BackgroundThe ability to combine with the high-temperature applications even in less sunlight distinguishes vacuum tube solar collectors (VTSCs) from other collectors. Loading nanoparticles can lead to effectiveness enhancement. In this numerical study, using regression-based methods the thermal behavior of VTSCs filled with SiO2/EG-water was evaluated. MethodsFor this purpose, using the statistical parameters of R-square and margin of deviation (MOD), the appropriate number of neurons for the artificial neural network (ANN) was determined. FindingsThe results showed that using ANN for the prediction of outlet temperature was successful. Considering R2 > 0.99 and MOD < 0.3%, it was found that for all three coils (helical, U-tube and spiral) ANN can estimate collector outlet temperature with very little error.According to the output temperature predicted by ANN, the instantaneous/overall efficiencies were calculated with a maximum error of 7% and 0.298%. Moreover, the approved ANN for instantaneous efficiency has R2 > 0.886 while this figure for overall efficiency was greater than 0.9999.
Read full abstract