ABSTRACT
Sedimentation in open channel occurs regularly according to the alternating natural flow. The long term deposit of material in the open channels increases the risk of changes in the sediments and their consolidation and cementation. In particular, during the dry seasons the permanent deposits on the bed cause changes in the cross section such as roughness, thereby affecting the velocity distribution and consequently the distribution of the boundary shear stress. Generally, to prevent sedimentation at different flow sections under the non-deposition conditions, two simple criteria, based on the minimum velocity or minimum shear stress at a specified depth of flow or period, have been defined by various references. The values of minimum velocity or shear stress can be concluded not to be uniform under differing conditions and in different regions. Therefore, many researchers have conducted several experiments in specified conditions and consequently presented relations they have derived through considering the effective parameters of sediment transport in sewer systems, but relations presented in different flow conditions, cannot provide the same results and in some experiments unforeseen circumstances, the results are often presented with a large error. Therefore, need to develop methods that can accurately predict the sediment transport. This study presents Artificial Neural Network (ANN), Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA), as an alternative approach for modeling the functional relationships of sediment transport. The proposed relationship can be applied to different boundaries.
