A Two-Stage Model for Data-Driven Leakage Detection and Localization in Water Distribution Networks and Introduction to Leak Detection Dashboard
Prerna Pandey is a postdoc from IISc Bangalore working on the DP-Trans project together with Nikolaj, Sander, and Kees. She is visiting CWI for two weeks and will in this regard present her work in person (and online).
Her area of research is water distribution networks with a focus on leak detection, demand forecasting, and calibration.
Join Zoom Meeting
https://cwi-nl.zoom.us/j/9508871194?pwd=K3JRbG90RURuY2FuTWpMU1ZqT3JpUT09
Water utilities face the challenge of reducing water losses by promptly detecting, localizing, and repairing leaks during their operational stage. To address this challenge, utilities are exploring alternative approaches to detect leaks with high accuracy in a timely manner, while minimizing environmental and economic consequences. In this study, we propose a data-driven two-stage model that leverages pressure and flow rate data monitored at several locations in most water distribution networks (WDNs) to predict the occurrence and location of leaks. The first stage involves computing the errors in predicting pressure heads, while the second stage uses statistical measures in the error distributions to classify the leak occurrence and location. The proposed approach is cost-effective and can be readily deployed. Simulation-based case studies are used to demonstrate the effectiveness of the proposed model on several benchmark networks. The results of this approach indicate that the model accurately predicts the occurrence and location of leaks. The precision of leak prediction has been evaluated by examining its sensitivity to varying numbers of sensors and different levels of noise. However, the model's performance decreases as the network size increases, leading to reduced accuracy.
To showcase the practical application of this model by industry experts, we have developed an interactive dashboard that visualizes the data collected from sensors (Flow and pressure sensors) and presents simulations of water networks, including the location of leaks in the water pipeline.
Keywords: EPANET simulation; leakage identification and localization; IOT Sensors; Statistical measure.
