Simulation of the reactor-regenerator-main fractionator fluid catalytic cracking unit using artificial neural networks

The dynamic behavior of the FCC unit was simulated using artificial neural networks (ANN). An analytical model, validated with construction and operation data, was used for producing a comprehensive input-target set of training data. The model predicted the final production rate of the main products, gasoline and diesel. The architecture and training algorithm used by the ANN were efficient and this was proved by the results obtained both on training set and set of input-target data not met during the training procedure. The same good ANN performance was obtained by the comparison between dynamic simulations results emerged from the ANN vs. first principle modeling, both using the same randomly varying inputs. The computation time was reduced when using the ANN model, compared to the use of the analytical model. This is an abstract of a paper presented at the 18th International Congress of Chemical Process Engineering (Praque, Czech Republic 8/24-28/2008).