Forecasting the energy efficiency of an earth-air heat exchanger with integrated twisted tabs using machine learning techniques
DOI:
https://doi.org/10.24425/ather.2025.156584Abstract
This study investigates the potential of machine learning models as efficient alternatives to traditional computational methods for evaluating the performance of earth-air heat exchanger systems. A validated numerical model was used to simulate system behaviour under varying parameters, including soil type, pipe material, number of internal twisted tabs and outlet temperature. Based on these simulations, a dataset comprising 216 entries was generated to train three machine learning models: support vector regression, gradient boosting and decision trees. The gradient boosting model achieved the highest predictive accuracy, with a root mean square error of 0.0188 and a mean absolute error of 0.0138. Support vector regression and decision trees also demonstrated strong performance, with prediction accuracies of 97% and 96%, respectively. Additionally, the proposed earth-air heat exchanger design with twisted tabs showed superior thermal performance compared to the conventional configuration. Over extended operation, the temperature difference between inlet and outlet exceeded 7°C, with the new configuration system incorporating 10 tabs yielding optimal performance. This configuration led to more than a 10% improvement in thermal efficiency and an increase of approximately 25% in the heat transfer coefficient. These results confirm that integrating machine learning with advanced earth-air heat exchanger designs offers a reliable and computationally efficient approach for enhancing system performance.References
[1] Alrwashdeh, S.S., Ammari, H., Madanat, M.A., & Al-Falahat, A.M. (2022). The Effect of Heat Exchanger Design on Heat Transfer Rate and Temperature Distribution. Emerging Science Journal, 6(1), 128–137. doi: 10.28991/esj-2022-06-01-010
[2] Bejan, A., Alalaimi, M., Lorente, S., Sabau, A., & Klett, J. (2016). Counterflow heat exchanger with core and plenums at both ends. International Journal of Heat and Mass Transfer, 99, 622–629. doi: 10.1016/j.ijheatmasstransfer.2016.03.117
[3] Kareem, Z.S., Jaafar, M.M., Lazim, T.M., Abdullah, S., & Abdulwahid, A.F. (2015). Passive heat transfer enhancement review in corrugation. Experimental Thermal and Fluid Science, 68, 22–38. doi: 10.1016/j.expthermflusci.2015.04.012
[4] Liu, S., & Sakr, M. (2013). A comprehensive review on passive heat transfer enhancements in pipe exchangers. Renewable and Sustainable Energy Reviews, 19, 64–81. doi: 10.1016/j.rser.2012.11.021
[5] Aziz, A., & Rehman, S. (2020). Analysis of non-equidistant baffle spacing in a small shell and tube heat exchanger. Archives of Thermodynamics, 41(2), 201–221. doi: 10.24425/ather.2020.133629
[6] Muszyński, T., & Dorao, A. (2019). Heat transfer and pressure drop characteristics of the silicone-based plate heat exchanger. Archives of Thermodynamics, 40(1), 127–143. doi: 10.24425/ather.2019.128294
[7] Serrao, P., Pawase, H., Prakash, A., & Pandita, V. (2017). Comparison of overall heat transfer coefficient in plain and corrugated pipe and its CFD analysis. International Journal of Advances in Engineering & Technology, 10(4), 523–540.
[8] Vignesh, S., Moorthy, V.S., & Nallakumarasamy, G. (2017). Experimental and CFD analysis of concentric dimple tube heat exchanger. International Journal of Emerging Technologies in Engineering Research (IJETER), 5(7), 18–26.
