Improved Heat Transfer Correlation in the Transition Region for a Circular Tube with Three Inlet Configurations Using Artificial Neural Networks
Authors:
- 1 March 2004
- journal article
- research article
- Published by Taylor & Francis in Heat Transfer Engineering
- Vol. 25 (2) , 30-40
Abstract
Local forced and mixed heat transfer coefficients were measured by Ghajar and Tam [ 5 Ghajar, A. J. and Tam, L. M. 1994. Heat Transfer Measurements and Correlations in the Transition Region for a Circular Tube with Three Different Inlet Configurations. Experimental Thermal and Fluid Science, vol. 8(no. 1): pp. 79–90. [Crossref], [Web of Science ®] [Google Scholar] ] in a horizontal circular straight tube fitted with reentrant, square-edged, and bell-mouth inlets under uniform wall heat flux boundary condition. For the experiments, the Reynolds, Prandtl, and Grashof numbers varied from about 280 to 49000, 4 to 158, and 1000 to 2.5 × 105, respectively. The heat transfer transition regions were established by observing the change in the heat transfer behavior. The data in the transition region were correlated by using the traditional least squares method. The correlation predicted the transitional data with an average absolute deviation of about 8%. However, about 30% of the data in the transition region were predicted with 10–20% deviation, and about 3% with deviations greater than 20%. This is due to the abrupt change in the heat transfer characteristic and its intermittent behavior in this region. Since the value of the heat transfer coefficient has a direct impact on the size of the heat exchanger, a more accurate correlation has been developed using artificial neural networks. A total of 1290 data points (441 for reentrant, 416 for square-edged, and 433 for bell-mouth) were used. The accuracy of the improved heat transfer correlation is excellent, with the majority of the data points predicted with less than 5% deviation.Keywords
This publication has 18 references indexed in Scilit:
- Neural network analysis of fin-tube refrigerating heat exchanger with limited experimental dataInternational Journal of Heat and Mass Transfer, 2001
- Simulation of Heat Exchanger Performance by Artificial Neural NetworksHVAC&R Research, 1999
- Evaluating convective heat transfer coefficients using neural networksInternational Journal of Heat and Mass Transfer, 1996
- Heat transfer measurements and correlations in the transition region for a circular tube with three different inlet configurationsExperimental Thermal and Fluid Science, 1994
- A neural network methodology for heat transfer data analysisInternational Journal of Heat and Mass Transfer, 1991
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Accelerating the convergence of the back-propagation methodBiological Cybernetics, 1988
- Increased rates of convergence through learning rate adaptationNeural Networks, 1988
- Comprehensive Correlating Equations for Heat, Mass and Momentum Transfer in Fully Developed Flow in Smooth TubesIndustrial & Engineering Chemistry Fundamentals, 1977
- Heat Transfer and Pressure Drop of Liquids in TubesIndustrial & Engineering Chemistry, 1936