EVALUATION OF NEURAL NETWORKS FOR SIMULATION OF 3-PHASE BUBBLE-COLUMNREACTORS

The use of a neural network model (NNM) to simulate the performance of a three-phase slurry bubble-column reactor for Fischer-Tropsch synthe sis is investigated, The learning set needed to generate the NNM is ob tained from a cell-type model where the number of cells relates to the degree of backmixing. To develop the neural network and to perform th e required learning. model-predicted output responses are generated fr om the cell model by using all possible combinations of six key input parameters. The axial variation of the output responses is represented by a recurrent NNM. The NNM parameters are then identified using a sp ecial-purpose package that implements both training and analysis. To s imulate the behaviour of an actual reactor. data used for training are corrupted with random noise. The NNM obtained from noisy data exhibit s substantial filtering capability.