Premium
Application of neural networks to mass‐transfer predictions in a fast fluidized bed of fine solids
Author(s) -
Zamankhan Piroz,
Malinen Pekka,
Lepomäki Hannu
Publication year - 1997
Publication title -
aiche journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.958
H-Index - 167
eISSN - 1547-5905
pISSN - 0001-1541
DOI - 10.1002/aic.690430705
Subject(s) - mass transfer , fluidized bed , sherwood number , sublimation (psychology) , fluidization , artificial neural network , mechanics , materials science , range (aeronautics) , superficial velocity , mass transfer coefficient , process engineering , flow (mathematics) , thermodynamics , physics , computer science , composite material , artificial intelligence , engineering , nusselt number , psychology , psychotherapist , reynolds number , turbulence
In this study back‐propagation, feed‐forward neural networks are applied to estimate mass‐transfer parameters in fast fluidized beds of fine solids. These networks are trained to predict mass‐transfer rates using measurements of the sublimation rate of coarse naphthalene balls in fast fluidized beds of fine glass beads at several solid‐to‐gas mass flow rates within the relevant superficial gas‐velocity range. When tested to predict the effective diffusivities from a coarse particle to the bulk of the fast bed of fine solids, trained neural networks calculated the Sherwood number with high accuracy. It is demonstrated that back‐propagation, feed‐forward neural networks provide a more accurate correlation for the mass‐transfer coefficient compared to those obtained by the currently used heuristic models.