Prediction of penetration depth in a plunging water jet using soft computing approaches

The flow characteristics of the plunging water jets can be defined as volumetric air entrainment rate, bubble penetration depth, and oxygen transfer efficiency. In this study, the bubble penetration depth is evaluated based on four major parameters that describe air entrainment at the plunge point: the nozzle diameter (D (N)), jet length (L (j)), jet velocity (V (N)), and jet impact angle (theta). This study presents artificial neural network (ANN) and genetic expression programming (GEP) model, which is an extension to genetic programming, as an alternative approach to modeling of the bubble penetration depth by plunging water jets. A new formulation for prediction of penetration depth in a plunging water jets is developed using GEP. The GEP-based formulation and ANN approach are compared with experimental results, multiple linear/nonlinear regressions, and other equations. The results have shown that the both ANN and GEP are found to be able to learn the relation between the bubble penetration depth and basic water jet properties. Additionally, sensitivity analysis is performed for ANN, and it is found that D (N) is the most effective parameter on the bubble penetration depth.