关于智能分析的供水管网浊度模拟研究.pdf

第 3 7 卷第 4 期 青岛理工大学学报 Vol. 37 No. 4 2016 Journal of Qingdao University of Technology 基于智能分析的供水管网浊度模拟研究 李 航 \ 李 雅 蕾 2 ，吕 谋i % 张 伟 1 ( 1 .青岛理工大学环境与市政工程学院，青岛 266033;2.平度市环境保护局，平 度 266700) 摘 要 :在分析国内外供水管网水质研究现状的基础上，对管网水的浊度特性及演变规律进行了深人研究，总 结了饮用水浊度指标在管网中的变化规律，并据此筛选出对管网水浊度变化影响较大的三方面因素，即流速、 水龄、总铁含量.在对主要因素进行连续监测的基础上，运用 M A T L A B 分别构建B P 和 R B F 神经网络模型对 管网水浊度进行模拟分析，结果表明模拟值与实测值吻合良好,R B F 神经网络的非线性逼近能力更强，预测 精度更高. 关 键 词 :供水管网;浊度模拟;B P 神经网络;R B F 神经网络 中图分类号 :TU991 文献标志码 ：A 文章编号 = 1673-4602(2016)04-0075-07 Study on intelligent turbidity simulation analysis of water supply network LI Hang1, LI Ya -lei2 ,L V Mou 1 * , ZHANG Wei 1 (1. School of Environmental and Municipal Engineering,Qingdao University of Technology,Qingdao 266033,China ； 2. Pingdu Municipal Environmental Protection Bureau,Pingdu 266700,China) Abstract ： Based on the statistical analysis of the research status of water quality of water sup ­ ply network at home and abroad? the paper carries out an in-depth study of the water turbidi ­ ty properties and evolution rule with the general regularity of turbidity index in water supply network summarized . Three aspects such as flow rate ? water age， and total iron concentra­ tions greatly impacting on the turbidity in water supply network filtered out . Based on the continuous monitoring of the main factors? it makes a study of the turbidity in water supply network with the help of M ATLAB to structure the BP and RBF neural network . The simu­ lation result shows that the error between simulation values and the measured values is mi ­ nor , and the nonlinear approximation abi