Advanced Machine Learning Driven Optimization of Radiator Heat Exchanger Performance for Automotive Applications

Articles in Press

Document Type : Research Paper

Authors
Faizan Ahmed 1 , 2
Hiren Mewada 3
Nayeemuddin Mohammed 4
1 Department of Mechanical Engineering, Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi Arabia
2 Center of Environment and Water Solutions (CEWS), Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi Arabia
3 Department of Electrical Engineering, Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi Arabia
4 Department of Civil Engineering, Prince Mohammad Bin Fahd University, Al Khobar 31952, Saudi Arabia
10.22055/jacm.2026.49435.5979
Abstract
In this research, response surface methodology (RSM) based experimental investigation coupled with three machine learning techniques namely, Bagging (Bootstrap Aggregating), Categorical Boosting (CatBoost) and Random Forest (RF) are employed to optimize and model the performance of a radiator. Model development is performed by collecting experimental data by varying hot water flow rate (0.5-2.5 l/min), cold air velocity (1-5 m/s) and feeding temperature (50-60 °C). The best radiator effectiveness was figured out to be 71.9%. The model RSM was found to be capable of predicting effectiveness with a coefficient of determination (R2) of 0.966 as compared to Bagging, CatBoost and RF techniques with an R2 of 0.99, 0.99 and 0.98, respectively. The Mean Squared Error (MSE) of Bagging, CatBoost and RF techniques were found as 6.242, 2.876 and 8.837, respectively while the Root Mean Squared Error (RMSE) for Bagging, CatBoost and RF techniques were found as 2.498, 1.696 and 2.973, respectively. The CatBoost model emerged as the best model because it had the highest coefficient of determination, along with the lowest mean square error and root mean square error. SHapley Additive exPlanations (SHAP) analysis indicated that the ML models relied most heavily on feed temperature (mean |SHAP| of 10.23, 9.65 and 6.67 for Bagging, RF and CatBoost, respectively), whereas ANOVA of the RSM model identified air velocity and water flow rate as the statistically significant factors. The reasons for this difference are discussed. This research highlights the importance of a data-driven approach to optimizing and modeling radiators.
Keywords
Optimization
Response surface methodology
Machine learning
Modeling
Radiator heat exchanger
Subjects

Publisher’s Note Shahid Chamran University of Ahvaz remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

