An optimal feed-forward artificial neural network model and a new empirical correlation for prediction of the relative viscosity of Al2O3-engine oil nanofluid

Abstract

This study presents the design of an artificial neural network (ANN) to evaluate and predict the viscosity behavior of Al2O3/10W40 nanofluid at different temperatures, shear rates, and volume fraction of nanoparticles. Nanofluid viscosity ($${\mu }_{nf}$$ μ nf ) is evaluated at volume fractions ($$\varphi$$ φ =0.25% to 2%) and temperature range of 5 to 55 °C. For modeling by ANN, a multilayer perceptron (MLP) network with the Levenberg–Marquardt algorithm (LMA) is used. The main purpose of this study is to model and predict the $${\mu }_{nf}$$ μ nf of Al2O3/10W40 nanofluid through ANN, select the best ANN structure from the set of predicted structures and manage time and cost by predicting the ANN with the least error. To model the ANN, $$\varphi$$ φ , temperature, and shear rate are considered as input variables, and $${\mu }_{nf}$$ μ nf is considered as output variable. From 400 different ANN structures for Al2O3/10W40 nanofluid, the optimal structure consisting of two hidden layers with the optimal structure of 6 neurons in the first layer and 4 neurons in the second layer is selected. Finally, the R regression coefficient and the MSE are 0.995838 and 4.14469E−08 for the optimal structure, respectively. According to all data, the margin of deviation (MOD) is in the range of less than 2% < MOD < + 2%. Comparison of the three data sets, namely laboratory data, correlation output, and ANN output, shows that the ANN estimates laboratory data more accurately.

A Comprehensive Review of Predicting the Thermophysical Properties of Nanofluids Using Machine Learning Methods

“…Figure (a)–(d) shows the MOD of these data at different stages. The MOD value does not exceed 2%, indicating that the proposed correlation coefficient is acceptable for estimating the accuracy of Al 2 O 3 /10W40 nanofluid …”

“…Research on carbon-based magnetic nanofluids by machine learning methods (a)–(d) Margin of deviation at different stages …”

“…The results show that, compared with the artificial neural network model, the accuracy of the SVR model is slightly higher, and due to its higher accuracy, it is recommended for heat transfer calculations. Shi et al established an ANN to predict the specific heat of magnetic nanofluids, using experimental data such as viscosity, thermal conductivity, and specific heat as input conditions. As shown in Figure (a)­(b)­(c), the specific heat of the carbon-based magnetic nanofluid decreases with the increase of the solid particle concentration, and slowly increases with the increase of temperature.…”

A novel framework for the evaluation of coastal protection schemes through integration of numerical modelling and artificial intelligence into the Sand Engine App

“…Out of several transfer functions, two of them are used in this model for each node: log-sigmoid transfer function [Eq. ( 5 )] for all nodes of hidden layers 52 and linear transfer function for nodes in output layer. Models were trained using two training functions: Levenberg–Marquardt (trainlm) for ENN and LRNN and Bayesian Regularization (trainbr) for FFNN and CFNN models.…”

Mixed Convection Stagnation Point Flow of a Hybrid Nanofluid Past a Permeable Flat Plate with Radiation Effect

“…The effect of nanoparticle volume fraction and temperature on dynamics viscosity of Al 2 O 3 -MWCNT (40:60)-Oil SAE50 hybrid nanofluid is examined by Qing et al [16]. Esfe and Toghraie [17] applied an optimal feed-forward artificial neural network model and new empirical correlation to predict the viscosity of Al 2 O 3 -engine oil nanofluid. It is found that ANN estimated laboratory data more accurately than correlation output and ANN output.…”