Study on the prediction of thermal conductivity for Al-CuO/water nanofluids using artificial neural networks

This research aims to provide a comprehensive analysis of thermal conductivity prediction for CuO and Al2O3 nanoparticles synthesized using the chemical combustion technique. This method reduces nanoparticle surface area, enhancing heat transfer with minimal heat loss and improved dispersion in liquid media. Nanofluids, consisting of nanoparticles suspended in base fluids, offer superior thermal properties compared to conventional fluids. In this study, CuO and Al2O3 nanoparticles were introduced into deionized water at weight fractions of 5 g and 10 g, respectively. An Artificial Neural Network (ANN) was utilized to predict the thermal conductivity of these nanofluids, with the model trained and validated using experimental data to improve predictive accuracy. The study primarily evaluates the effectiveness of the chemical combustion technique in producing nanoparticles with optimized thermal conductivity properties. Additionally, the ANN predictions were compared to experimental results to assess the model's reliability. The findings offer valuable insights into the application of ANN in predicting nanofluid thermal conductivity and can guide future research and industrial applications focused on thermal management.