Artificial Neural Network-CFD Model to Predict the Bio Production Rate of High Fructose Date Syrup

Abstract

Many parameters involved in the bioproduction of fructose from date. These parameters can have significant effects on the yield and quality of the biopruduction of the high fructose date syrup (HFDS); they can be determined by either empirical or numerical investigations for the selected configurations; however, they are expensive procedures. The problem becomes more difficult if the aim is the inverse determination of the operating production process. This paper presents a predictive hybrid model based on the artificial neural networks (ANNs) and finite element method (FEM) that can be used for both forward and inverse prediction. The former is able to determine the diffusion rate, the bioconversion rate and the Fructose %at varying of process parameters, namely the date variety, the speeds of agitation, the date/water ratio, the initial concentration of glucose, the inoculum volume of biomass and the induction time of bioconversion process.The optimal ANN model was found to be a network with two hidden layers and nine neurones in each hidden layer for forward prediction and eleven neurones in each hidden layers for inverse prediction.Prediction errors range between 4% and 5% for the whole data set, both for forward analysis and inverse process design. The results show very good agreement between the predicted and the desired values.