A comparison between joint and dual UKF implementations for state estimation and leak localization in water distribution networks

2025-10-28

AI Summary

This study addresses state estimation and leakage localization in urban water distribution networks. We propose and comparatively evaluate two data-driven approaches based on the unscented Kalman filter (UKF): a joint-estimation architecture and a dual-filter architecture. Both methods fuse pressure, flow, and water consumption sensor measurements while coupling with a hydraulic model to jointly estimate nodal heads and pipe flows and localize leaks. Experiments on the L-TOWN benchmark network show that the joint UKF achieves higher estimation accuracy but incurs significantly higher computational cost; in contrast, the dual UKF maintains competitive localization accuracy while substantially reducing real-time computational overhead. To our knowledge, this work is the first to systematically quantify the trade-offs among estimation accuracy, computational efficiency, and engineering deployability across these two UKF architectures. The results provide both theoretical insights and practical guidance for selecting appropriate filtering frameworks in intelligent water network monitoring systems.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

The sustainability of modern cities highly depends on efficient water distribution management, including effective pressure control and leak detection and localization. Accurate information about the network hydraulic state is therefore essential. This article presents a comparison between two data-driven state estimation methods based on the Unscented Kalman Filter (UKF), fusing pressure, demand and flow data for head and flow estimation. One approach uses a joint state vector with a single estimator, while the other uses a dual-estimator scheme. We analyse their main characteristics, discussing differences, advantages and limitations, and compare them theoretically in terms of accuracy and complexity. Finally, we show several estimation results for the L-TOWN benchmark, allowing to discuss their properties in a real implementation.

Problem

• Comparing joint and dual UKF for water network state estimation
• Evaluating leak localization methods in water distribution systems
• Analyzing hydraulic state estimation accuracy and computational complexity

Innovation

• Joint UKF with single estimator for state estimation
• Dual UKF scheme for leak localization
• Fusing pressure demand flow data via UKF