Empirical data-driven multi-layer perceptron and radial basis function techniques in predicting the performance of nanofluid-based modified tubular solar collectors

In the present study, modified evacuated tube solar collector (METSC) with a bypass pipe utilizing copper oxide/distilled water (Cu2O/DW) nanofluid is experimented. Then, performance of METSC was predicted through Artificial Neural Networks (ANNs) techniques. The input variables were different volumes storage tank from 5 to 8 l, various diameters 6 10 mm, and volumetric concentration 0 0.04. Also, output temperature difference fluid in 1-h period energetic efficiency METSC. results demonstrated that mostly impacted by volume alteration. Moreover, optimum diameter value obtained, it denoted using Cu2O/DW enhances daily energy up 4%. Furthermore, shown both MLP RBF techniques are two reliable algorithms predict thermal characteristics an maximum amounts mean relative percentage error for reported as 0.576 0.907, respectively. Hence, mathematical models formulating terms technique.