Prediction of Scour around Cross-Vane Structures using Generalized Structure of Group Method of Data Handling

In this study, the scour pattern in the vicinity of cross-vane structures with I, U and J shapes in bending channels is simulated by a new artificial intelligence method called "generalized structures group method of data handling” (GSGMDH). Initially, all the parameters affecting the scour depth in the vicinity of cross-vane structures are identified and then using these parameters, six different models are defined for each of the GMDH and GSGMDH methods. By analyzing the results yielded by the artificial intelligence models, the superior models are introduced. The GMDH and GSGMDH superior models estimate the scour values in terms of all input parameters. In addition, the accuracy of the GSGMDH models is higher than that the GMDH ones. For example, for the GMDH and GSGMDH superior models, the values of "variance accounted for" in the test mode are calculated 73.075 and 86.408, respectively. Also, the superior model forecasts the objective function values with acceptable accuracy. For example, the correlation coefficient (R), the scatter index (SI), and the Nash-Sutcliffe model efficiency coefficient (NSC) for the GSGMDH superior model in the training mode are approximated 0.913, 0.214 and 0.800, respectively. Based to the results of the sensitivity analysis, the shape factor of cross-vane structures, the ratio of the difference between the upstream and downstream flow depths to the height of the structure and the densimetric Froude number (Fd) are introduced as the most effective input parameters. An uncertainty analysis exhibits that the GSGMDH superior model has an underestimated performance.