基于GA优化BP神经网络模型的污水管道系统健康状况评估  

Evaluation of the health status of sewage pipeline system based on GA optimized BP neural network model

作　　者：杨利伟[1] 邢雯雯 张莉平 赵传靓 周煜欣 路鹏 李昊 YANG Liwei;XING Wenwen;ZHANG Liping;ZHAO Chuanliang;ZHOU Yuxin;LU Peng;LI Hao(School of Civil Engineering,Key Lalxjratory of Water Supply&Seuuage Engineering of Ministry of Housing and Urban-rural Kvelopment,Changy an University,Xi'an 710061,China)

机构地区：[1]长安大学建筑工程学院住建部给水排水重点实验室,西安710061

出　　处：《给水排水》2021年第9期123-131,共9页Water & Wastewater Engineering

基　　金：国家重点研发计划(2018YFE0103800)。

摘　　要：污水管道系统健康评估是城市黑臭水体及城市体检中解决城市水环境污染、内涝灾害等城市病问题的核心和依据。以污水管道系统为研究对象,根据CCTV检测结果,采用层次分析法进行指标赋权与筛选,构建包含环境影响、排水能力、适应及修复能力3个影响要素及管龄和维护管理水平等14个子指标的健康状况评估体系。利用遗传算法优化BP神经网络,建立基于数据驱动的污水管道系统健康状况评估模型,并以北方某市污水管道系统为例进行仿真模拟,结果表明,研究区域内污水管道系统健康度Ⅰ、Ⅱ、Ⅲ、Ⅳ级管道占比分别为28.28%、62.39%、7.00%和2.33%;评估结果与实际情况比对,预测准确率91.63%。Health assessment of sewage pipeline system is the core and basis for solving urban water pollution,waterlogging disaster and other urban diseases in the background of black-odor water treatment and urban physical examination.Taking the sewerage system as the research object,according to CCTV(closed-circuit television)test results,using Analytic Hierarchy Process(AHP)for weighting and selection,environmental impact,drainage ability,adapt to the building contains and three influence factors of the ability to repair,and 14 sub-indexes of the health of the evaluation system such as pipe age,maintenance management level.A genetic algorithm(GA)was used to optimize BP neural network,and a data-driven health status assessment model of the sewage pipeline system was established.The pipeline systems in northern cities as an example to carry on the simulation,the results show that the study area in the sewer system health Ⅰ,Ⅱ,Ⅲ,Ⅳ piping proportion were 28.28%,62.39%,7.00%,and 2.33%.Compared with the actual situation,the prediction accuracy is 91.63%,which has good applicability and generalization.

关 键 词：污水管道 健康状况评估 层次分析法 遗传算法 BP神经网络 

分 类 号：TU992[建筑科学—市政工程]