Isı Değiştirici Tasarım Kriterlerinin Makine Öğrenmesi Ağaç Modelleri Kullanılarak İncelenmesi

Öz

Isı değiştiriciler, kimya, otomotiv ve HVAC gibi çeşitli endüstrilerde yaygın olarak kullanılan kritik bileşenlerdir. Isı değiştirici tasarım kriterlerinin değerlendirilip iyileştirilmesi endüstriyel uygulamaların iyileştirilmesinde büyük önem arz etmektedir. Makine öğrenmesi ağaç modelleri, optimizasyon ve sınıflandırma tahminleri yoluyla küçük, orta veya büyük veri kümelerine sahip problemler için zaman alıcı sayısal çözümlere güçlü bir alternatif sunmaktadır. Bu çalışmada, ısı değiştirici tasarım kriterlerinin makine öğrenmesi ağaç modelleri kullanılarak incelenmesi ve her bir tasarım kriteri için en uygun modelin belirlenmesi amaçlanmaktadır. Sonuç olarak; ısı transfer hızı, güvenlik ve güvenilirlik tasarım kriteri için XGBoost modelinin, tip ve bakım kolaylığı tasarım kriteri için AdaBoost modelinin, maliyet ve pompa gücü tasarım kriteri için RF modelinin etkin çözümler sunabileceği değerlendirilmiştir. Gelecekte ısı değiştirici tasarım kriterlerinin farklı tip makine öğrenmesi metotları ile analiz edilerek daha maliyet etkin ısı değiştiricilerin tasarlanabileceği öngörülmüştür.

Anahtar Kelimeler

• Isı Değiştiriciler
• Makine Öğrenmesi
• Ağaç Modelleri
• Tasarım Kriteri

An Investigation on Design Criteria of Heat Exchangers by Using Tree Models of Machine Learning Methods

Öz

Heat exchangers are critical components widely used in various industries such as chemical processing, automotive, and HVAC. The evaluation and optimization of heat exchanger design criteria play a vital role in improving industrial applications. Tree-based machine learning models offer a powerful alternative to time-consuming numerical solutions by enabling optimization and classification predictions for problems involving small, medium, or large datasets. This study aims to analyze heat exchanger design criteria using tree-based machine learning models and to identify the most suitable model for each design parameter. As a result, it has been evaluated that the XGBoost model provides effective solutions for design criteria such as heat transfer rate, safety, and reliability; the AdaBoost model is more suitable for criteria such as exchanger type and ease of maintenance; and the RF model performs well for cost and pumping power. It is anticipated that in the future, analyzing heat exchanger design parameters using various machine learning approaches will enable the development of more cost-effective and efficient heat exchangers.

Anahtar Kelimeler

• Heat Exchangers
• Machine Learning
• Tree Models
• Design Criteria

Kaynakça

1. 1. Singh, A., Sahu, D. & Verma, O.P. (2023). Study on performance of working model of heat exchangers. Materials Today: Proceedings, 80, 8-13.
2. 2. Thulukkanam, K. (2000). Heat exchanger design handbook. CRC Press.
3. 3. Tang, G., Han, Y., Chen, H., Zhang, X. (2018). Design, fabrication and characterization of a mini heat exchanger for data centre cooling application. 2018 IEEE 20th Electronics Packaging Technology Conference (EPTC), 485-490.
4. 4. Pardakhe, P.P.K., Samarth, P.A.B., Bhambere, V.L. & Rathod, P.P.H. (2019). A review on basics of heat exchanger. International Research Journal of Engineering and Technology (IRJET), 6(10), 416-420.
5. 5. Hassan, A.H., Martínez-Ballester, S. & Gonzálvez-Maciá, J. (2016). Two-dimensional numerical modeling for the air-side of minichannel evaporators accounting for partial dehumidification scenarios and tube-to-tube heat conduction. International Journal of Refrigeration, 67, 90-101.
6. 6. Karaçaylı, İ., Şimşek, E., Altay, L. & Hepbaşlı, A. (2018). Experimental and analytical investigation of heat transfer coefficient of a water cooled condenser for different water flows and condensation pressures. Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 33(2), 101-112.
7. 7. Güneş, T., Şahin, M., & Kılıç, M. (2023). Investigation of the effect of different parameters of phase change materials on heat exchanger performance. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 38(4), 1117-1128.
8. 8. Fakheri, A. (2007). Heat exchanger efficiency. J Heat Transfer 129, 1268-1276.

