Designing an artificial neural network using radial basis function to model exergetic efficiency of nanofluids in mini double pipe heat exchanger

• Published in: Heat and mass transfer Vol. 54; no. 6; pp. 1707 - 1719
• Main Authors: Ghasemi, Nahid, Aghayari, Reza, Maddah, Heydar
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2018; Springer Nature B.V
• Subjects: Aluminum oxide; Artificial neural networks; Basis functions; Correlation coefficients; Efficiency; Engineering; Engineering Thermodynamics; Exergy; Fluid flow; Heat and Mass Transfer; Heat exchangers; Industrial Chemistry/Chemical Engineering; Mathematical models; Nanocomposites; Nanofluids; Neural networks; Optimization; Original; Parameters; Pipes; Predictions; Radial basis function; Reynolds number; Thermodynamics; Titanium dioxide; exergetic efficiency; radial basis function; nanofluid
• ISSN: 0947-7411; 1432-1181
• DOI: 10.1007/s00231-017-2261-7

The present study aims at predicting and optimizing exergetic efficiency of TiO 2 -Al 2 O 3 /water nanofluid at different Reynolds numbers, volume fractions and twisted ratios using Artificial Neural Networks (ANN) and experimental data. Central Composite Design (CCD) and cascade Radial Basis Function (RBF) were used to display the significant levels of the analyzed factors on the exergetic efficiency. The size of TiO 2 -Al 2 O 3 /water nanocomposite was 20–70 nm. The parameters of ANN model were adapted by a training algorithm of radial basis function (RBF) with a wide range of experimental data set. Total mean square error and correlation coefficient were used to evaluate the results which the best result was obtained from double layer perceptron neural network with 30 neurons in which total Mean Square Error(MSE) and correlation coefficient (R 2 ) were equal to 0.002 and 0.999, respectively. This indicated successful prediction of the network. Moreover, the proposed equation for predicting exergetic efficiency was extremely successful. According to the optimal curves, the optimum designing parameters of double pipe heat exchanger with inner twisted tape and nanofluid under the constrains of exergetic efficiency 0.937 are found to be Reynolds number 2500, twisted ratio 2.5 and volume fraction( v /v%) 0.05.