基于神经网络的排水管道破损诱发地陷风险评价
Risk assessment on ground collapse induced by sewer breakage based on artificial neural network models
唐洋博 1黄标 2李玮 1管梦林1
作者信息
- 1. 长江经济带生态环境国家工程研究中心,湖北 武汉 430014;中国长江三峡集团有限公司 长江生态环境工程研究中心,湖北武汉 430014
- 2. 宁波大学土木工程与地理环境学院,浙江宁波 315211
- 折叠
摘要
城市地面塌陷威胁居民生命财产安全,为甄别地面塌陷影响因素、筛查风险区域、减少潜在损失,建立了地面塌陷风险评价方法.以衡阳市为例,收集整理了排水管网基础数据,采用人工神经网络算法预测管网破损尺寸,并通过逻辑回归算法预测管网管周地面塌陷风险发生率.结果表明:人工神经网络模型训练集预测值与真实值的平均方差为0.026,逻辑回归模型预测的地面塌陷风险与管道破损位置高度相关;衡阳市城西排水分区及酃湖排水分区地面塌陷发生率高,地面塌陷诱因包括管道破损、路面荷载、极端降雨、高速水流等.研究成果可为长江中游城市管网管周地面塌陷的防治工作提供科学依据.
Abstract
Urban ground collapses pose significant threats to human life and property safety.To identify the influence indicators of ground collapse,find out risk areas,and reduce potential disaster losses,a ground collapse risk assessment method was estab-lished.Taking Hengyang City as an example,the basic data of the drainage network were collected.The artificial neural network(ANN)was used to predict the size of the sewer breakage,and the logistic regression algorithm was used to predict the occurrence rate of ground collapse around the sewer.The results show that the average variance between the ANN predicted values and the true values is 0.026,and the ground collapse risk is highly correlated with the sewer breakage according to the logistic regression algorithm.The Chengxi and Linhu drainage areas have the high risk of ground collapse,which might be caused by sewer breakage,surface loading,extreme rainfall,high-speed flow,etc.This study provides support for the prevention and control of ground col-lapse in urban areas of the middle reaches of the Changjiang River.
关键词
排水管道/管网破损/地面塌陷/人工神经网络/预防措施/城市排水系统/衡阳市Key words
drainage sewer/sewer breakage/ground collapse/artificial neural network/prevention measures/urban drainage system/Hengyang City引用本文复制引用
基金项目
国家重点研发计划项目(2022YFC30300)
中国长江三峡集团有限公司科研项目(NBWL202300013)
宁波大学浙江省-加拿大可持续城市排水联合实验室开放基金项目()
出版年
2024
国家科技期刊平台
NSTL
万方数据