, geometric specifications, and dimensionless numbers employed in the two-phase flows. A dataset including 812 data points representing the flow of R12, R125, R134a, R22, R32, R32/R134a, R407c, and R410a through smooth and micro-fin pipes is used to evaluate feed-forward and backward propagation multi-layer perceptron networks. The findings demonstrate that the neural networks have an average error margin of 10 percent when predicting the pressure drop of the refrigerant flow in both smooth and micro-fin tubes. The calculated R-values for the artificial neural network’s supplementary performance factors are found above 0.99 for all models. According to the results, margins of deviations of 0.3 percent and 0.05 percent are obtained for the tested tubes in Model 1, while deviations of 0.79 percent and 0.32 percent are found for them in Model 2.

Keywords: artificial neural network; machine learning; micro-fin tube; pressure drop; two-phase flow

Corresponding author: Andaç Batur Çolak, Information Technologies Application and Research Center, Istanbul Ticaret University, Istanbul 34445, Türkiye, E-mail: abcolak@ticaret.edu.tr

Acknowledgments

This paper used NIST’s data, including Choi et al. (1999) and Eckels and Pate (1991) experimental data, which were presented in Choi et al. (1999) study provided by NIST. The authors wish to thank them for their contributions to the subject of in-tube, two-phase flow.

Research ethics: Not applicable.
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Competing interests: The authors states no conflict of interest.
Research funding: None declared.
Data availability: Not applicable.

Nomenclature

Bo: bond number
Cp_l: specific heat capacity, kJ/kgK
D: tube inside diameter, m
Fr: Froude number
g: gravitational acceleration, m/s²
G: mass flux, kg/m² s
h _lg: enthalpy of evaporation, kJ/kg
k _l: liquid thermal conductivity, kW/mK
P _avg: average saturation pressure, kPa
Pr_l: liquid Prandtl number
R: coefficient of determination
Re_l: liquid Reynolds number
Re_g: gas Reynolds number
u: fluid velocity, m/s
x _avg: average vapor quality
X: variable
X _tt: Martinelli parameter
µ _l: liquid dynamic viscosity, kN/ms²
µ _g: gas dynamic viscosity, kN/ms²
ρ: density, kg/m³
ρ _l: liquid density, kg/m³
ρ _g: vapor density, kg/m³
ρ _tp: two-phase density, kg/m³
σ: surface tension, kN/m
α: Void fraction
ΔP: pressure drop, kPa

Abbreviations

AARE: acceptable average absolute relative error
ANN: artificial neural network
ANFIS: artificial neural fuzzy inference system
BP: back propagation
DNN: deep neural network
GRNN: generalized regression neural networks
HEX: heat exchangers
HTC: heat transfer coefficient
MAE: mean absolute error
MAPE: mean absolute percentage error
MARD: mean absolute relative deviation
MoD: margin of variation, %
MRE: mean relative error
MSE: mean squared error
MLP: multi-layer perceptron
MRA: multiple regression analysis
XGBoost: extreme gradient boosting

References

Ardam, K., Najafi, B., Lucchini, A., Rinaldi, F., and Colombo, L.P.M. (2021). Machine learning based pressure drop estimation of evaporating R134a flow in micro-fin tubes: investigation of the optimal dimensionless feature set. Int. J. Refrig. 131: 20–32, https://doi.org/10.1016/j.ijrefrig.2021.07.018.Suche in Google Scholar

Awad, M.M. and Muzychka, Y.S. (2008). Effective property models for homogeneous two-phase flows. Exp. Therm. Fluid Sci. 33: 106–113, https://doi.org/10.1016/j.expthermflusci.2008.07.006.Suche in Google Scholar

Balcilar, M., Dalkilic, A.S., Agra, O., Atayilmaz, S.O., and Wongwises, S. (2012). A correlation development for predicting the pressure drop of various refrigerants during condensation and evaporation in horizontal smooth and micro-fin tubes. Int. Commun. Heat Mass Transfer 39: 937–944, https://doi.org/10.1016/j.icheatmasstransfer.2012.05.005.Suche in Google Scholar

Balcilar, M., Aroonrat, K., Dalkilic, A.S., and Wongwises, S. (2013). A generalized numerical correlation study for the determination of pressure drop during condensation and boiling of R134a inside smooth and corrugated tubes. Int. Commun. Heat Mass Transfer 49: 78–85, https://doi.org/10.1016/j.icheatmasstransfer.2013.08.010.Suche in Google Scholar

