Employing deep learning for predicting the thermal properties of water and nano-encapsulated phase change material
Annotatsiya
Abstract The field of thermal engineering is undergoing a transformative revolution through the application of artificial intelligence (AI). In this study, an artificial neural network (ANN) with a genetic algorithm is employed as a powerful tool to accurately predict the thermophysical properties of nano-encapsulated phase change material (NEPCM) suspensions. The NEPCM consists of water as the base fluid, with the shell and core materials represented by sodium lauryl sulfate (SLS) and n-eicosane, respectively. The results demonstrate the effectiveness of the ANN model in successfully predicting dynamic viscosity, density, and shear stress using only two input parameters. However, it is worth noting that the model exhibits slightly weaker performance in predicting thermal conductivity. These findings contribute to the growing body of knowledge in AI-assisted thermal engineering and highlight the potential for enhanced prediction of NEPCM properties. Future research should focus on improving the accuracy of thermal conductivity predictions and exploring additional input parameters to further enhance the model's performance.