Leak detection in water supply networks using two-stage temporal segmentation and incremental learning for non-stationary acoustic signals

IF 8.2 2区 环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL
Xingke Ma , Yipeng Wu , Guancheng Guo , Shuming Liu , Yuexia Xu , Jingjing Fan , Hongbin Wang , Liren Xu
{"title":"Leak detection in water supply networks using two-stage temporal segmentation and incremental learning for non-stationary acoustic signals","authors":"Xingke Ma ,&nbsp;Yipeng Wu ,&nbsp;Guancheng Guo ,&nbsp;Shuming Liu ,&nbsp;Yuexia Xu ,&nbsp;Jingjing Fan ,&nbsp;Hongbin Wang ,&nbsp;Liren Xu","doi":"10.1016/j.wroa.2025.100333","DOIUrl":null,"url":null,"abstract":"<div><div>Acoustic detection is a primary method for identifying leaks in urban water supply networks. However, acoustic signals within pipelines are highly susceptible to dynamic interference noise. This complicates the differentiation between leak and non-leak signals. To address this challenge, this paper presents a temporal segmentation-based approach for processing acoustic signals. Specifically, the two-stage temporal segmentation approach, which applies long-term segments to isolate non-stationary characteristics and short-term segments for capturing quasi-stationary features in acoustic signals, is introduced. We then applied the CNN model to recognize the Mel spectrogram features of the two-stage segmented signals and compared its performance with other models. Results indicate that this approach enhances both the accuracy and stability of leak detection, with the model achieving an average detection accuracy of 95 %. Moreover, the model is designed as an adaptive and continuous learning model, integrating its detection outcomes and newly labeled data segments into its training dataset. In practical applications, this continuous learning capability enables the model to improve its detection efficacy over time as data volume expands.</div></div>","PeriodicalId":52198,"journal":{"name":"Water Research X","volume":"29 ","pages":"Article 100333"},"PeriodicalIF":8.2000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Water Research X","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589914725000325","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
引用次数: 0

Abstract

Acoustic detection is a primary method for identifying leaks in urban water supply networks. However, acoustic signals within pipelines are highly susceptible to dynamic interference noise. This complicates the differentiation between leak and non-leak signals. To address this challenge, this paper presents a temporal segmentation-based approach for processing acoustic signals. Specifically, the two-stage temporal segmentation approach, which applies long-term segments to isolate non-stationary characteristics and short-term segments for capturing quasi-stationary features in acoustic signals, is introduced. We then applied the CNN model to recognize the Mel spectrogram features of the two-stage segmented signals and compared its performance with other models. Results indicate that this approach enhances both the accuracy and stability of leak detection, with the model achieving an average detection accuracy of 95 %. Moreover, the model is designed as an adaptive and continuous learning model, integrating its detection outcomes and newly labeled data segments into its training dataset. In practical applications, this continuous learning capability enables the model to improve its detection efficacy over time as data volume expands.

Abstract Image

基于两阶段时间分割和非平稳声学信号增量学习的供水管网泄漏检测
声学检测是识别城市供水管网泄漏的主要方法。然而,管道内的声信号极易受到动态干扰噪声的影响。这使得区分泄漏和非泄漏信号变得复杂。为了解决这一挑战,本文提出了一种基于时间分割的声学信号处理方法。具体来说,介绍了两阶段时间分割方法,该方法使用长时间段来隔离非平稳特征,使用短时间段来捕获声信号中的准平稳特征。然后应用CNN模型对两级分割信号的Mel谱图特征进行识别,并与其他模型进行性能比较。结果表明,该方法提高了泄漏检测的准确性和稳定性,模型的平均检测准确率达到95%。此外,该模型被设计为一个自适应和持续学习模型,将其检测结果和新标记的数据段集成到其训练数据集中。在实际应用中,这种持续学习能力使模型能够随着数据量的增加而提高其检测效率。
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 求助全文
来源期刊
Water Research X
Water Research X Environmental Science-Water Science and Technology
CiteScore
12.30
自引率
1.30%
发文量
19
期刊介绍: Water Research X is a sister journal of Water Research, which follows a Gold Open Access model. It focuses on publishing concise, letter-style research papers, visionary perspectives and editorials, as well as mini-reviews on emerging topics. The Journal invites contributions from researchers worldwide on various aspects of the science and technology related to the human impact on the water cycle, water quality, and its global management.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信