Bard, A., Qiu, Y., Kharangate, C.R., and French, R. (2022). Consolidated modeling and prediction of heat transfer coefficients for saturated flow boiling in mini/micro-channels using machine learning methods. Appl. Therm. Eng. 210: 118305, https://doi.org/10.1016/j.applthermaleng.2022.118305.Suche in Google Scholar

Barroso-Maldonado, J.M., Montañez-Barrera, J.A., Belman-Flores, J.M., and Aceves, S.M. (2019). ANN-based correlation for frictional pressure drop of non-azeotropic mixtures during cryogenic forced boiling. Appl. Therm. Eng. 149: 492–501, https://doi.org/10.1016/j.applthermaleng.2018.12.082.Suche in Google Scholar

Choi, J.Y., Kedzierski, M.A., and Domański, P. (1999). A generalized pressure drop correlation for evaporation and condensation of alternative refrigerants in smooth and micro-fin tubes, Vol. 10. US Department of Commerce, Technology Administration, National Institute of Standards and Technology, Building and Fire Research Laboratory, Gaithersburg.10.6028/NIST.IR.6333Suche in Google Scholar

Cicchitti, A., Lombardi, C., Silvestri, M., Soldaini, G., and Zavattarelli, R. (1959). Two-phase cooling experiments: pressure drop, heat transfer and burnout measurements (No. CISE-71). Centro Informazioni Studi Esperienze, Milan.Suche in Google Scholar

Çolak, A.B. (2021a). An experimental study on the comparative analysis of the effect of the number of data on the error rates of artificial neural networks. Int. J. Energy Res. 45: 478–500, https://doi.org/10.1002/er.5680.Suche in Google Scholar

Çolak, A.B. (2021b). A novel comparative investigation of the effect of the number of neurons on the predictive performance of the artificial neural network: an experimental study on the thermal conductivity of ZrO2 nanofluid. Int. J. Energy Res. 45: 18944–18956, https://doi.org/10.1002/er.6989.Suche in Google Scholar

Çolak, A.B., Celen, A., and Dalkılıç, A.S. (2022). Numerical determination of condensation pressure drop of various refrigerants in smooth and micro-fin tubes via ANN method. Kerntechnik 87: 506–519, https://doi.org/10.1515/kern-2022-0037.Suche in Google Scholar

Dalkilic, A.S. (2011). Condensation pressure drop characteristics of various refrigerants in a horizontal smooth tube. Int. Commun. Heat Mass Transfer 38: 504–512, https://doi.org/10.1016/j.icheatmasstransfer.2010.12.029.Suche in Google Scholar

Eckels, S.J. and Pate, M.B. (1991). In-tube evaporation and condensation of refrigerant-lubricant mixtures of HFC-134a and CFC-12. ASHRAE Trans. 97: 62–67, https://doi.org/10.31274/rtd-180813-11226.Suche in Google Scholar

Kandlikar, S.G. (2019). Handbook of phase change: boiling and condensation. Routledge, London, UK.10.1201/9780203752654Suche in Google Scholar

Liang, X., Xie, Y., Day, R., Meng, X., and Wu, H. (2021). A data driven deep neural network model for predicting boiling heat transfer in helical coils under high gravity. Int. J. Heat Mass Transfer 166: 120743, https://doi.org/10.1016/j.ijheatmasstransfer.2020.120743.Suche in Google Scholar

Lin, L., Gao, L., Kedzierski, M.A., and Hwang, Y. (2020). A general model for flow boiling heat transfer in micro-fin tubes based on a new neural network architecture. Energy AI 8: 100151, https://doi.org/10.1016/j.egyai.2022.100151.Suche in Google Scholar

Lockhart, W.R. (1949). Proposed correlation of data for isothermal two-phase, two-component flow in pipes. Chem. Eng. Prog. 45: 39–48.Suche in Google Scholar

Mehdi, S., Nannapaneni, S., and Hwang, G. (2022). Structural-material-operational performance relationship for pool boiling on enhanced surfaces using deep neural network model. Int. J. Heat Mass Transfer 198: 123395, https://doi.org/10.1016/j.ijheatmasstransfer.2022.123395.Suche in Google Scholar

Montañez-Barrera, J.A., Barroso-Maldonado, J.M., Bedoya-Santacruz, A.F., and Mota-Babiloni, A. (2022). Correlated-informed neural networks: a new machine learning framework to predict pressure drop in micro-channels. Int. J. Heat Mass Transfer 194: 123017, https://doi.org/10.1016/j.ijheatmasstransfer.2022.123017.Suche in Google Scholar

