An artificial neural network modeling of solar drying of mint: Energy, exergy, and drying kinetics

Abstract

The energy and exergy analysis of thin-layer drying of mint leaves was performed in a forced convective solar dryer with new design solar collector. The effects of inlet airflow rates on the energy utilization ratio (EUR), energy generated by the solar air collector, exergy losses, exergy efficiency, and kinetics of drying were determined. The EUR varied between 7.45 to 87.1% and it increased when the flow rate decreased. The average exergy loss for the air with mass flow rates of 0.012, 0.026, and 0.033 kg/s was calculated as 16.2 W, 8.2 W, and 6.88 W, respectively. Unlike other studies, exergy and EUR data obtained from experimental data were modeled with an artificial neural network (ANN). The experimental data were modeled by an artificial neural network (ANN) via a feed-forward back-propagation network. The values obtained from ANN modeling were significantly closed to the experimental values. In both experimental and ANN models, EUR and exergy loss decreased with increasing airflow rate. The importance of airflow rates was promising to modify EUR and exergy losses.