Prediction of Energy and Exergy of Carrot Cubes in a Fluidized Bed Dryer by Artificial Neural Networks

In this study both static and recurrent artificial neural networks (ANNs) were used to predict the energy and exergy of carrot cubes during fluidized bed drying. Drying experiments were conducted at air temperatures of 50, 60, and 70 degrees C; bed depths of 3, 6, and 9 cm; and square-cubed carrot dimensions of 4, 7, and 10 mm. Five hundred eighteen patterns, obtained from experiments, were used to develop the ANN models. Initially, a static ANN was applied to correlate the outputs (energy and exergy of carrot cubes) to the four exogenous inputs (drying time, drying air temperature, carrot cube size, and bed depth). In the recurrent ANNs, in addition to the four exogenous inputs, two state inputs and outputs (energy and exergy of carrot cubes) were used. To find optimum ANN models, various numbers of hidden neurons were investigated. The energy and exergy of carrot cubes were predicted with R-2 values of greater than 0.95 and 0.97 using static and recurrent ANNs, respectively. Accordingly, the optimal recurrent model could be utilized for determining the appropriate drying conditions of carrot cubes to reach the optimal energy efficiency in fluidized bed drying.