Development of an Artificial Neural Network EMMS Drag Model for the Simulation of Fluidized Beds in Chemical Looping Combustion

The current work presents an Artificial Neural Network Energy Minimization Multi-Scale (ANN-EMMS) drag scheme, which has been developed specifically for applications of fluidized bed reactors in chemical looping combustion. The data that feed the neural network are generated by a custom-built Matlab code that solves the EMMS equations for gas-particle conditions that correspond to those encountered in chemical looping combustion. The examined particles correspond to the various bed materials encountered in chemical looping combustion i.e., ilmenite (FeTiO₃), hematite (Fe₂O₃) and titanium oxide (TiO₂). The developed drag model is tested in a CFD simulation of a pilot scale circulating fluidized bed air reactor, which has been also performed as part of this work; the results of the pressure profile in the reactor were in good agreement with those of the conventional EMMS model.