Department of Civil Engineering, Indian Institute of Science, Bangalore, India.
*E-mail: ark@civil.iisc.ernet.in
**E-mail: bimk@civil.iisc.ernet.in
The paper illustrates the application of a neural-network model to the modeling of mass transfer in unbaffled surface aeration tank fitted with six flat bladed rotors under geometrically similar conditions. Back-propagation with Levenberg-Marquadt algorithm is used for the modeling of neural-network. This paper discusses the ability of neural-network to model the mass transfer rate in unbaffled surface aeration tank. A thorough sensitive analysis has also been made to ascertain which variables are having maximum influence on re-aeration rates.
Levenberg-Marquadt algorithm, Neural network, Sensitivity analysis, Surface aerator, Theoretical power per unit volume
