Author(s): Yaser Sheikhi; Babak Lashkar-Ara
Linked Author(s):
Keywords: Critical Submergence; Nonlinear Regression; CSSS; Neural Network
Abstract: Horizontal intakes are one of the most important parts of hydraulic sets such as river for irrigation or reservoir for power generation and industrial purposes. Air entrainment by means of a free air-core vortex occurring at intake pipes is an important problem encountered in hydraulic engineering. Formation of the vortices in front of intake is the result of complex interaction between many parameters and cause operational problems for turbine or pump and reduction of coefficient of discharge. In this study, the equation s for estimating critical submergence are developed using experimental data. The results are compared with critical spherical sink surface (CSSS) presented by Yilderim method, Gurbuzdal model and artificial neural network (ANN) .According to the results, the neural network is more accurate than previous models proposed by researchers and equation presented in this study, but there is a better agreement between the presented equation and experimental data than CSSS I, CSSS II and equation presented by Gurbuzdal. Therefore, the presented equation as a simple and the precise equation is recommended to estimate the critical submergence. In this equation, the value of RMSE and2R are 0. 283 and 0. 826respectively.
Year: 2015