Artificial neural network prediction of minimum fluidization velocity for mixtures of biomass and inert solid particles

ANDRÉS REYES URRUTIA; JUAN PABLO CAPOSSIO; CÉSAR M. VENIER; ERICK DAVID TORRES; ROSA ANA RODRIGUEZ; GERMÁN MAZZA

FLUIDS

Multidisciplinary Digital Publishing Institute MDPI

Lugar: Basel; Año: 2023 vol. 8 p. 1 - 18

The fluidization of certainbiomasses used in thermal processes, like sawdust, is particularly difficult dueto their irregular shapes, varied sizes, and low densities, causing highminimum fluidization velocities (Umf). The addition of an inertmaterial causes its Umf to drop significantly. The determination ofthe Umf of the binary mixture is however hard to obtain. Generally,predictive correlations are based on a small number of specific experiments, andsphericity is seldom included. In the present work, three models, i.e., anempirical correlation and two artificial neural networks (ANN) models were usedto predict the Umf of biomass-inert mixtures. An extensivebibliographical survey of more than 200 datasets was conducted, with completedata about densities, particle diameters, sphericities, biomass fraction, and Umf.With the combined application of the Partial Dependence Plot (PDP) and the ANNmodels, the average effect of sphericity on Umf was quantitatively determined(inverse relationship) together with the average impact of the biomass fractionon Umf (direct relationship). In comparison with the empiricalcorrelations, results showed that both ANN models can accurately predict the Umfof the presented binary mixtures with errors lower than 25%.