Adaptive Neuro-Fuzzy Modeling of the Thermal Conductivity of Alumina-Water Nanofluids

By using on Adaptive Neuro-Fuzzy Inference System (ANFIS) as well as experimental data, a model was established for the prediction of the thermal conductivity ratio of alumina (Al₂O₃)-water nanofluids. In the ANFIS the target parameter was the thermal conductivity ratio, and the nanoparticle volume concentration, temperature and Al₂O₃ nanoparticle size were considered as the input (design) parameters. In the development of the model, the empirical data was divided into train and test sections. The ANFIS network was instructed by eighty percent of the experimental data and the remaining data (twenty percent) were considered for benchmarking. The results which were obtained by the proposed Adaptive Neuro-Fuzzy Inference System (ANFIS) model were in good agreement with the experimental results.