Modeling of heat transfer enhancement by wire coil inserts using artificial neural network analysis

• Published in: Applied thermal engineering 2010-02, Vol.30 (2), p.143-151
• Main Authors: Jafari Nasr, M.R., Habibi Khalaj, A., Mozaffari, S.H.
• Format: Article
• Language: English
• Subjects: Applied sciences; Artificial neural network; Coiling; Computational fluid dynamics; Energy; Energy. Thermal use of fuels; Exact sciences and technology; Fluid flow; Friction factor; Heat transfer; Heat transfer enhancement; Learning theory; Neural networks; Nusselt numbers; Theoretical studies. Data and constants. Metering; Turbulence; Turbulent flow; Wire; Wire coil inserts
• ISSN: 1359-4311
• DOI: 10.1016/j.applthermaleng.2009.07.014

This study presents an application of artificial neural networks (ANNs) to characterize thermo-hydraulic behavior of helical wire coil inserts inside tube. An experimental study was carried out to investigate the effects of four types of wire coil inserts on heat transfer enhancement and pressure drop. The experimental data sets were extracted from four wire coils which were tested within a geometrical range with helical pitch 0.156 < p / d h < 0.354 and wire diameter 0.027 < e / d h < 0.094 . The investigation was conducted with transition and turbulent flow regimes with Reynolds numbers ranging from 4200 to 49,000. The experimental data sets have been utilized in training and validation of the ANN in order to predict the Nusselt numbers and friction factor inside tube with wire coil inserts, and the results were compared to the corresponding correlations. The mean relative errors (MRE) between the predicted results and experimental data were found less than 1.79% for Nusselt numbers and less than 3.27% for friction factor. The performance of the ANN was found to be superior in comparison with corresponding power-law regressions. Finally, using the ANN in order to predict the performance of thermal systems in engineering applications is recommended.