Abstract

The present paper deals with the design of a neural network type model for drying of carrots, which includes the associated transport mechanisms of the process. The model uses the operational variables and the time as input parameters. Two sub-layers of linear and sigmoidal nodes make up the hidden layer, to represent the external and internal resistances to the diffusion of water vapors during the drying process. The single output node weights the contribution of each mechanism of the drying process to predict the exit moisture content of the product. This model was used to predict the drying of carrot particles in a mechanically fluidized bed dryer reported in a previous paper [Reyes, A.; Alvarez, P.; Marquardt, F. Drying of carrots in a fluidized bed: I.- effects of drying conditions and modeling. Drying Technology 2002, 20 (7), 1463-1483.]. Simulated drying curves obtained with this model fits adequately the curves determined experimentally for the most operation conditions, which would indicate that this model is appropriate to be used for rough estimations in the design, the selection of optimal operational conditions, and the scaling up of dryers.