Hybrid neural model of thermal drying in a fluidized bed

Abstract

A preliminary study aimed at applying Hybrid Neural Models (HNM) to describe 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 Artificial 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 predict evaporation rate and heat flux in the drying process. In the second HN model, ANN was used to determine heat transfer coefficient only. Excellent agreement between predicted and test data for the case where ANN was applied to determine heat transfer coefficient is shown.