An expert system with radial basis function neural network based on decision trees for predicting sediment transport in sewers

Author:

Ebtehaj Isa1,Bonakdari Hossein1,Zaji Amir Hossein1

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.

Publisher

IWA Publishing

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

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3