A well-trained artificial neural network for predicting the rheological behavior of MWCNT-Al2O3 (30-70%)/oil SAE40 hybrid nanofluid

Mohammad Hemmat Esfe; S Ali Eftekhari; Maboud Hekmatifar; Davood Toghraie

doi:10.1038/s41598-021-96808-4

A well-trained artificial neural network for predicting the rheological behavior of MWCNT-Al₂O₃ (30-70%)/oil SAE40 hybrid nanofluid

Sci Rep. 2021 Aug 31;11(1):17696. doi: 10.1038/s41598-021-96808-4.

Authors

Mohammad Hemmat Esfe¹, S Ali Eftekhari², Maboud Hekmatifar³, Davood Toghraie⁴

Affiliations

¹ Department of Mechanical Engineering, Imam Hossein University, Tehran, Iran.
² Department of Mechanical Engineering, Khomeinishahr Branch, Islamic Azad University, Khomeinishahr, Iran. A.Eftekhari@iaukhsh.ac.ir.
³ Department of Mechanical Engineering, Khomeinishahr Branch, Islamic Azad University, Khomeinishahr, Iran.
⁴ Department of Mechanical Engineering, Khomeinishahr Branch, Islamic Azad University, Khomeinishahr, Iran. Toghraee@iaukhsh.ac.ir.

Abstract

In this study, the influence of different volume fractions ([Formula: see text]) of nanoparticles and temperatures on the dynamic viscosity ([Formula: see text]) of MWCNT-Al₂O₃ (30-70%)/oil SAE40 hybrid nanofluid was examined by ANN. For this reason, the [Formula: see text] was derived for 203 various experiments through a series of experimental tests, including a combination of 7 different [Formula: see text], 6 various temperatures, and 5 shear rates. These data were then used to train an artificial neural network (ANN) to generalize results in the predefined ranges for two input parameters. For this reason, a feed-forward perceptron ANN with two inputs (T and [Formula: see text]) and one output ([Formula: see text]) was used. The best topology of the ANN was determined by trial and error, and a two-layer with 10 neurons in the hidden layer with the tansig function had the best performance. A well-trained ANN is created using the trainbr algorithm and showed an MSE value of 4.3e-3 along 0.999 as a correlation coefficient for predicting [Formula: see text]. The results show that an increase [Formula: see text] has a significant effect on [Formula: see text] value. As [Formula: see text] increases, the viscosity of this nanofluid increases at all temperatures. On the other hand, with increasing temperature, the viscosity of this nanofluid decreases. Based on all of the diagrams presented for the trained ANNs, we can conclude that a well-trained ANN can be used as an approximating function for predicting the [Formula: see text].