Scholarlink

<p>Water distribution network (WDN) leaks can lead to water loss, reduced pressure, increased repair costs, and potential contamination. Identifying and resolving unreported leaks is a significant challenge for water utilities. However, traditional leak detection methods are often expensive, time-consuming, and require specialized expertise. As a result, hydraulic simulation methods have gained popularity for leak detection. This study employs a hydraulic model calibration method that establishes an objective function based on minimizing the variance between field and simulated data. The function is optimized using meta-heuristic algorithms. The effectiveness of various algorithms was compared to identify the most efficient option for addressing hydraulic and leak detection challenges. To ensure a comprehensive comparison, the Chess Ranking System for Evolutionary Algorithms (CRS4EAs) was used to analyze 45 random leakage scenarios across three WDNs. The results showed that the Equilibrium Optimizer&#xa0;(EO) algorithm outperformed others in terms of optimal solutions, reliability in single runs, and operational efficiency. Therefore, to reduce the computational time and ensure the highest level of reliability in detecting leaks in WDNs, the EO algorithm is recommended for use in the optimization-calibration approach. Results of this study can be used for the development of new leak detection methods in WDNs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Improving the detection of leaks in water distribution networks using a meta-heuristic optimization-calibration method

  • 期刊论文

  • 发表日期：

    2025年10月3日

查看全文
  • M. Nasiri Dahaj,
  • M. Jalili Ghazizadeh,
  • E. Jabbari,
  • R. Moasheri,
  • A. Rezaeizadeh

摘要

Water distribution network (WDN) leaks can lead to water loss, reduced pressure, increased repair costs, and potential contamination. Identifying and resolving unreported leaks is a significant challenge for water utilities. However, traditional leak detection methods are often expensive, time-consuming, and require specialized expertise. As a result, hydraulic simulation methods have gained popularity for leak detection. This study employs a hydraulic model calibration method that establishes an objective function based on minimizing the variance between field and simulated data. The function is optimized using meta-heuristic algorithms. The effectiveness of various algorithms was compared to identify the most efficient option for addressing hydraulic and leak detection challenges. To ensure a comprehensive comparison, the Chess Ranking System for Evolutionary Algorithms (CRS4EAs) was used to analyze 45 random leakage scenarios across three WDNs. The results showed that the Equilibrium Optimizer (EO) algorithm outperformed others in terms of optimal solutions, reliability in single runs, and operational efficiency. Therefore, to reduce the computational time and ensure the highest level of reliability in detecting leaks in WDNs, the EO algorithm is recommended for use in the optimization-calibration approach. Results of this study can be used for the development of new leak detection methods in WDNs.