Combined Usage of Hydraulic Model Calibration Residuals and Improved Vector Angle Method for Burst Detection and Localization in Water Distribution Systems

This paper proposes a combined usage of the hydraulic model calibration residuals and an improved vector angle method for the Battle of the Leakage Detection and Isolation Methods (BattLeDIM). The proposed method starts with the hydraulic model decomposition and followed by data partition, with both procedures aimed at simplifying the BattLeDIM problem. Next, a calibration residuals-based burst detection approach is used, in which the nodal demands of the hydraulic model are calibrated in real-time using a newly developed algorithm based on prior information. The burst detection is achieved by identifying the anomalous calibration residuals. Finally, the locations of pipe bursts are approximated by an improved vector angle method, which compares the angle between each pipe's sensitivity vector and the vector of calibration residuals. Application results to the BattLeDIM problem indicate the proposed method is effective and efficient in burst detection and localization, with nearly all abrupt bursts (9 out of the total 19 bursts) in 2019 being successfully detected within 5-10 min after their occurrence, and 7 out of 10 detected bursts being localized with a spatial difference less than 300 m from the true burst pipes. Performance comparisons with the Kalman filtering-based burst detection method have been conducted, and the obtained results indicate the proposed method has better performance under both consistent and varying operation conditions, as well as in detectability for small bursts. Lessons learned from this battle and future works are summarized towards the development of a more effective and robust burst detection and localization method.

Automated summary

This study proposes a combined usage of hydraulic model calibration residuals and an improved vector angle method for leakage detection and isolation. The method simplifies the problem by decomposing the hydraulic model and partitioning the data. Burst detection is done using calibration residuals, with burst locations approximated by the improved vector angle method. Application results demonstrate the effectiveness of the proposed method in burst detection and localization.