Comparing various machine learning approaches in modeling the dynamic viscosity of CuO/water nanofluid

Nanofluids are broadly employed in heat transfer mediums to enhance their efficiency and heat transfer capacity. Thermophysical properties of nanofluids play a crucial role in their thermal behavior. Among various properties, the dynamic viscosity is one of the most crucial ones due to its impact on fluid motion and friction. Applying appropriate models can facilitate the design of nanofluidics thermal devices. In the present study, various machine learning methods including MPR, MARS, ANN-MLP, GMDH, and M5-tree are used for modeling the dynamic viscosity of CuO/water nanofluid based on the temperature, concentration, and size of nanostructures. The input data are extracted from various experimental studies to propose a comprehensive model, applicable in wide ranges of input variables. Moreover, the relative importance of each variable is evaluated to figure out the priority of the variables and their influences on the dynamic viscosity. Finally, the accuracy of the models is compared by employing the statistical criteria such as R-squared value. The models’ outputs disclosed that employing ANN-MLP approach leads to the most precise model. R-square value and average absolute percent relative error (AAPR) value of the model by using ANN-MLP model are 0.9997 and 1.312%, respectively. According to these values, ANN-MLP is a reliable approach for predicting the dynamic viscosity of the studied nanofluid. Additionally, based on the relative importance of the input variables, it is concluded that concentration has the highest relative importance; while the influence of size is the lowest one.