Numerical investigation of heat transfer in helical tubes modified with aluminum oxide nanofluid and modeling of data obtained by artificial neural network

Abstract

The purpose of this study is to investigate the computational fluid dynamics to find the effects of Reynolds number, different volume fractions of aluminum oxide nanofluid and different heat fluxes in heat transfer performance (Nusselt number) in a helical tube. This simulation was investigated at Reynolds number range 2000 and 10,000 and volumetric fraction range 1% and 4% of aluminum oxide nanofluid and constant heat fluxes of 4000–6000 W/m2. The single-phase model was used to model the nanofluid and the feasible k-ε model was used to simulate the turbulent flow. Then, perceptron artificial neural networks with the Levenberg–Marquardt algorithm were used to predict the Nusselt number such that input parameters include Reynolds number, nanoparticle volume fraction and output or target was considered Nusselt number for the network. The results show that with increasing the volume fraction of aluminum oxide nanofluid and Reynolds number, the Nusselt number increases by about 20.35%. Also, by increasing the constant heat flux from 4000–6000 W/m2, the Nusselt number increases by 18.75%. The results of the artificial neural network show that the topology 2-10-1 is very successful in predicting the Nusselt number so that the minimum mean squared error for the data allocated to the training and validation sections were 0.024449627 and 0.117025052, respectively, which are obtained under optimal epochs 19 and 9. The value of the correlation coefficient obtained in predicting the Nusselt number is 0.944416302.