Artificial Neural Network Prediction of Minimum Fluidization Velocity for Mixtures of Biomass and Inert Solid Particles

The fluidization of certain biomasses used in thermal processes, such as sawdust, is particularly difficult due to their irregular shapes, varied sizes, and low densities, causing high minimum velocities (Umf). addition an inert material causes its Umf drop significantly. determination the binary mixture however hard obtain. Generally, predictive correlations are based on a small number specific experiments, sphericity seldom included. In present work, three models, i.e., empirical correlation two artificial neural networks (ANN) models were predict biomass-inert mixtures. An extensive bibliographical survey more than 200 datasets was conducted with complete data about particle diameters, sphericities, biomass fraction, Umf. With combined application partial dependence plot (PDP) ANN average effect quantitatively determined (inverse relationship) together impact fraction (direct relationship). comparison correlations, results showed that both can accurately presented mixtures errors lower 25%.