Modeling Viscosity of Refrigerant and Lubricant Mixtures Using Artificial Neural Network (ANN)

In this research, artificial neural networks(ANNs) have been used to predict the viscosity of lubricant/refrigerant mixtures. Temperature, pressure, molecular weight, the mole fraction of refrigerant, and viscosity of refrigerant are used as input variables and viscosity of refrigerant + lubricant mixtures is used as a target. The total number of experimental data point of viscosity that used in this study is 1053 that is trained, validated, and tested with random70%(837 data points), 15% (158 data points), and 15% (158 data points), respectively. The results of the AAD% for the train, validation and test sets of data are 0.39, 0.48, and 0.49, respectively. Therefore, studied ANN models with 15 neurons in a hidden layer are in good agreement with experimental data.