Prediction of the pressure drop for CuO/(Ethylene glycol-water) nanofluid flows in the car radiator by means of Artificial Neural Networks analysis integrated with genetic algorithm

Abstract

In this investigation, neural networks were used to predict pressure drop of CuO-based nanofluid in a car radiator. For this purpose, the neural network with the multilayer perceptron structure was used to formulate a model for estimating the pressure drop In this way, different concentrations of copper oxide-based nanofluid were prepared. The base fluid was the mixture of ethylene glycol and pure water (60:40 wt%) which usually used as the cooling fluid in automotive industries. The prepared nanofluid samples were used in a car radiator and the pressure drop of nanofluid flows in the system at different Reynolds were measured. The main purpose of this study was developing the optimized neural networks for predicting the pressure drop of the system with sufficient precision. For the aim of designing the model’s structure, different neural networks were constructed and applied by changing the adjustable parameters (containing the transfer function, training rule, momentum’s amount, hidden layers’ number and the neurons’ number in hidden layer). In each case, the structure with the highest correlation coefficient was chosen as the final model. The selection of each parameters in the neural network model requires repeated tests and errors. So, genetic algorithm was used to optimize these parameters. Additionally, the pressure drop in the radiator of this method was investigated in neural network optimization. The outcomes indicated which a high accuracy in modeling and estimating the pressure drop of nanofluid flows in the studied system can be achieved by the neural network.