A preliminary study aimed at applying Hybrid Neural Models (HNM) to de
scribe thermal dewatering process in a fluidized bed is presented. Two
schemes of HN modelling were developed to find the most efficient way
of combining a classical mathematical model of the process and Artifi
cial Neural Network (ANN). Data used for network training was gathered
from the existing mathematical model of fluidized bed drying process
of baker's yeast. In the first HNM a feed-forward ANN was trained to p
redict evaporation rate and heat flux in the drying process. In the se
cond HN model, ANN was used to determine heat transfer coefficient onl
y. Excellent agreement between predicted and test data for the case wh
ere ANN was applied to determine heat transfer coefficient is shown.