[9] Wang, Z., Wang, Y., Zhang, J., Li, S., & Xu, Y. (2022). Numerical simulation of heat transfer performance of a dimpled tubular heat exchanger. Applied Sciences, 12(24), 12965. doi: 10.3390/app122412965
[10] Kumar, P.M., & Chandrasekar, M. (2019). CFD analysis on heat and flow characteristics of double helically coiled tube heat exchanger handling MWCNT/water nanofluids. Heliyon, 5(7), e02030. doi: 10.1016/j.heliyon.2019.e02030
[11] Khan, A., Shah, I., Gul, W., Khan, T.A., Ali, Y., & Masood, S.A. (2023). Numerical and experimental analysis of shell and tube heat exchanger with round and hexagonal tubes. Energies, 16(2), 880. doi: 10.3390/en16020880
[12] Kishan, R., Singh, D., & Sharma, A.K. (2020). CFD analysis of heat exchanger models design using Ansys Fluent. International Journal of Mechanical Engineering and Technology, 11(2), 1–9. doi: 10.34218/IJMET.11.2.2020.001
[13] Sharma, S., Sharma, S., Singh, M., Singh, P., Singh, R., Maharana, S., Khalilpoor, N., & Issakhov, A. (2021). Computational fluid dynamics analysis of flow patterns, pressure drop, and heat transfer coefficient in staggered and inline shell-tube heat exchangers. Mathematical Problems in Engineering, 2021, 6645128. doi: 10.1155/2021/6645128
[14] Rahimi, M., Shabanian, S.R., & Alsairafi, A.A. (2009). Experimental and CFD studies on heat transfer and friction factor characteristics of a tube equipped with modified twisted tape inserts. Chemical Engineering and Processing – Process Intensification, 48(3), 762–770. doi: 10.1016/j.cep.2008.09.07
[15] Larwa, B., & Kupiec, K. (2020). Principles of modelling of slinky-coil ground heat exchangers. Chemical and Process Engineering – New Frontiers, 41(2). doi: 10.24425/cpe.2019.130225
[16] Molcrette, V., & Autier, V. (2020). New expression to calculate quantity of recovered heat in the earth-pipe-air heat-exchanger operating in winter heating mode. Archives of Thermodynamics, 41(2), 103–117. doi: 10.24425/ather.2020.133624
[17] Ahmad, S.N., & Prakash, O. (2022). Thermal performance evaluation of an earth-to-air heat exchanger for heating mode applications using an experimental test rig. Archives of Thermodynamics, 43(1), 185–207. doi: 10.24425/ather.2022.140931
[18] Suenaga, D., Takase, Y., Abe, T., Orita, G., & Ando, S. (2023). Prediction accuracy of machine learning methods for shear resistance of post-installed anchors. Structures, 50, 1252–1263. doi: 10.1016/j.istruc.2023.02.066
[19] Huang, J., Jin, T., Liang, M., & Chen, H. (2021). Prediction of heat exchanger performance by support vector machine. Applied Thermal Engineering, 182, 116053. doi: 10.1016/j.applthermaleng.2020.116053
[20] Celik, N., Tasar, B., Kapan, S., & Tanyildizi, V. (2023). Performance optimization of a heat exchanger with turbulator insert using machine learning. International Journal of Thermal Sciences, 192, 108439. doi: 10.1016/j.ijthermalsci.2023.108439
[21] Karami, A., Rezaei, E., Rahimi, M., & Zanjani, M. (2012). Artificial neural modeling of heat transfer in an air cooled heat exchanger equipped with butterfly inserts. International Energy Journal, 13, 21–28.
