Upgrading Water Distribution System based on GA-RBF Neural Network Model

被引：0

作者：

Wang, Hongxiang ^{[1
]}

Guo, Wenxian ^{[1
]}

机构：

[1] N China Univ Water Resources & Elect Power, Zhengzhou, Peoples R China

来源：

MANUFACTURING SYSTEMS AND INDUSTRY APPLICATIONS | 2011年 / 267卷

关键词：

Water distribution system; Calibration; Genetic algorithm; RBF neural network;

D O I：

10.4028/www.scientific.net/AMR.267.605

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Hydraulic network calibration model is to minimize the sum of the squares of the differences between the calibrated and initial pipe roughness estimates, under a set of constraints determined from a sensitivity matrix. The upgrading problem of water distribution system was put forward after the preferable network model was obtained. Radial Basis Function neural network (RBF) based on genetic algorithm (GA) was proposed to solve the model. Genetic algorithm was applied to optimize the parameters of the neural network, and overcome the over-fitting problem. Case study concludes that using Radial Basis Function neural network (RBF) based on genetic algorithm (GA) and good results were obtained.

引用

页码：605 / 608

页数：4