Moradkhani, M.A., Hosseini, S.H., and Karami, M. (2022). Forecasting of saturated boiling heat transfer inside smooth helically coiled tubes using conventional and machine learning techniques. Int. J. Refrig. 143: 78–93, https://doi.org/10.1016/j.ijrefrig.2022.06.036.Suche in Google Scholar

Najafi, B., Ardam, K., Hanušovský, A., Rinaldi, F., and Colombo, L.P.M. (2021). Machine learning based models for pressure drop estimation of two-phase adiabatic air-water flow in micro-finned tubes: determination of the most promising dimensionless feature set. Chem. Eng. Res. Des. 167: 252–267, https://doi.org/10.1016/j.cherd.2021.01.002.Suche in Google Scholar

Nie, F., Yan, S., Wang, H., Zhao, C., Zhao, Y., and Gong, M. (2023). A universal correlation for predicting two-phase frictional pressure drop in horizontal tubes based on machine learning. Int. J. Multiphase Flow 160: 104377, https://doi.org/10.1016/j.ijmultiphaseflow.2022.104377.Suche in Google Scholar

Öcal, S., Gökçek, M., Çolak, A.B., and Korkanç, M. (2021). A comprehensive and comparative experimental analysis on thermal conductivity of TiO2-CaCO 3/Water hybrid nanofluid: proposing new correlation and artificial neural network optimization. Heat Transfer Res. 52: 55–79, https://doi.org/10.1615/HeatTransRes.2021039444.Suche in Google Scholar

Qiu, Y., Garg, D., Kim, S.M., Mudawar, I., and Kharangate, C.R. (2021). Machine learning algorithms to predict flow boiling pressure drop in mini/micro-channels based on universal consolidated data. Int. J. Heat Mass Transfer 178: 121607, https://doi.org/10.1016/j.ijheatmasstransfer.2021.121607.Suche in Google Scholar

Qiu, Y., Vo, T., Garg, D., Lee, H., and Kharangate, C.R. (2023). A systematic approach to optimization of ANN model parameters to predict flow boiling heat transfer coefficient in mini/micro-channel heatsinks. Int. J. Heat Mass Transfer 202: 123728, https://doi.org/10.1016/j.ijheatmasstransfer.2022.123728.Suche in Google Scholar

Reddy, D.R., Bhramara, P., and Govindarajulu, K. (2020). A Comparative Study of Multiple Regression and Artificial Neural Network models for a domestic refrigeration system with a hydrocarbon refrigerant mixtures. Mater. Today: Proc. 22: 1545–1553, https://doi.org/10.1016/j.matpr.2020.02.116.Suche in Google Scholar

Soleimani, S., Eckels, S., and Campbel, M. (2022). Parametric study and application of a data-mining model in 2D and 3D micro-fin tubes. Appl. Therm. Eng. 207: 118165, https://doi.org/10.1016/j.applthermaleng.2022.118165.Suche in Google Scholar

Stephan, K. (1992). Heat transfer in condensation and boiling, Vol. 1. Springer-Verlag, Berlin, p. 84.10.1007/978-3-642-52457-8Suche in Google Scholar

Sun, L. and Mishima, K. (2008). Evaluation analysis of prediction methods for two-phase flow pressure drop in mini-channels. In: Int. Conf. on Nucl. Eng., Vol. 48159, pp. 649–65.10.1115/ICONE16-48210Suche in Google Scholar

Zhao, X., Shirvan, K., Salko, R.K., and Guo, F. (2020). On the prediction of critical heat flux using a physics-informed machine learning-aided framework. Appl. Therm. Eng. 164: 114540, https://doi.org/10.1016/j.applthermaleng.2019.114540.Suche in Google Scholar

Zhu, G., Wen, T., and Zhang, D. (2021). Machine learning based approach for the prediction of flow boiling/condensation heat transfer performance in mini channels with serrated fins. Int. J. Heat Mass Transfer 166: 120783, https://doi.org/10.1016/j.ijheatmasstransfer.2020.120783.Suche in Google Scholar

Received: 2023-08-25

Accepted: 2023-12-15

Published Online: 2024-01-29

Published in Print: 2024-02-26

Sie haben derzeit keinen Zugang zu diesem Inhalt.

Artikel in diesem Heft

https://doi.org/10.1515/kern-2023-0087

Schlagwörter für diesen Artikel

artificial neural network; machine learning; micro-fin tube; pressure drop; two-phase flow