Nodal Hydraulic Head Estimation through Unscented Kalman Filter for Data-driven Leak Localization in Water Networks
This work addresses leak detection in water networks, which is critical for infrastructure management, but it appears incremental as it builds on existing Kalman filter methods with specific enhancements.
The paper tackled the problem of estimating nodal hydraulic heads in water distribution networks to improve leak localization, using an Unscented Kalman Filter with dynamic weight updates, and demonstrated effectiveness in enhancing state estimation and leak localization under realistic conditions on the Modena benchmark.
In this paper, we present a nodal hydraulic head estimation methodology for water distribution networks (WDN) based on an Unscented Kalman Filter (UKF) scheme with application to leak localization. The UKF refines an initial estimation of the hydraulic state by considering the prediction model, as well as available pressure and demand measurements. To this end, it provides customized prediction and data assimilation steps. Additionally, the method is enhanced by dynamically updating the prediction function weight matrices. Performance testing on the Modena benchmark under realistic conditions demonstrates the method's effectiveness in enhancing state estimation and data-driven leak localization.