[1] Wu, Y., Zhi, C., Wang, Z., Chen, Y., Wang, C., Chen, Q., Tan, G., Ming, T., Enhanced thermal and mechanical performance of 3D architected micro-channel heat exchangers, Heliyon, 9(3), 2023, e13902.
[2] Li, J., Su, J., Wang, S., Research on the performance of radiators in hybrid vehicle thermal management systems, World Electric Vehicle Journal, 16(2), 2025, 89.
[3] Hai, A., Patah, M.F.A., Sabri, M.A., Bharath, G., Banat, F., Daud, W.M.A.W., Advancing electrochemical water desalination: Machine learning-driven prediction and RSM optimization of activated carbon electrodes, Desalination, 597, 2025, 118401.
[4] Bargal, M.H.S., Souby, M.M., Abdelkareem, M.A.A., Sayed, M., Tao, Q., Chen, M., Wang, Y., Experimental investigation of the thermal performance of a radiator using various nanofluids for automotive PEMFC applications, International Journal of Energy Research, 45(5), 2021, 6831-6849.
[5] Yu, C., Xue, X., Shi, K., Wang, R., Zhang, L., Shao, M., Optimization of wavy fin-and-elliptical tube heat exchanger using CFD, multi-objective genetic algorithm and radical basis function, Energy Science & Engineering, 9, 2021, 1359-1372.
[6] Yu, C., Xue, X., Shi, K., Shao, M., Optimization of thermal and flow characteristics of plate heat exchanger with variable structure parameter, Journal of Thermal Analysis and Calorimetry, 147, 2022, 12617-12629.
[7] Zheng, D., Wang, J., Chen, Z., Baleta, J., Sundén, B., Performance analysis of a plate heat exchanger using various nanofluids, International Journal of Heat and Mass Transfer, 158, 2020, 119993.
[8] Liu, Z., Xu, W., Li, Z., Zhang, L., Li, J., Li, A., Feng, A., Research on heating performance of heating radiator at low temperature, Journal of Building Engineering, 36, 2021, 102016.
[9] Dzierzgowski, M., Verification and improving the heat transfer model in radiators in the wide change operating parameters, Energies, 14(20), 2021, 6543.
[10] Taler, D., Taler, J., Trojan, M., Experimental verification of an analytical mathematical model of a round or oval tube two-row car radiator, Energies, 13(13), 2020, 3399.
[11] Panchal, G.T., Nitnaware, P.T., Nanwatkar, R.K., Bansod, P.J., Comparative analysis of numerical and CFD approaches for cooling performance evaluation in tube and plate heat exchangers, SSRG International Journal of Mechanical Engineering, 12(3), 2025, 93-108.
[12] He, Z., Yu, Q., Ye, J., Yan, F., Li, Y., Optimization of plate-fin heat exchanger performance for heat dissipation of thermoelectric cooler, Case Studies in Thermal Engineering, 53, 2024, 103953.
[13] Kroulíková, T., Kudelová, T., Bartuli, E., Vancura, J., Astrouski, I., Comparison of a novel polymeric hollow fiber heat exchanger and a commercially available metal automotive radiator, Polymers, 13(7), 2021, 1175.
[14] Masood, F., Alam, M.A., Nor, N.B.M., Irshad, K., Elamvazuthi, I., Rehman, S., Akhter, J., Zayed, M.E., Modeling and optimization of thermal conductivity of synthesized MWCNT/water nanofluids using response surface methodology for heat transfer applications, Journal of Thermal Analysis and Calorimetry, 150(1), 2025, 573-584.
[15] Ahmed, F., Abdul Aziz, M.S., Mohd Arif Zainol, M.R.R., Yee, K.C., Shaik, F., Che Halin, D.S., Mohd Salleh, M.A.A., Kheimi, M., Design, modelling and optimization of a novel concentrated solar powered (CSP) flash desalination system involving direct heating and pressure modulation using response surface methodology (RSM), Sustainability, 14(18), 2022, 11558.
[16] Ahmed, F., Aziz, M.S.A., Palaniandy, P., Shaik, F., A review on application of renewable energy for desalination technologies with emphasis on concentrated solar power, Sustainable Energy Technologies and Assessments, 53, 2022, 102772.
[17] Nayeemuddin, M., Palaniandy, P., Shaik, F., Mewada, H., Experimental and computational analysis for optimization of seawater biodegradability using photo catalysis, IIUM Engineering Journal, 24(2), 2023, 11-33.
[18] Bhattacharyya, S., Sarkar, D., Roy, R., Chakraborty, S., Goel, V., Almatrafi, E., Application of new artificial neural network to predict heat transfer and thermal performance of a solar air-heater tube, Sustainability, 13(13), 2021, 7477.
[19] Alphonse, P., Muthukumarasamy, K., Elumalai, S., Kadamban, M., Dhairiyasamy, R., Optimization of heat transfer in heat pipes using nanofluids at various inclinations and filling levels, Case Studies in Thermal Engineering, 65, 2025, 105624.
[20] Xu, Q., Yang, G., Jia, S., Wang, Z., Akkurt, N., Zhang, H., Zhou, Q., Shen, M., Yang, D., Zhu, L., Liu, L., Du, Y., Xiong, Y., Experimental study on synergistic enhancement of thermal performance of a closed two-phase thermosyphon by a TiO2 nanofluid doped with Al2O3, Case Studies in Thermal Engineering, 36, 2022, 102192.
