Soft computing based predictive modelling of oxygen transfer performance of plunging hollow jets

Abstract

ABSTRACT Bubbles are formed as the plunging water jet passes through atmosphere and impinges on the surface of water in the pool, which increases the oxygen level of water. The amount of oxygen transferred into an aeration system can be altered by the flow characteristics of plunging jet. The present study models and simulates the oxygen transfer properties with basic flow characteristics of plunging hollow jets. Variables related to the jet included in this study are jet thickness, jet velocity, jet length, and depth of water. For the estimation of volumetric oxygen transfer coefficient (), modelling techniques such as multiple nonlinear regression (MNLR), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), multivariate adaptive regression splines (MARS), and generalized regression neural network (GRNN) are used. The results are presented based on training and testing of the models. A nonlinear relationship proposed for the estimation of is compared with the other soft computing-based approaches. The overall comparison of the results obtained from the application of modelling techniques in estimating the experimental data of plunging hollow jets yielded better prediction accuracy by ANFIS (bell-shaped membership function) as well as ANN as compared to MNLR, MARS, and GRNN.