Affiliation:
1. Department of Civil Engineering, Razi University, Kermanshah, Iran and Water and Wastewater Research Center, Razi University, Kermanshah, Iran
Abstract
In this study, an expert system with a radial basis function neural network (RBF-NN) based on decision trees (DT) is designed to predict sediment transport in sewer pipes at the limit of deposition. First, sensitivity analysis is carried out to investigate the effect of each parameter on predicting the densimetric Froude number (Fr). The results indicate that utilizing the ratio of the median particle diameter to pipe diameter (d/D), ratio of median particle diameter to hydraulic radius (d/R) and volumetric sediment concentration (CV) as the input combination leads to the best Fr prediction. Subsequently, the new hybrid DT-RBF method is presented. The results of DT-RBF are compared with RBF and RBF-particle swarm optimization (PSO), which uses PSO for RBF training. It appears that DT-RBF is more accurate (R2 = 0.934, MARE = 0.103, RMSE = 0.527, SI = 0.13, BIAS = −0.071) than the two other RBF methods. Moreover, the proposed DT-RBF model offers explicit expressions for use by practicing engineers.
Subject
Water Science and Technology,Environmental Engineering
Reference21 articles.
1. Ab Ghani
A.
1993
Sediment Transport in Sewers. PhD thesis, Newcastle University, Newcastle Upon Tyne, UK.
2. Rectangular storm sewer design under equal sediment mobility;Almedeij;American Journal of Environmental Science,2012
3. Remarks on Camp's criterion for self-cleansing storm sewers;Almedeij;Journal of Irrigation and Drainage Engineering,2010
4. Hydraulic performance of sewer pipes with deposited sediments;Banasiak;Water Science and Technology,2008
Cited by
27 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献