Python-based machine learning estimation of thermo-hydraulic performance along varying nanoparticle shape, nanofluid and tube configuration

• Published in: Advances in engineering software (1992) Vol. 199; p. 103814
• Main Authors: Gürsoy, Emrehan, Tan, Muhammed, Gürdal, Mehmet, Çetinceviz, Yücel
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2025
• Subjects: CFD; Forced convection; Machine learning; Nanofluid; Python; Various dimpled fins; CFD; Forced convection; Nanofluid; Various dimpled fins; Machine learning; Python
• ISSN: 0965-9978
• DOI: 10.1016/j.advengsoft.2024.103814

•Analysis of thermodynamics for nanofluid flow with different nanoparticle type, shape (cylindrical, blade, platelet for Al2O3/H2O), concentration (φ= 0 %, 1 %, 0.5–1.5 %, 2 %).•Impact on forced convection of the original expansion tube (α= 30°, 45°, 60°, 90°) and fin geometry (P/d = 10, 15, 20).•First study on forced internal flow using Python based on artificial neural network.•Comparison of numerical and Python based artificial intelligence findings.•The highest PEC for Re= 2000 based on Al2O3/H2O (platelet) shows an increase of 4.84 %, 12.08 %, 11.76 %, 66.05 %, and 148.94 % compared to Al2O3/H2O (cylindrical), Al2O3/H2O (blade), CoFe2O4/H2O, Fe3O4/H2O, and Ag-MgO/H2O, respectively.•The ML models achieved a high degree of accuracy, with some models reaching an error rate as low as 0.2 %. In this research article, a Python-based machine learning model prediction study was conducted based on the study results obtained from sudden expansion tubes containing different expansion angles, dimpled fin structures and nanofluids, whose thermo-hydraulic performance was previously examined. In the study, Artificial Neural Network and Ridge regression models were used to make predictions on the average Nusselt number (Nu), average Darcy friction factor (f) and performance evaluation criteria (PEC). Physical variations of the sudden expansion tube were taken into account and a detailed comparison of the results was made. A superior average Nu was acquired as 172.45 %, 22.05 %, 17.18 %, 13.65 %, and 7.76 % compared to Ag-MgO/H2O, Al2O3/H2O (blade), CoFe2O4/H2O, Al2O3/H2O (cylindrical), and Al2O3/H2O (platelet), respectively. The highest Performance Evaluation Criteria (PEC) for Re= 2000 based on Al2O3/H2O (platelet) shows an increase of 4.84 %, 12.08 %, 11.76 %, 66.05 %, and 148.94 % compared to Al2O3/H2O (cylindrical), Al2O3/H2O (blade), CoFe2O4/H2O, Fe3O4/H2O, and Ag-MgO/H2O, respectively. From the results obtained, it was determined that Python-based Machine Learning approach which facilitates custom optimizations showed a significant performance with small margins of error in predicting the heat transfer parameters. The lowest error rates of machine learning and polynomial ridge regression models ranged from 0.2 % to 5.4 % for the unseen test set and the application of Python-based algorithms provided considerable savings in calculation time compared to conventional methods. On the other hand, using machine learning models with feature engineering has been found to increase model performance by at least 30 %. In these years when studies on the predictions of thermo-hydraulic studies are very rare in the literature, this study is intended to facilitate scientists, engineers and academicians who will further study on this subject.