Modeling of Drying Behaviors of Mushroom in a Solar Assisted Heat Pump Dryer by Using Artificial Neural Network

Dryer was tested by drying mushroom with solar energy and solar assisted heat pump separately at 45 degrees C and 55 degrees C drying air temperature and 0.9 m s(-1) and 1.2 m s(-1) drying air velocities. Moisture content (MC), moisture ratio (MR) and drying rate (DR) which were obtained from experiments were modeled by using Levenberg-Marquardt (LM) the backpropagation learning algorithm and fermi transfer function with artificial neural networks (ANNs). The coefficient of multiple determination (R-2), the root means square error (RMSE) and the mean absolute percentage error (MAPE) were used for the determination of statistical validity of the developed model. R-2, RMSE and MAPE were determined for MC 0.998, 0.0015608, 0.1940471, MR 0.998, 0.0000971, 0.2214687 and DR 0.993, 0.0000075, 0.8627478 respectively. In this way, drying behaviors of mushroom can be analyzed successfully for different drying conditions with this modeling.