A neural network approach for prediction of critical submergence of an intake in still water and open channel flow for permeable and impermeable bottom

Free air-core vortex occurring at a water-intake pipe is an important problem encountered in hydraulic engineering. When the submergence of the intake pipe is not sufficient, air enters the pipe and reduction in discharge occurs. The most common solution for avoiding air entrainment is to provide sufficient submergence to the intake. In this study, the critical submergence of intakes is investigated in still water and open channel flow for permeable and impermeable bottom. It is seen that the permeability of the bottom is effective on the critical submergence. The main aim of this study is to develop a suitable model for the critical submergence for intake pipe. Therefore, an artificial neural network (ANN) and multi-linear regression models are used. Results of these experimental studies are compared with those obtained by the ANN and MLR approaches. The ANN model results are found to be in good agreement with the experimental results.