Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The impact of sensor placement on graph-neural-network-based leakage detection

J. J. H. van Gemert, V. Breschi, D. R. Yntema, K. J. Keesman, M. Lazar

Abstract

Sensor placement for leakage detection in water distribution networks is an important and practical challenge for water utilities. Recent work has shown that graph neural networks can estimate and predict pressures and detect leaks, but their performance strongly depends on the available sensor measurements and configurations. In this paper, we investigate how sensor placement influences the performance of GNN-based leakage detection. We propose a novel PageRank-Centrality-based sensor placement method and demonstrate that it substantially impacts reconstruction, prediction, and leakage detection on the EPANET Net1.

The impact of sensor placement on graph-neural-network-based leakage detection

Abstract

Sensor placement for leakage detection in water distribution networks is an important and practical challenge for water utilities. Recent work has shown that graph neural networks can estimate and predict pressures and detect leaks, but their performance strongly depends on the available sensor measurements and configurations. In this paper, we investigate how sensor placement influences the performance of GNN-based leakage detection. We propose a novel PageRank-Centrality-based sensor placement method and demonstrate that it substantially impacts reconstruction, prediction, and leakage detection on the EPANET Net1.
Paper Structure (13 sections, 25 equations, 8 figures, 2 tables, 1 algorithm)

This paper contains 13 sections, 25 equations, 8 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Preliminaries and Problem Statement
  3. Basic graph notions $\&$ WDNs
  4. Problem formulation
  5. Main results
  6. PageRank-Centrality-based Sensor Placement
  7. ChebNet Architecture for Pressure Reconstruction and Prediction
  8. Consistent Graph Construction for PageRank and ChebNet
  9. Simulation results
  10. Sensor placement and training
  11. Testing of the reconstructor and predictor
  12. Leakage simulation setup and detection
  13. Conclusion and Future Work

Figures (8)

  • Figure 1: Illustration of EPANET Net1 WDN consisting of two reservoirs/tanks (black icons), one pump (black circle), and junctions (blue circles) connected through pipes (blue lines).
  • Figure 2: Processing pipeline from WDN topology to Chebnet input.
  • Figure 3: ChebNet architecture for pressure reconstruction and prediction in water distribution networks (WDNs).
  • Figure 4: Training and validation loss on a logarithmic scale for the reconstructor (a) and predictor (b), using PageRank-Centrality-based sensor placement.
  • Figure 5: Residual distributions for the four GNNs on Net1, shown as violin plots over all junctions in (a) and over non-sensed junctions in (b).
  • ...and 3 more figures