Pace Regresyon Algoritması İle Kaynama Isı Transferinde Isı Akısının Modellenmesi

Yıl 2020, Ejosat Özel Sayı 2020 (ISMSIT), 43 - 49, 30.11.2020

Erdem Alıç Mehmet Daş

https://doi.org/10.31590/ejosat.819017

Öz

Küçük sıcaklık farkları ile yüksek miktarda enerji dönüşümüne imkân sağlayan kaynama ısı transferi, buhar kazanları, ısı değiştiricileri, enerji sistemleri ve nükleer santral reaktörleri gibi birçok alanda araştırılmaktadır. Bu çalışmada daha önce deneysel olarak çalışılmış silindirik metal yüzey üzerinde izole buhar kabarcığı bölgesinde gerçekleşen kaynama ısı transferi incelenmiştir. Yüzey malzemesi olarak pürüzsüz çelik seçilmiştir. Deneysel verilerle hesaplanmış metal malzemenin yüzeyinde gerçekleşen havuz kaynama ısı transferi sonucu ortaya çıkan ısı akısı değerleri, bir makine öğrenmesi algoritması olan Pace regresyon algoritması ile ilk kez modellenmiştir. Pace regresyonda 2 farklı metot sonucu üretilen veriler ile deneyler sonucunda elde edilen veriler karşılaştırılmıştır. Çelik malzeme için 0.132 (RAE) hata oranı ile ısı akısı başarılı bir şekilde PG algoritması OLS metodu tarafından modellenmiştir.

Anahtar Kelimeler

Havuz kaynama, Isı transferi, Isı akısı, Pace regresyon

Modeling of Heat Flux in Boiling Heat Transfer with Pace Regression Algorithm

Öz

Boiling heat transfer, which allows a large amount of energy conversion with small temperature differences, has been investigated in many areas such as steam boilers, heat exchangers, energy systems and nuclear power plant reactors. In this study, the boiling heat transfer occurring in the isolated vapor bubble region on the cylindrical metal surface, which was experimentally studied before, was investigated. Smooth steel has been chosen as the surface material. The heat flux values resulting from pool boiling heat transfer on the surface of the metal material calculated with experimental data were modeled for the first time with the Pace regression algorithm, which is a machine learning algorithm. The data obtained as a result of 2 different methods in pace regression were compared with the data obtained from the experiments. With an error rate of 4.06 (RMSE) for steel, the heat flux was successfully modeled by the PG algorithm OLS method.

Anahtar Kelimeler

Pool boiling, Heat transfer, Heat flux, Pace regresyon

Kaynakça

• G. Su et al., “Applications of artificial neural network for the prediction of flow boiling curves,” Journal of Nuclear Science and Technology, vol. 39, no. 11, pp. 1190–1198, 2002.
• S. A. Rushdi, “Prediction of Heat Transfer Coefficient of Pool Boiling Using Back propagation Neural Network Prediction of Heat Transfer Coefficient of Pool Boiling Using Back propagation Neural Network ﺭ Engineering and Technology Journal, 30(8), 2016.
• M. Liang, X. Zhang, R. Zhao, X. Wen, and S. Qing, “Optimization of R245fa Flow Boiling Heat Transfer Prediction inside Horizontal Smooth Tubes Based on the GRNN Neural Network,” vol. 2018, 2018.
• H. Badem, A. Basturk, A. Caliskan, and M. E. Yuksel, “A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited–memory BFGS optimization algorithms,” Neurocomputing, vol. 266, pp. 506–526, 2017.
• A. B. Demirpolat and M. Das, “Prediction of viscosity values of nanofluids at different pH values by alternating decision tree and multilayer perceptron methods,” Applied Sciences (Switzerland), vol. 9, no. 7, 2019.
• H. M. Ertunc, “Prediction of the pool boiling critical heat flux using artificial neural network,” IEEE Transactions on Components and Packaging Technologies, vol. 29, no. 4, pp. 770–777, 2006.
• S. A. Alavi Fazel, “A genetic algorithm-based optimization model for pool boiling heat transfer on horizontal rod heaters at isolated bubble regime,” Heat and Mass Transfer/Waerme- und Stoffuebertragung, vol. 53, no. 9, pp. 2731–2744, 2017.
• E. Alic, O. Cermik, N. Tokgoz, and O. Kaska, “Optimization of the Pool Boiling Heat Transfer in the Region of the Isolated Bubbles using the ABC Algorithm,” vol. 12, no. 4, pp. 1241–1248, 2019.
• E. Alic, M. Das, and O. Kaska, “Heat flux estimation at pool boiling processes with computational intelligence methods,” Processes, vol. 7, no. 5, 2019.
• J. M. Barroso-Maldonado, J. A. Montañez-Barrera, J. M. Belman-Flores, and S. M. Aceves, “ANN-based correlation for frictional pressure drop of non-azeotropic mixtures during cryogenic forced boiling,” Applied Thermal Engineering, vol. 149, no. November 2018, pp. 492–501, 2019.
• N. Parveen, S. Zaidi, and M. Danish, “Comparative analysis for the prediction of boiling heat transfer coefficient of R134a in micro/mini channels using artificial intelligence (AI)-based techniques,” International Journal of Modelling and Simulation, vol. 40, no. 2, pp. 114–129, 2020.
• Peng, Y., Li, W., Luo, X., Li, H. A geographically and temporally weighted regression model for spatial downscaling of MODIS land surface temperatures over urban heterogeneous regions. IEEE Transactions on Geoscience and Remote Sensing, 57(7), 5012-5027, 2019.
• Wang Y, Witten IH. Modeling for optimal probability prediction. In: Proceedings of the 19th International Conference in Machine Learning, Sydney, Australia, 2002, pp. 650-7.
• Meshkin, A., Sadeghi, M., Ghasem-Aghaee, N. Prediction of relative solvent accessibility using pace regression. EXCLI J, 8, 211-217, 2009.
• Wang JY, Ahmad S, Gromiha MM, Sarai A. Look-up tables for protein solvent accessibility prediction and nearest neighbor effect analysis. Biopolymers; 75:209-16, 2004.
• Das, M., Akpinar, E. K. Investigation of pear drying performance by different methods and regression of convective heat transfer coefficient with support vector machine. Applied Sciences, 8(2), 215, 2018.
• FAZEL, SA Alavi; JAMIALAHMADI, M. Semi-empirical modeling of pool boiling heat transfer in binary mixtures. International journal of heat and fluid flow, 44: 468-477, 2013.