Experimental results published in the literature between 1935 and 2000 were
used to generate a working database of 558 loading capacity data for rando
mly dumped packed beds. The reported measurements were first used to review
the accuracy of the few available predicting loading capacity correlations
. The Billet and Schultes semiempirical correlation (Trans IChemE 77 (1999)
p. 498) emerged as the best prediction method and is recommended for loadi
ng transition estimation, only when the constant C-SO of a given packing el
ement is available. When such a model-dependent parameter is unavailable, a
n alternative and generalized neural network correlation is proposed to imp
rove the broadness and accuracy in predicting the loading capacity for pack
ed towers. A combination of five dimensionless groups, namely the liquid Re
ynolds (Re-L), Galileo (Ga-L) and Stokes (St(L)) numbers as well as the pac
king sphericity (phi) and one bed number (S-B) outlining the tower dimensio
ns were used as inputs of the neural network correlation for the prediction
of the loading capacity via the Lockhart-Martinelli parameter (chi),The co
rrelation yielded an absolute average relative error of 21 % and a standard
deviation of 19.9 %. Through a sensitivity analysis: the Stokes number in
the liquid phase exhibits the strongest influence on the prediction while t
he liquid velocity, gas density and packing surface area are the leading ph
ysical properties defining the loading level.