9. 9. Ala, M., Şahin, M. & Kılıç, M. (2024). Experimental investigation of the effect of different parameters on plate and frame heat exchanger effectiveness. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi 39, 951-9.
10. 10. Habib, G., Hussain, T., Kilic, M. & Ullah, A. (2024). Development of generalized correlations for predicting density and Specific heat of nanofluids for enhanced heat transfer. Journal of Modern Nanotechnology, 4(3), 1-10.
11. 11. Ghajar, A. & Cengel, Y. (2020). Heat and mass transfer - fundamentals and applications. 6th Edition, McGraw-Hill Education, New York, NY.
12. 12. Nasteski, V. (2017). An overview of the supervised machine learning methods. Horizons. b, 4(51-62), 56.
13. 13. Sen, P.C., Hajra, M. & Ghosh, M. (2020). Supervised classification algorithms in machine learning: A survey and review. In Emerging Technology in Modelling and Graphics: Proceedings of IEM Graph, 99-111.
14. 14. Ghalandari, M., Irandoost Shahrestani, M., Maleki, A., Safdari Shadloo, M. & El Haj Assad, M. (2021). Applications of intelligent methods in various types of heat exchangers: a review. Journal of Thermal Analysis and Calorimetry, 1-12.
15. 15. Mudhsh, M., El-Said, E.M., Aseeri, A.O., Almodfer, R., Abd Elaziz, M., Elshamy, S.M. & Elsheikh, A.H. (2023). Modelling of thermo-hydraulic behavior of a helical heat exchanger using machine learning model and fire hawk optimizer. Case Studies in Thermal Engineering, 49, 103294.
16. 16. Umamaheswari, K. & Madhumathi, R. (2024). Predicting crop yield based on stacking ensemble model in machine learning. In 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud)(I-SMAC), 1831-1836, IEEE.
17. 17. Traverso, T., Coletti, F., Magri, L., Karayiannis, T.G. & Matar, O.K. (2023). A machine learning approach to the prediction of heat-transfer coefficients in micro-channels. arXiv preprint arXiv: 2305.18406.
18. 18. Zou, J., Hirokawa, T., An, J., Huang, L. & Camm, J. (2023). Recent advances in the applications of machine learning methods for heat exchanger modeling-a review. Frontiers in Energy Research, 11, 1294531.
19. 19. Boutahri, Y. & Tilioua, A. (2024). Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results in Engineering, 22, 102148.
20. 20. Tun, W., Wong, J.K.W. & Ling, S.H. (2021). Hybrid random forest and support vector machine modeling for HVAC fault detection and diagnosis. Sensors, 21(24), 8163.
21. 21. Sun, L., Wei, Q., He, L. & Yin, Z. (2020). The prediction of building heating and ventilation energy consumption base on adaboost-bp algorithm. In IOP Conference Series: Materials Science and Engineering (782), 3, 032008. IOP Publishing.
22. 22. Bian, J., Wang, J. & Yece, Q. (2024). A novel study on power consumption of an HVAC system using CatBoost and AdaBoost algorithms combined with the metaheuristic algorithms. Energy, 302, 131841.
23. 23. Chen, T. & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, 785-794.
24. 24. de Giorgio, A., Cola, G. & Wang, L. (2023). Systematic review of class imbalance problems in manufacturing. Journal of Manufacturing Systems, 71, 620-644.
25. 25. Freund, Y. & Schapire, R.E. (1996). Experiments with a new boosting algorithm. Proceedings of the Thirteenth International Conference on International Conference on Machine Learning, San Francisco, CA, USA: Morgan Kaufmann Publishers, 148-56.
26. 26. de Giorgio, A., Cola, G. & Wang, L. (2023) Systematic review of class imbalance problems in manufacturing. J Manuf Syst., 2023(71), 620-644.
27. 27. Chen, T. & Guestrin, C. (2016). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA: ACM, 785-794.
28. 28. Wang, H., Mai, D., Li, Q. & Ding, Z. (2024). Evaluating machine learning models for HVAC demand response: the impact of prediction accuracy on model predictive control performance. Buildings, 14.
29. 29. Shaeri, M.R., Ellis, M.C. & Randriambololona, A.M. (2023). Xgboost-based model for prediction of heat transfer coefficients in liquid cold plates. In ASTFE Digital Library. Begel House Inc.
30. 30. Luo, H. & Li, X. (2023). A hybrid model of CNN-BiLSTM and XGBoost for HVAC systems energy consumption prediction. In 2023 5th International Conference on Industrial Artificial Intelligence (IAI), 1-6. IEEE.
31. 31. Zhang, S., Zhu, X., Anduv, B., Jin, X. & Du, Z. (2021). Fault detection and diagnosis for the screw chillers using multi-region XGBoost model. Science and Technology for the Built Environment, 27(5), 608-623.
32. 32. Kaligambe, A., Fujita, G. & Tagami, K. (2022). Indoor room temperature and relative humidity estimation in a commercial building using the XGBoost machine learning algorithm. In 2022 IEEE PES/IAS PowerAfrica, 1-5. IEEE.
33. 33. Zheng, X., Yang, R., Wang, Q., Yan, Y., Zhang, Y., Fu, J. & Liu, Z. (2022). Comparison of GRNN and RF algorithms for predicting heat transfer coefficient in heat exchange channels with bulges. Applied Thermal Engineering, 217, 119263.
34. 34. Godasiaei, S.H. & Chamkha, A.J. (2025). Advancing heat transfer modeling through machine learning: A focus on forced convection with nanoparticles. Numerical Heat Transfer, Part A: Applications, 86(10), 3409-3431.
35. 35. Sammil, S. & Sridharan, M. (2024). Employing ensemble machine learning techniques for predicting the thermohydraulic performance of double pipe heat exchanger with and without turbulators. Thermal Science and Engineering Progress, 47, 102337.
36. 36. Zhou, L., Garg, D., Qiu, Y., Kim, S.M., Mudawar, I. & Kharangate, C.R. (2020). Machine learning algorithms to predict flow condensation heat transfer coefficient in mini/micro-channel utilizing universal data. International Journal of Heat and Mass Transfer, 162, 120351.
37. 37. Qian, N., Wang, X., Fu, Y., Zhao, Z., Xu, J. & Chen, J. (2020). Predicting heat transfer of oscillating heat pipes for machining processes based on extreme gradient boosting algorithm. Applied Thermal Engineering, 164, 114521.
38. 38. Migliore, D.F., D’Alessio, G., Caggese, S., De Martin, A., Acerra, F., Sorli, M. & Fioriti, M. (2024). Comparative Analysis of Machine Learning Algorithms for Heat Exchangers Diagnosis in Electrified Aircraft. In ICAS PROCEEDINGS. International Council of the Aeronautical Sciences.
39. 39. Zhuang, Z., Zhai, X., Ben, X., Wang, B. & Yuan, D. (2021). Accurately predicting heat transfer performance of ground-coupled heat pump system using improved autoregressive model. PeerJ Computer Science, 7, e482.