[22] Li, Z., Shao, L., & Zhang, C. (2016). Modeling of finned-tube evaporator using neural network and response surface methodology. Journal of Heat Transfer, 138(5), 051502. doi: 10.1115/1.4032358
[23] Shojaeefard, M.H., Zare, J., Tabatabaei, A., & Mohammadbeigi, H. (2017). Evaluating artificial neural network structures for performance prediction of compact heat exchanger. Neural Computing and Applications, 28(12), 3953–3965. doi: 10.1007/s00521-016-2302-z
[24] Deb, D., Rajan, H., Kundu, R., & Mohan, R. (2021). CFD and machine learning-based simulation of flow and heat transfer characteristics. IOP Conference Series Earth and Environmental Science, 850(1), 012034. doi: 10.1088/1755-1315/850/1/012034
[25] Liao, T., Zhao, C., Wang, H., & Ju, S. (2024). Data-driven design of multilayer hyperbolic metamaterials. International Journal of Heat and Mass Transfer, 219, 124831. doi: 10.1016/j.ijheatmasstransfer.2023.124831
[26] Ren, F., Zhang, F., Zhu, Y., Wang, Z., & Zhao, F. (2024). Enhancing heat transfer from a circular cylinder using reinforcement learning. Applied Thermal Engineering, 236, 121919. doi: 10.1016/j.applthermaleng.2023.121919
[27] Wang, C., & Vafai, K. (2024). Heat transfer enhancement for 3D chip thermal simulation. Applied Thermal Engineering, 236, 121499. doi: 10.1016/j.applthermaleng.2023.121499
[28] Çolak, A.B., Açıkgöz, Ö., Mercan, H., Dalkılıç, A.S., & Wongwises, S. (2022). Prediction of parameters of double-pipe heat exchangers using ANN. Case Studies in Thermal Engineering, 39, 102391. doi: 10.1016/j.csite.2022.102391
[29] Çolak, A.B., Mercan, H., Açıkgöz, Ö., Dalkılıç, A.S., & Wongwises, S. (2023). Prediction of nanofluid flows using ANN. Kerntechnik, 88(1), 100–113. doi: 10.1515/kern-2022-0097
[30] Colak, A.B., Akgul, D., Mercan, H., Dalkılıç, A.S., & Wongwises, S. (2023). Estimation of heat transfer parameters using machine learning. Case Studies in Thermal Engineering, 42, 102713. doi: 10.1016/j.csite.2023.102713
[31] Çolak, A.B., Kirkar, S.M., Gönül, A., & Dalkilic, A.S. (2024). Assessment of corrugated heat exchanger characteristics using ANN. International Journal of Heat and Fluid Flow, 108, 109455. doi: 10.1016/j.ijheatfluidflow.2024.109455
[32] Bansal, V., Misra, R., Agrawal, G.D., & Mathur, J. (2010). Performance analysis of earth–pipe–air heat exchanger for cooling. Energy and Buildings, 42(5), 645–648. doi: 10.1016/j.enbuild.2009.11.001
[33] ANSYS Inc. (2020). ANSYS CFX User’s Guide, Release 2020 R2. Canonsburg, USA.
[34] Patankar, S. (2018). Numerical Heat Transfer and Fluid Flow. CRC Press.
[35] Versteeg, H.K., & Malalasekera, W. (2007). An Introduction to Computational Fluid Dynamics. Pearson.
[36] Wilcox, D.C. (1998). Turbulence Modeling for CFD. DCW Industries.
[37] Vu, A.T., Gulati, S., Vogel, P., Grunwald, T., & Bergs, T. (2021). Machine learning-based modeling of heat transfer. International Journal of Heat and Mass Transfer, 174, 121300.
[38] Chen, X., et al. (2023). Machine learning and numerical algorithms. Mathematics, 11(21), 4418.
[39] Maharana, K., Mondal, S., & Nemade, B. (2022). Data preprocessing techniques. Global Transitions Proceedings, 3(1), 91–99.
[40] Pandey, Y.N., et al. (2020). Machine Learning in the Oil and Gas Industry. Apress.
[41] Jiang, J., et al. (2020). Multitask deep learning for datasets. Journal of Chemical Information and Modeling, 60(3), 1235–1244.
[42] Lubke, G., et al. (2013). Gradient boosting as SNP filter. Journal of Data Mining in Genomics & Proteomics, 4(4).
[43] Cha, G., Moon, H., & Kim, Y. (2021). Random forest vs gradient boosting. IJERPH, 18(16), 8530.
[44] Bouke, M.A., et al. (2023). DDoS detection model. Microprocessors and Microsystems, 98.
[45] Chai, T., & Draxler, R.R. (2014). RMSE vs MAE. Geoscientific Model Development, 7(1), 1525–1534.
[46] Willmott, C., & Matsuura, K. (2005). MAE advantages. Climate Research, 30(1), 79–82.
[47] Nash, J., & Sutcliffe, J. (1970). River flow forecasting. Journal of Hydrology, 10(3), 282–290.
[48] Gong, M., et al. (2020). Gradient boosting for district heating. Journal of Building Engineering, 27, 100950.
