FAST-RESPONSE DISTRIBUTED-PARAMETER FLUIDIZED-BED REACTOR MODEL FOR PROPYLENE PARTIAL OXIDATION USING FEEDFORWARD NEURAL-NETWORK METHODS

The use of a neural network model (NNM) to simulate the performance of a fluidized-bed reactor for the partial oxidation of propylene to acr olein is investigated The training set needed to generate the NNM is o btained from a two-phase cell model of the fluidized-bed where the flo w patterns for the bubble and emulsion phases in each cell are assumed to be plug-flow and perfectly mixed, respectively. The intrinsic kine tics, which are taken from the literature, are based upon a single sit e redox type model that exhibits a nonlinear dependence on both molecu lar oxygen and propylene. The formation of acrolein, acetaldehyde, and total combustion products is described by a series-parallel reaction network. The fluidized bed model accounts for variable gas velocity as well as finite transport resistance between the bubble and emulsion p hases. To perform the required NNM training, output responses predicte d From the cell model are first generated by using all possible combin ations of eleven key input parameters varied over practical ranges of interest. The axial variation of the nine output responses is represen ted by a recurrent NNM. The NNM parameters are then identified using a special-purpose computer software package that implements both traini ng and analysis of the input data and corresponding output responses. To simulate the behavior of a real reactor, the output responses are c orrupted with random noise. Comparisons between the output responses o btained from the NNM trained to noisy data to those from the cell mode l with no noise indicate that the NNM is capable of providing filterin g. Furthermore, a sensitivity analysis indicates that the NNM captures the dependence of the output variables on the input ones.