Abstract
Graphene Oxide is one of the carbon-based-materials that has wide application range such as Water purification, Flexible rechargeable battery electrode, Solar Collectors, and Energy conversion. In this research, initially, Graphene Oxide nanoparticles were dispersed in water to make a nanofluid. The nanofluid was prepared at 0.10, 0.15, 0.20, 0.25, 0.35, and 0.45% mass fractions. After that, heat transfer and viscosity (at 10 and 100 Revolutions per minute (RPM)) of the prepared samples were calculated at 25, 30, 35, 40, 45, and 50 degrees C temperatures. In the Flat Plate Solar Collector (FPSC) - Riser tube, from the start point to the end of tube, the temperature decreases and thus the heat transfer and viscosity change. As the calculated range does not contain all the temperatures and mass fractions, and to lower the experimental costs, thus, Fuzzy system and Artificial Neural Network models were used to predict the whole range of data. After that, the trained models were compared to detect the error and to choose the best model with the least error. Results confirmed that Fuzzy system has lower error. This means that Fuzzy system predicts the input-target dataset as definite as obtainable.