Machine Learning and Simulation-Optimization Coupling for Water Distribution Network Contamination Source Detection.

Luka Grbčić,Siniša Družeta,Lado Kranjčević

doi:10.3390/s21041157

Abstract

This paper presents and explores a novel methodology for solving the problem of a water distribution network contamination event, which includes determining the exact source of contamination, the contamination start and end times and the injected contaminant concentration. The methodology is based on coupling a machine learning algorithm for predicting the most probable contamination sources in a water distribution network with an optimization algorithm for determining the values of contamination start time, end time and injected contaminant concentration for each predicted node separately. Two slightly different algorithmic frameworks were constructed which are based on the mentioned methodology. Both algorithmic frameworks utilize the Random Forest algorithm for classification of top source contamination node candidates, with one of the frameworks directly using the stochastic fireworks optimization algorithm to determine the contamination start time, end time and injected contaminant concentration for each predicted node separately. The second framework uses the Random Forest algorithm for an additional regression prediction of each top node’s start time, end time and contaminant concentration and is then coupled with the deterministic global search optimization algorithm MADS. Both a small sized (92 potential sources) network with perfect sensor measurements and a medium sized (865 potential sources) benchmark network with fuzzy sensor measurements were used to explore the proposed frameworks. Both algorithmic frameworks perform well and show robustness in determining the true source node, start and end times and contaminant concentration, with the second framework being extremely efficient on the fuzzy sensor measurement benchmark network.

Highlights

Functional water supply networks are essential for a proper urban environment and the population that inhabits it
The framework was repeatedly run for 100 times and for all runs the true source node was in the top 10 of the potential source nodes predicted by the Random Forests (RF) classifier and it was found in 99 out of 100 times after the simulation-optimization process had finished
The absolute error is the absolute distance from the contamination event parameters presented in Table 1 and it can be seen that the RF regression overestimates all of the three parameters, which is an additional proof that in order to reconstruct the whole contamination event scenario accurately, the simulation-optimization procedure is necessary

Summary

Introduction

Functional water supply networks are essential for a proper urban environment and the population that inhabits it. Monitoring the quality of water in the water supply network, and in case of contamination, identifying and controlling the source and contamination propagation is an extremely important task for human health and safety. Water supply network security methodologies heavily rely on accurate water quality models and pipe network hydraulic simulators. A thorough and recent review of methodologies for water supply network quality modeling with contamination source detection can be found in [14] and a general, recent thorough review of water supply network security research and methods are covered in [15]

Methods

Results

Conclusion