A fractional gas hold-up performance in mechanically agitated reactor (i.d. range is 0.382m to 1.16m) with mixed hydrofoil impeller 6k5 and Rushton turbine was presented. The effects of geometrical variables

including the ratio of impeller diameter

the distance between impellers

the clearance of lower impeller

gas sparger position

the baffle type

and the operating conditions such as agitator speed

the rate of gas

and the pumping mode of axial impeller 6k5 on fractional gas hold-up were investigated. With the dimensionless and dimensional methods

two correlations were proposed

but their prediction ability was not satisfactory.The correlation based on artificial neural network was established.It was able to predict fractional gas hold-up reasonably well and the relative mean error of generalization by this neural network model was within ±10%

if the parameters were in the trained range. The neural network model could be used for offline prediction and parameter optimization

and could be useful for scale-up because dimensionless parameters were used.