Abstract
This study introduces a method to predict scour hole geometry at downstream of a ski-jump bucket by group method of data handling (GMDH). The GMDH network was developed using evolutionary and iterative algorithms including those of genetic programming (GP), particle swarm optimization (PSO), and back propagation (BP) algorithms. Results of alternative GMDH networks were compared with those obtained using artificial neural networks, genetic programming, ANFIS, empirical equations, and regression-based equations. Performances indicated that proposed GMDH-BP produced more accurate results in comparison with other methods. Moreover, the most effective independent parameters on scour hole geometry were determined using sensitivity analysis. Finally, combination of evolutionary and iterative algorithms has been confirmed that the GMDH network is a useful soft computing tool for prediction of scour hole geometry at downstream of a ski-jump bucket.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have