Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

`Just One More Sensor is Enough' -- Iterative Water Leak Localization with Physical Simulation and a Small Number of Pressure Sensors

Michał Cholewa, Michał Romaszewski, Przemysław Głomb, Katarzyna Kołodziej, Michał Gorawski, Jakub Koral, Wojciech Koral, Andrzej Madej, Kryspin Musioł

TL;DR

This work tackles leak localization in water distribution networks using very few pressure sensors by leveraging hydraulic simulations (EPANET) and an iterative mobile-sensor relocation scheme. The authors introduce a two-stage approach: a basic RMSE-based localization using simulated pressure matrices P^{sw} and a sequential extension that moves a single mobile sensor toward the most probable leak location, refining estimates over iterations. Key findings show that relocating one mobile sensor significantly improves localization, achieving average detection distances around a few hundred meters and ranking leaks highly even with only 1–3 stationary sensors, as demonstrated on simulated data and real BattLeDIM/L-Town measurements. The approach offers a practical strategy for resource-constrained networks, enabling accurate leak localization without extensive sensor deployments, and highlights directions for improving single-iteration performance and sensor-placement strategies.

Abstract

In this article, we propose an approach to leak localisation in a complex water delivery grid with the use of data from physical simulation (e.g. EPANET software). This task is usually achieved by a network of multiple water pressure sensors and analysis of the so-called sensitivity matrix of pressure differences between the network's simulated data and actual data of the network affected by the leak. However, most algorithms using this approach require a significant number of pressure sensors -- a condition that is not easy to fulfil in the case of many less equipped networks. Therefore, we answer the question of whether leak localisation is possible by utilising very few sensors but having the ability to relocate one of them. Our algorithm is based on physical simulations (EPANET software) and an iterative scheme for mobile sensor relocation. The experiments show that the proposed system can equalise the low number of sensors with adjustments made for their positioning, giving a very good approximation of leak's position both in simulated cases and real-life example taken from BattLeDIM competition L-Town data.

`Just One More Sensor is Enough' -- Iterative Water Leak Localization with Physical Simulation and a Small Number of Pressure Sensors

TL;DR

This work tackles leak localization in water distribution networks using very few pressure sensors by leveraging hydraulic simulations (EPANET) and an iterative mobile-sensor relocation scheme. The authors introduce a two-stage approach: a basic RMSE-based localization using simulated pressure matrices P^{sw} and a sequential extension that moves a single mobile sensor toward the most probable leak location, refining estimates over iterations. Key findings show that relocating one mobile sensor significantly improves localization, achieving average detection distances around a few hundred meters and ranking leaks highly even with only 1–3 stationary sensors, as demonstrated on simulated data and real BattLeDIM/L-Town measurements. The approach offers a practical strategy for resource-constrained networks, enabling accurate leak localization without extensive sensor deployments, and highlights directions for improving single-iteration performance and sensor-placement strategies.

Abstract

In this article, we propose an approach to leak localisation in a complex water delivery grid with the use of data from physical simulation (e.g. EPANET software). This task is usually achieved by a network of multiple water pressure sensors and analysis of the so-called sensitivity matrix of pressure differences between the network's simulated data and actual data of the network affected by the leak. However, most algorithms using this approach require a significant number of pressure sensors -- a condition that is not easy to fulfil in the case of many less equipped networks. Therefore, we answer the question of whether leak localisation is possible by utilising very few sensors but having the ability to relocate one of them. Our algorithm is based on physical simulations (EPANET software) and an iterative scheme for mobile sensor relocation. The experiments show that the proposed system can equalise the low number of sensors with adjustments made for their positioning, giving a very good approximation of leak's position both in simulated cases and real-life example taken from BattLeDIM competition L-Town data.
Paper Structure (23 sections, 2 equations, 4 figures, 2 tables)

This paper contains 23 sections, 2 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Iterative leak localization algorithm
  3. Simulations
  4. Basic algorithm for leak localization
  5. Preliminaries
  6. Input
  7. Step 1: Calculating pressure matrices
  8. Step 2: Calculating measures of similarity
  9. Result
  10. Proposed extension to the basic algorithm with iterative use of pressure matrix
  11. First iteration
  12. The shift
  13. Subsequent iteration
  14. Results
  15. Dataset description
  16. ...and 8 more sections

Figures (4)

  • Figure 1: The impact of the number of available sensors and algorithm iteration on its performance measures: detection distance, distance of the closes sensor to the leak node, node rank.
  • Figure 2: Visualisation of the relationships between leak detection distance, leak node rank and distance of the leak to the nearest sensor. Every dot represents averaged result for five repetitions of the experiment with different initial position of sensors.
  • Figure 3: Visualisation of the leak detection/localisation results.
  • Figure 4: Examples of simulated leak localisation for links: p457, p896, p843. Colours represent average node ranks over 5 iterations with different placement of three sensors (one mobile, two stationary).