Performance evaluation of hybrid nanofluid-filled cylindrical heat pipe by machine learning algorithms

Abstract

The current study attempts to predict the outlet temperature of a hybrid nanofluid heat pipe using three machine learning models, namely Extra Tree Regression (ETR), CatBoost Re-gression (CBR), and Light Gradient Boosting Machine Regression (LGBMR), in the Python environment. Based on 7000 experimental data (various heat input, inclination angle, flow rate, and fluid ratio), different training (95%–5%) and testing (5%–95%) split sizes, a closer prediction was attained at 85:15. The three attempted machine learning models are capable of predicting the outlet temperature, as evidenced by the less than 5% deviation from the experi-mental results. Of the three attempted machine learning models, the ETR model outperforms the other two with a higher accuracy (98%). Further, the sensitivity analysis indicates the ab-sence of data overfitting in the attempted models.

Keywords

• Cylindrical Heat Pipe
• Error
• Hybrid Nanofluid
• Machine
• Learning
• Outlet Temperature
• Regression Algorithms

References

1. [1] Chi SW. Heat Pipe Theory and Practice: A Sourcebook. New York: McGraw-Hill; 1976.
2. [2] Xu Y, Xue Y, Qi H, Cai W. An updated review on working fluids, operation mechanisms, and applications of pulsating heat pipes. Renew Sust Energy Rev 2021;144:110995. [CrossRef]
3. [3] Pathak SK, Kumar R, Goel V, Pandey AK, Tyagi VV. Recent advancements in thermal performance of nano-fluids charged heat pipes used for thermal management applications: A comprehensive review. Appl Therm Eng 2022;216:119023. [CrossRef]
4. [4] Dave C, Dandale P, Shri̇vastava K, Dhaygude D, Rahangdale K, More N. A review on pulsating heat pipes: latest research, applications and future scope. J Therm Eng 2021;7:387–408. [CrossRef]
5. [5] Mehta K, Mehta N, Patel V. Experimental investigation of the thermal performance of closed loop flat plate oscillating heat pipe. Exp Heat Transf 2021;34:85–103. [CrossRef]
6. [6] Chernysheva MA, Yushakova SI, Maydanik YF. Effect of external factors on the operating characteristics of a copper–water loop heat pipe. Int J Heat Mass Transf 2015;81:297–304. [CrossRef]
7. [7] Shafieian A, Khiadani M, Nosrati A. Thermal performance of an evacuated tube heat pipe solar water heating system in cold season. Appl Therm Eng 2019;149:644–657. [CrossRef]
8. [8] Khan MN, Nadeem S. Theoretical treatment of bio-convective Maxwell nanofluid over an exponentially stretching sheet. Can J Phys 2020;98:732–741. [CrossRef]

