Pipe Failure Prediction in the Water Distribution System Using a Deep Graph Convolutional Network and Temporal Failure Series

IF 7.4 Q1 ENGINEERING, ENVIRONMENTAL ACS ES&T engineering Pub Date : 2024-08-27 DOI:10.1021/acsestengg.4c00234
Yanran Xu, Zhen He
{"title":"Pipe Failure Prediction in the Water Distribution System Using a Deep Graph Convolutional Network and Temporal Failure Series","authors":"Yanran Xu, Zhen He","doi":"10.1021/acsestengg.4c00234","DOIUrl":null,"url":null,"abstract":"Ensuring the safety and reliability of the water distribution system (WDS) manifests significant importance for residential, commercial, and industrial needs and may benefit from the structure deterioration models for early warning of water pipe breaks. However, challenges exist in model calibration with limited monitoring data, unseen underground conditions, or high computing requirements. Herein, a novel deep learning-based DeeperGCN framework was proposed to predict pipe failure by cooperating with graph convolutional network (GCN) models for graph processing. The DeeperGCN model achieved much deeper architectures and was designed to utilize spatial and temporal data simultaneously. Two graph representation methods and three GCN models were compared, showing the best predictions with the “Pipe_as_Edge” method and the DeeperGEN model. To identify the priority of pipe maintenance directly, the prediction targets were assigned as a binary classification question to determine break or not over 1-, 3-, and 5-year periods, with prediction accuracies of 96.91, 96.73, and 97.23%, respectively. The issue of data imbalance was observed and addressed through varied evaluation metrics, resulting in the weighted F1 scores >0.96. The DeeperGCN framework demonstrated potential applications in visualizing pipe failure prediction with high accuracies of 97.09, 96.31, and 97.81% across three periods in 2015, for example.","PeriodicalId":7008,"journal":{"name":"ACS ES&T engineering","volume":null,"pages":null},"PeriodicalIF":7.4000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS ES&T engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1021/acsestengg.4c00234","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Ensuring the safety and reliability of the water distribution system (WDS) manifests significant importance for residential, commercial, and industrial needs and may benefit from the structure deterioration models for early warning of water pipe breaks. However, challenges exist in model calibration with limited monitoring data, unseen underground conditions, or high computing requirements. Herein, a novel deep learning-based DeeperGCN framework was proposed to predict pipe failure by cooperating with graph convolutional network (GCN) models for graph processing. The DeeperGCN model achieved much deeper architectures and was designed to utilize spatial and temporal data simultaneously. Two graph representation methods and three GCN models were compared, showing the best predictions with the “Pipe_as_Edge” method and the DeeperGEN model. To identify the priority of pipe maintenance directly, the prediction targets were assigned as a binary classification question to determine break or not over 1-, 3-, and 5-year periods, with prediction accuracies of 96.91, 96.73, and 97.23%, respectively. The issue of data imbalance was observed and addressed through varied evaluation metrics, resulting in the weighted F1 scores >0.96. The DeeperGCN framework demonstrated potential applications in visualizing pipe failure prediction with high accuracies of 97.09, 96.31, and 97.81% across three periods in 2015, for example.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用深度图卷积网络和时态故障序列预测输水系统中的管道故障
确保配水系统(WDS)的安全性和可靠性对住宅、商业和工业需求具有重要意义,而结构劣化模型可用于水管破裂的早期预警。然而,在监测数据有限、地下条件不可见或计算要求高的情况下,模型校准存在挑战。本文提出了一种基于深度学习的新型 DeeperGCN 框架,通过与图卷积网络(GCN)模型合作进行图处理来预测管道故障。DeeperGCN 模型实现了更深层次的架构,旨在同时利用空间和时间数据。对两种图表示方法和三种 GCN 模型进行了比较,结果表明 "Pipe_as_Edge "方法和 DeeperGEN 模型的预测效果最佳。为了直接确定管道维护的优先级,预测目标被分配为一个二元分类问题,以确定在 1 年、3 年和 5 年期间是否断裂,预测准确率分别为 96.91%、96.73% 和 97.23%。通过不同的评估指标观察和解决了数据不平衡问题,加权 F1 分数为 0.96。DeeperGCN 框架在可视化管道故障预测方面展示了潜在的应用前景,例如在 2015 年的三个时段中,预测准确率分别高达 97.09%、96.31% 和 97.81%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
ACS ES&T engineering
ACS ES&T engineering ENGINEERING, ENVIRONMENTAL-
CiteScore
8.50
自引率
0.00%
发文量
0
期刊介绍: ACS ES&T Engineering publishes impactful research and review articles across all realms of environmental technology and engineering, employing a rigorous peer-review process. As a specialized journal, it aims to provide an international platform for research and innovation, inviting contributions on materials technologies, processes, data analytics, and engineering systems that can effectively manage, protect, and remediate air, water, and soil quality, as well as treat wastes and recover resources. The journal encourages research that supports informed decision-making within complex engineered systems and is grounded in mechanistic science and analytics, describing intricate environmental engineering systems. It considers papers presenting novel advancements, spanning from laboratory discovery to field-based application. However, case or demonstration studies lacking significant scientific advancements and technological innovations are not within its scope. Contributions containing experimental and/or theoretical methods, rooted in engineering principles and integrated with knowledge from other disciplines, are welcomed.
期刊最新文献
Issue Editorial Masthead Issue Publication Information Kinetics of Fluorapatite Precipitation in Fluoride-Contaminated Water Porous Iron Electrodes Reduce Energy Consumption During Electrocoagulation of a Virus Surrogate: Insights into Performance Enhancements Using Three-Dimensional Neutron Computed Tomography Porous Iron Electrodes Reduce Energy Consumption During Electrocoagulation of a Virus Surrogate: Insights into Performance Enhancements Using Three-Dimensional Neutron Computed Tomography.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1