Artificial neural network techniques for the determination of condensation heat transfer characteristics during downward annular flow of R134a inside a vertical smooth tube

Abstract In this study, the best artificial intelligence method is investigated to estimate the measured convective heat transfer coefficient and pressure drop of R134a flowing downward inside a vertical smooth copper tube having an inner diameter of 8.1 mm and a length of 500 mm during annular flow numerically. R134a and water are used as working fluids in the tube side and annular side of a double tube heat exchanger, respectively. The ANN training sets have the experimental data of in-tube condensation tests including six different mass fluxes of R134a such as 260, 300, 340, 400, 456 and 515 kg m− 2 s− 1, two different saturation temperatures of R134a such as 40 and 50 °C and heat fluxes ranging from 10.16 to 66.61 kW m− 2. The quality of the refrigerant in the test section is calculated considering the temperature and pressure obtained from the experiment. The pressure drop across the test section is directly measured by a differential pressure transducer. Input of the ANNs are the measured values of test section such as mass flux, heat flux, the temperature difference between the tube wall and saturation temperature, average vapor quality, while the outputs of the ANNs are the experimental condensation heat transfer coefficient and measured pressure drop in the analysis. Condensation heat transfer characteristics of R134a are modeled to decide the best approach using several artificial neural network (ANN) methods such as multilayer perceptron (MLP), radial basis networks (RBFN), generalized regression neural network (GRNN) and adaptive neuro-fuzzy inference system (ANFIS). Elimination process of the ANN methods is performed by means of 183 data points, divided into two sets randomly, obtained in the experiments. Sets of test and training/validation include 33 and 120/30 data points respectively for the elimination process. Validation process, in terms of various experimental conditions, is done by means of 368 experimental data points having 68 data points for test set and 300 data points for training set. In training phase, 5-fold cross validation is used to determine the best value of ANNs control parameters. The ANNs performances were measured by means of relative error criteria with the usage of unknown test sets. The performance of the method of multi layer perceptron (MLP) with 5-13-1 architecture and radial basis function networks (RBFN) were found to be in good agreement, predicting the experimental condensation heat transfer coefficient and pressure drop with their deviations being within the range of ± 5% for all tested conditions. Dependency of outputs of the ANNs from input values is also investigated in the paper.

[1]  A. S. Dalkılıç,et al.  A Comparison of the Void Fraction Correlations of R134A During Condensation in Vertical Downward Laminar Flow in a Smooth and Microfin Tube , 2008 .

[2]  A. S. Dalkılıç,et al.  A performance comparison of vapour-compression refrigeration system using various alternative refrigerants , 2010 .

[3]  P. Kosky.  Thin liquid films under simultaneous shear and gravity forces , 1971 .

[4]  O. Shoham,et al.  Flow pattern transition for vertical downward two phase flow , 1982 .

[5]  I. Teke,et al.  Comparison of frictional pressure drop models during annular flow condensation of R600a in a horizontal tube at low mass flux and of R134a in a vertical tube at high mass flux , 2010 .

[6]  Peter B. Whalley,et al.  Boiling, Condensation, and Gas-Liquid Flow , 1987 .

[7]  I. Teke,et al.  Experimental analysis for the determination of the convective heat transfer coefficient by measuring pressure drop directly during annular condensation flow of R134a in a vertical smooth tube , 2011 .

[8]  H. Demir,et al.  Generalized neural network model of alternative refrigerant (R600a) inside a smooth tube , 2009 .

[9]  A. S. Dalkılıç,et al.  Experimental Investigation on the Condensation Heat Transfer and Pressure Drop Characteristics of R134A at High Mass Flux Conditions During Annular Flow Regime Inside a Vertical Smooth Tube , 2009 .

[10]  A. Cavallini,et al.  A DIMENSIONLESS CORRELATION FOR HEAT TRANSFER IN FORCED CONVECTION CONDENSATION , 1974 .

[11]  A. S. Dalkılıç,et al.  Experimental investigation of heat transfer coefficient of R134a during condensation in vertical downward flow at high mass flux in a smooth tube , 2009 .

[12]  C. L. Tien,et al.  GENERAL FILM CONDENSATION CORRELATIONS , 1987 .

[13]  A. S. Dalkılıç,et al.  Effect of void fraction models on the two-phase friction factor of R134a during condensation in vertical downward flow in a smooth tube , 2008 .

[14]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[15]  Ulrich Renz,et al.  Heat transfer and film thickness during condensation of steam flowing at high velocity in a vertical pipe , 1992 .

[16]  Ralph L. Webb,et al.  A New Equivalent Reynolds Number Model for Condensation in Smooth Tubes , 1998 .

[17]  A. S. Dalkılıç,et al.  Effect of void fraction models on the film thickness of R134a during downward condensation in a vertical smooth tube , 2009 .

[18]  Fred W. Staub,et al.  Local condensing heat transfer coefficients in the annular flow regime , 1971 .

[19]  D. Kenning.  Liquid—vapor phase-change phenomena , 1993 .

[20]  A. S. Dalkılıç,et al.  New experimental approach on the determination of condensation heat transfer coefficient using frictional pressure drop and void fraction models in a vertical tube , 2010 .

[21]  A. S. Dalkılıç,et al.  Two-phase friction factor in vertical downward flow in high mass flux region of refrigerant HFC-134a during condensation☆ , 2008 .

[22]  H. Müller-Steinhagen.  Heat Transfer Fouling: 50 Years After the Kern and Seaton Model , 2011 .

[23]  M. Shah.  A general correlation for heat transfer during film condensation inside pipes , 1979 .

[24]  A. S. Dalkılıç,et al.  Experimental investigation of convective heat transfer coefficient during downward laminar flow condensation of R134a in a vertical smooth tube , 2009 .

[25]  A. S. Dalkılıç,et al.  Experimental Research on the Similarity of Annular Flow Models and Correlations for the Condensation of R134a at High Mass Flux Inside Vertical and Horizontal Tubes , 2009 .

[26]  A. S. Dalkılıç,et al.  Experimental Study on the Modeling of Condensation Heat Transfer Coefficients in High Mass Flux Region of Refrigerant HFC-134a Inside the Vertical Smooth Tube in Annular Flow Regime , 2011 .

[27]  A. S. Dalkılıç,et al.  Experimental Study on the Flow Regime Identification in the Case of Co-Current Condensation of R134a in a Vertical Smooth Tube , 2010 .

[28]  S. J. Kline,et al.  Describing Uncertainties in Single-Sample Experiments , 1953 .

[29]  A. S. Dalkılıç,et al.  Validation of void fraction models and correlations using a flow pattern transition mechanism model in relation to the identification of annular vertical downflow in-tube condensation of R134a ☆ , 2010 .

[30]  A. S. Dalkılıç,et al.  An investigation of a model of the flow pattern transition mechanism in relation to the identification of annular flow of R134a in a vertical tube using various void fraction models and flow regime maps , 2010 .

[31]  A. S. Dalkılıç,et al.  Intensive literature review of condensation inside smooth and enhanced tubes , 2009 .