Modeling the Influence of Nanoparticles and Gyrotactic Microorganisms on Natural Convection in a Heated Square Cavity: A New Machine-Learning Study

Abstract

The phenomenon of natural convection, which is widely used in nature and engineering applications, is a current issue that can be encountered in every field of daily life. In this study, the natural convection characteristics of a complex liquid containing nanoparticles and gyrotactic microorganisms in a heated square cavity were investigated using a machine learning approach. Nusselt number, average Sherwood number of nanoparticles and average Sherwood number of microorganisms were considered as natural convection parameters and an artificial neural network model was developed to estimate these values. Lewis number, Brownian motion parameter, thermophoresis parameter and buoyancy ratio parameter values were defined as input parameters in the network model, which has a multi-layer perceptron architecture developed with a total of 24 data sets. There were 10 neurons in the hidden layer of the network model, which has a Bayesian regularization training algorithm. The outputs obtained from the network model were compared with the target values, in addition, the prediction performance of the model was extensively analyzed using various performance parameters. It was seen that the predicted values obtained from the neural network and the target values were in an ideal harmony. On the other hand, the coefficient of determination value for the network model was 0.99999% and the mean deviation rates were lower than -0.03%. The results of the study showed that the developed neural network model can predict the natural convection parameters discussed with high accuracy.