Authors: Isa Ebtehaj Hossein Bonakdari
Publish Date: 2014/09/05
Volume: 28, Issue: 13, Pages: 4765-4779
Abstract
The application of models capable of estimating sediment transport in sewers has been a frequent practice in the past years Considering the fact that predicting sediment transport within the sewer is a complex phenomenon the existing equations used for predicting densimetric Froude number do not present similar results Using Adaptive Neural Fuzzy Inference System ANFIS this article studies sediment transport in sewers For this purpose five different dimensionless groups including motion transport sediment transport mode and flow resistance are introduced first and then the effects of various parameters in different groups on the estimation of the densimetric Froude number in the motion group are presented as six different models To present the models two states of grid partitioning and subclustering were used in Fuzzy Inference System FIS generation Moreover the training algorithms applied in this article include back propagation and hybrid The results of the proposed models are compared with the experimental data and the existing equations The results show that ANFIS models have greater accuracy than the existing sediment transport equations
Keywords: