A feed-forward artificial neural network with several training methods and various geometries for predicting the rheological behavior of Al2O3/ ethylene glycol-water hybrid nanofluid

In this study, the effect of volume fraction of nanoparticles (phi), temperature (Tem.), and shear rates (SR) on the viscosity (mu(nf)) of Al2O3/Ethylene Glycol-Water hybrid nanofluid is investigated using an artificial neural network (ANN). To this end, the mu(nf) is computed for all 180 different combinations of factors with experimental tests, including 7 different 8 ranging from 0 similar to 1.3 % (phi= 0, 0.15, 0.25, 0.5, 0.75, 1, and 1.3 %), 8 different Tem. varying from 25 similar to 60 degrees C (T = 25, 30, 35, 40, 45, 50, 55, and 60 degrees C), and 5 values for shear rates from 20 similar to 100 rpm (SR = 20, 30, 50, 60, and 100). The results show that two trainbr and trainlm methods show the highest performance for data prediction among all training methods. The trained ANN by employing the trainbr function (and trainlm in the next level) for training has the best performance and shows 0.041 and 0.997 for MSE value and correlation coefficient, respectively. Based on the obtained data, the phi has the highest influence on mu(nf) for this material. Increasing this parameter from 0 to 1.3 % grows the mu(nf) from 2.5 cP to around 12 cP. The next influential parameter is the SR, which has a moderate effect on mu(nf) that changes the mu(nf) around 125 % by changing the SR from 20 to 100. Also, increasing the Tem. to 60 degrees C will cause a variation of 40 % in the mu(nf). Tem. and SR are inversely related to mu(nf), i.e., increasing these variables reduces the output. In general, the results show that the phi has the greatest effect on mu(nf).