[21] Yunus, M., Alsoufi, M.S., Multi-thermal performance optimization of semi-circular heat pipes integrated with various solar collector profiles, Renewables: Wind, Water, and Solar, 8, 2021, 1.
[22] Dong, X., Knani, S., Ayed, H., Mouldi, A., Mahariq, I., Alhoee, J., Deep learning with multilayer perceptron for optimizing the heat transfer of mixed convection equipped with MWCNT-water nanofluid, Case Studies in Thermal Engineering, 57, 2024, 104309.
[23] Tafarroj, M.M., Mousavi Ajarostaghi, S.S., Ho, C.J., Yan, W., Artificial neural network approaches for predicting the heat transfer in a mini-channel heatsink with alumina/water nanofluid, Journal of Heat and Mass Transfer Research, 11(1), 2024, 75-88.
[24] Wang, Z., Zhang, H., Yin, L., Yang, D., Yang, G., Akkurt, N., Liu, D., Zhu, L., Qiang, Y., Yu, F., Xu, Q., Xiong, Y., Experimental study on heat transfer properties of gravity heat pipes in single/hybrid nanofluids and inclination angles, Case Studies in Thermal Engineering, 34, 2022, 102064.
[25] He, S., Wang, M., Zhang, J., Tian, W., Qiu, S., Su, G.H., A deep-learning reduced-order model for thermal hydraulic characteristics rapid estimation of steam generators, International Journal of Heat and Mass Transfer, 198, 2022, 123424.
[26] Amalfi, R.L., Kim, J., Machine learning-based prediction methods for flow boiling in plate heat exchangers, 20th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (iTherm), San Diego, CA, USA, 1131-1139, 2021.
[27] Esfandyari, M., Sajjadi, H., Amiri Delouei, A., GMDH and RSM models for prediction of heat transfer parameters in an ultrasonic vibrating fin-and-tube heat exchanger, International Journal of Heat and Fluid Flow, 114, 2025, 109795.
[28] Lv, J., Sun, Y., Lin, J., Luo, X., Li, P., Multi-objective optimization research of printed circuit heat exchanger based on RSM and NSGA-II, Applied Thermal Engineering, 254, 2024, 123925.
[29] Wang, Q., Zhang, S., Zhang, Y., Fu, J., Liu, Z., Enhancing performance of nanofluid mini-channel heat sinks through machine learning and multi-objective optimization of operating parameters, International Journal of Heat and Mass Transfer, 210, 2023, 124204.
[30] Zhang, T., Chen, L., Wang, J., Multi-objective optimization of elliptical tube fin heat exchangers based on neural networks and genetic algorithm, Energy, 269, 2023, 126729.
[31] McClure, E.R., Carey, V.P., Genetic algorithm and deep learning to explore parametric trends in nucleate boiling heat transfer data, ASME Journal of Heat Transfer, 143(12), 2021, 121602.
[32] Basu, A., Saha, A., Banerjee, S., Roy, P.C., Kundu, B., A review of artificial intelligence methods in predicting thermophysical properties of nanofluids for heat transfer applications, Energies, 17(6), 2024, 1351.
[33] Luo, Y., Li, G., Bennett, N.S., Luo, Z., Munir, A., Islam, M.S., Heat transfer enhancement in heat exchangers by longitudinal vortex generators: A review of numerical and experimental approaches, Energies, 18(11), 2025, 2896.
[34] Al Mahmud, S., Khan, M.R., Noor, W.I., Ismail, A.F., Momin, M.A., Bappy, J.H., Turbulent convective heat transfer enhancement modeling of water-Al2O3 nanofluid using CFD mixture model and adaptive neural fuzzy inference system, Numerical Heat Transfer, Part B: Fundamentals, 83, 2023, 120-138.
[35] Loganathan, P., Alagarsamy, S., Krishnamoorthi, S., Singh, V.K., Tiwary, R., Experimental analysis of computerized heat exchanger optimized by artificial neural network, AIP Conference Proceedings, 3042, 2024, 020043.
[36] Alazwari, M.A., Abu-Hamdeh, N.H., Salilih, E.M., Exergetic performance analysis on helically coiled tube heat exchanger-forecasting thermal conductivity of SiO2/EG nanofluid using ANN and RSM to examine effectiveness of using nanofluids, Journal of Thermal Analysis and Calorimetry, 144, 2021, 2721-2733.
[37] Sastry, G.R.K., Raju, L.B.B., Gugulothu, S.K., Agbulut, Ü., Barmavatu, P., Thermo-hydraulic optimization of rectangular duct solar air heaters using equilateral triangular roughness on absorber plates, Journal of Thermal Analysis and Calorimetry, 150, 2025, 4549-4567.
[38] Saravanan, G., Murugapoopathi, S., Muninathan, K., Experimental investigation and numerical predictions on the performance of FPSC utilizing mono and hybrid nanofluids using ANN and RSM, Journal of Thermal Analysis and Calorimetry, 150, 2025, 12777-12799.
[39] Jafarizadeh, A., Ahmadzadeh, M., Mahmoudzadeh, S., Panjepour, M., Pressure gradient computation for foams with different geometric properties: Based on ANN and SVR machine learning model and trained by CFD simulations, Journal of Porous Media, 26, 2023, 49-76.
Journal of Applied and Computational Mechanics

Articles in Press, Corrected Proof
Available Online from 27 September 2026