Prediction of scour hole characteristics caused by water jets using metaheuristic artificial bee colony-optimized neural network and pre-processing techniques

Abstract

Preventing plunge pool scouring in hydraulic structures is crucial in hydraulic engineering. Although many studies have been conducted experimentally to determine relationship between the scour depth and water jets in several fields, available equations have deficiencies in calculating the exact scour due to complexity of the scour process. This study investigated local scour depth in plunge pool using metaheuristic artificial bee colony-optimized feed-forward neural network (ABC-FFNN), variational mode decomposition (VMD), and ensemble empirical mode decomposition (EEMD) techniques. To set modeling, the input parameters are impact angle, densimetric Froude number, impingement length, and nozzle diameter. The models' training and testing were conducted using data available in the literature. The models' performances were compared with experiments. The results demonstrate that scour depth, length, width, and ridge height can be calculated more accurately than the available equations. A rank analysis was also applied to obtain the most critical parameter in predicting scour parameters in water jet scouring. ABC-FFNN, VMD-ABC-FFNN, and EEMD-VMD-FFNN hybrid models were performed to obtain scour parameters. As a result, ABC-FFNN algorithms produced the best solution to predict the scour due to circular water jets, with the values for training (R-2: 0.331-0.778) and testing (R-2: 0.495-0.863).