9. [9] Nadeem S, Khan MN, Muhammad N, Ahmad S. Mathematical analysis of bio-convective micropolar nanofluid. J Comput Des Eng 2019;6:233–242. [CrossRef]
10. [10] Liang Q, Li Y, Wang Q. Experimental investigation on the performance of a neon cryogenic oscillating heat pipe. Cryogenics 2017;84:7–12. [CrossRef]
11. [11] Zhang Z, Zhao R, Liu Z, Liu W. Application of biporous wick in flat-plate loop heat pipe with long heat transfer distance. Appl Therm Eng 2021;184:116283. [CrossRef]
12. [12] Zu S, Liao X, Huang Z, Li D, Jian Q. Visualization study on boiling heat transfer of ultra-thin flat heat pipe with single layer wire mesh wick. Int J Heat Mass Transf 2021;173:121239. [CrossRef]
13. [13] Martin K, Sözen A, Çiftçi E, Ali HM. An experimental investigation on aqueous Fe–CuO hybrid nanofluid usage in a plain heat pipe. Int J Thermophys 2020;41:135. [CrossRef]
14. [14] Chabani I, Mebarek-Oudina F, Vaidya H, Ismail AI. Numerical analysis of magnetic hybrid nano-fluid natural convective flow in an adjusted porous trapezoidal enclosure. J Magn Magn Mater 2022;564:170142. [CrossRef]
15. [15] Mebarek-Oudina F. Convective heat transfer of Titania nanofluids of different base fluids in cylindrical annulus with discrete heat source. Heat Transf—Asian Res 2019;48:135–147. [CrossRef]
16. [16] Mebarek-Oudina F, Preeti, Sabu AS, Vaidya H, Lewis RW, Areekara S, et al. Hydromagnetic flow of magnetite–water nanofluid utilizing adapted Buongiorno model. Int J Mod Phys B 2023:2450003. [CrossRef]
17. [17] Pandya NS, Desai AN, Kumar Tiwari A, Said Z. Influence of the geometrical parameters and particle concentration levels of hybrid nanofluid on the thermal performance of axial grooved heat pipe. Therm Sci Eng Prog 2021;21:100762. [CrossRef]
18. [18] Bumataria RK, Chavda NK, Nalbandh AH. Performance evaluation of the cylindrical shaped heat pipe utilizing water-based CuO and ZnO hybrid nanofluids. Energy Source Part A 2020;0:1–16. [CrossRef]
19. [19] Mebarek-Oudina F, Chabani I. Review on nano-fluids applications and heat transfer enhancement techniques in different enclosures. J Nanofluids 2022;11:155–168. [CrossRef]
20. [20] Dharmaiah G, Mebarek-Oudina F, Sreenivasa Kumar M, Chandra Kala K. Nuclear reactor application on Jeffrey fluid flow with Falkner-skan factor, Brownian and thermophoresis, non linear thermal radiation impacts past a wedge. J Indian Chem Soc 2023;100:100907. [CrossRef]
21. [21] Khan MN, Nadeem S, Muhammad N. Micropolar fluid flow with temperature-dependent transport properties. Heat Transf 2020;49:2375–2389. [CrossRef]
22. [22] Ahmad S, Nadeem S, Muhammad N, Khan MN. Cattaneo–Christov heat flux model for stagnation point flow of micropolar nanofluid toward a nonlinear stretching surface with slip effects. J Therm Anal Calorim 2021;143:1187–1199. [CrossRef]
23. [23] Ahmad S, Khan MN, Nadeem S. Mathematical analysis of heat and mass transfer in a Maxwell fluid with double stratification. Phys Scr 2020;96:025202. [CrossRef]
24. [24] Khan MN, Ullah N, Nadeem S. Transient flow of Maxwell nanofluid over a shrinking surface: numerical solutions and stability analysis. Surf Interface 2021;22:100829. [CrossRef]
25. [25] Khan MN, Nadeem S, Ullah N, Saleem A. Theoretical treatment of radiative Oldroyd-B nanofluid with microorganism pass an exponentially stretching sheet. Surf Interface 2020;21:100686. [CrossRef]
26. [26] Ahmad MW, Reynolds J, Rezgui Y. Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. J Clean Prod 2018;203:810–821. [CrossRef]
27. [27] Xiang W, Xu P, Fang J, Zhao Q, Gu Z, Zhang Q. Multi-dimensional data-based medium- and long-term power-load forecasting using double-layer CatBoost. Energy Rep 2022;8:8511–22. [CrossRef]
28. [28] Gong M, Bai Y, Qin J, Wang J, Yang P, Wang S. Gradient boosting machine for predicting return temperature of district heating system: A case study for residential buildings in Tianjin. J Build Eng 2020;27:100950. [CrossRef]
29. [29] Dong B, Xue N, Mu G, Wang M, Xiao Z, Dai L, et al. Synthesis of monodisperse spherical AgNPs by ultrasound-intensified Lee-Meisel method, and quick evaluation via machine learning. Ultrason Sonochem 2021;73:105485. [CrossRef]
30. [30] Sakthivadivel D, Ganesh Kumar P, Prabakaran R, Vigneswaran VS, Nithyanandhan K, Kim SC. A neem oil-based biodiesel with DEE enriched ethanol and Al2O3 nano additive: An experimental investigation on the diesel engine performance. Case Stud Therm Eng 2022;34:102021. [CrossRef]
31. [31] Heddam S, Ptak M, Zhu S. Modelling of daily lake surface water temperature from air temperature: Extremely randomized trees (ERT) versus Air2Water, MARS, M5Tree, RF and MLPNN. J Hydrol 2020;588:125130. [CrossRef]
32. [32] Abdurakipov SS, Kiryukhina NV, Butakov EB. Prediction of boiling crisis in channels using machine learning algorithms. Optoelect Instrument Data Process 2022;58:98–108. [CrossRef]
33. [33] Chun P, Izumi S, Yamane T. Automatic detection method of cracks from concrete surface imagery using two-step light gradient boosting machine. Comput-Aided Civ Inf 2021;36:61–72. [CrossRef]
34. [34] Chavda N, Bumataria R. Effect of particle size and concentration on thermal performance of cylindrical shaped heat pipe using silver-DI water nanofluid. Int J Ambient Energy 2023;44:305–316. [CrossRef]
35. [35] Ali B, Qayoum A, Saleem S, Mir FQ. Experimental investigation of nanofluids for heat pipes used in solar photovoltaic panels. J Therm Eng 2023:439–456. [CrossRef]
36. [36] Yang W, Shen P, Ye Z, Zhu Z, Xu C, Liu Y, et al. Adversarial training collaborating multi-path context feature aggregation network for maize disease density prediction. Processes 2023;11:1132. [CrossRef]
37. [37] Khan MN, Nadeem S. A comparative study between linear and exponential stretching sheet with double stratification of a rotating Maxwell nanofluid flow. Surf Interface 2021;22:100886. [CrossRef]
38. [38] Khan U, Mebarek-Oudina F, Zaib A, Ishak A, Abu Bakar S, Sherif E-SM, et al. An exact solution of a Casson fluid flow induced by dust particles with hybrid nanofluid over a stretching sheet subject to Lorentz forces. Waves Random Complex Media 2022:1–14. [CrossRef]
39. [39] Nadeem S, Khan MN, Abbas N. Transportation of slip effects on nanomaterial micropolar fluid flow over exponentially stretching. Alex Eng J 2020;59:3443–3450. [CrossRef]
40. [40] Shafiq A, Mebarek-Oudina F, Sindhu TN, Rasool G. Sensitivity analysis for Walters-B nanoliquid flow over a radiative Riga surface by RSM. Sci Iran 2022;29:1236–1249. [CrossRef]
41. [41] Singh U, Gupta NK. Thermal performance analysis of heat pipe using response surface methdologyUdayvir. J Therm Eng 2023:411–423. [CrossRef]