Development of an artificial neural network for the prediction of relative viscosity of ethylene glycol based nanofluids

  • PDF / 1,627,756 Bytes
  • 9 Pages / 595.276 x 790.866 pts Page_size
  • 82 Downloads / 213 Views

DOWNLOAD

REPORT


Development of an artificial neural network for the prediction of relative viscosity of ethylene glycol based nanofluids Naman Parashar1 · Mohd Seraj2 · Syed Mohd Yahya1   · Mohd Anas2 Received: 20 February 2020 / Accepted: 28 July 2020 © Springer Nature Switzerland AG 2020

Abstract In this paper, we have developed an artificial neural network (ANN) model for the prediction of the viscosity of ethylene glycol-based nanofluids using data available in the literature. To develop the model, 377 data points were taken from the available literature. The data includes MgO, Y3 Al5 O12 , In2 O3 , Ag, SiO2 , Fe, Mg(OH)2 , ZnO, SiC, Al2 O3 , CeO2 and Ce3 O4 nanoparticles. The inputs given to the ANN model were the diameter of the nanoparticles, temperature, and concentration of the nanoparticles, whereas output was the ratio of dynamic viscosity of the nanofluids to that of the base fluid. The ANN model was trained using 80% of the dataset and the rest of the dataset was used for testing the performance of the developed model. In order to prevent the model from getting overfit, dropout layers were also used. The trial and error method was used to find the optimum model. The optimum model consisted of 2 hidden layers and 45 neurons in both the hidden layers. The developed model shows good performance with the value of mean square error for the training data and test data being 3.9E−04 and 4.4E−04, respectively. The value of correlation coefficient (R) for the training data and test data was found to be 0.9962 and 0.996, respectively. Despite the high number of neurons in hidden layers, performance parameters reveal that there is no overfitting in the model. A comparison between the experimental values and the values predicted by the ANN model is also done in this paper. Keywords  Nanofluids · Artificial neural network · Ethylene glycol · Viscosity

1 Introduction Nanofluid is a class of fluids in which the fluid is suspended with nanometer-sized particles called the nanoparticles. These nanoparticles can be metallic (pure, oxide, carbide etc.), ceramics, carbon based nanomaterials (carbon nanotubes, diamond etc.), 2 dimensional nanomaterials (graphene, MXene etc.) [1, 2]. Nanofluids exhibits enhanced thermophysical properties due to which they have a wide number of applications such as in automotive industry [3, 4], electronics cooling [5, 6], solar thermal and photovoltaic systems [7, 8] etc. A lot of research has been done in order to determine the parameters affecting the thermophysical and rheological properties (such as thermal

conductivity, viscosity etc.) of nanofluids [9, 10]. It has been found that the parameters such as the nanoparticles size, nanofluid temperature, nanoparticles concentration have the most significant impact on the thermophysical and rheological properties. Moreover, thermal conductivity enhancement is desired as it leads to enhanced heat transfer rate, whereas viscosity enhancement is not desired as it significantly increases the pump work [11, 12]. Hence, it becomes important to determine the vi