Evaluation Type of Flow Regime over Broad-Crested Stepped Spillways Using a Hybrid FVM-ANN Approach

It is essential to know accurately characteristics of the flow over stepped spillways such as turbulent dissipation and flow regime. This study was concerned with application of FVM-ANN technique for investigation of the flow regime over broad-crested stepped spillways. For this purpose, finite volume method (FVM) was employed for numerical modeling of stepped spillways using laboratory data belonging to a previous research study. The perfect conformity of numerical and laboratory results is clearly observed according to a statistical test. Then, for development of the numerical model, different geometries of spillways were investigated and flow regimes over these spillways were obtained. Furthermore, it has been attempted to train an Artificial Neural Network (ANN) that includes two layers and entails one neuron on output layer using numerical results in addition to investigating the number of neurons at the first layer. As a result of using ANN, the flow regime can be evaluated by having the discharge per unit width over the spillway, the steps' height, and the channel slope's angle. Finally, the sensitivity analysis of the flow regime against the change of each parameter of geometry of the spillways was done. Results indicated the behavior of the flow regime against investigated parameters well.