Leakage Detection Using Smart Water System: Combination of Water Balance and Automated Minimum Night Flow

This paper presents a methodology for the application of the Smart Water technology to detect water leakage. This methodology consists in the use of the traditional water balance method together with the minimum night flow approach. This procedure has been applied to a large-scale pilot project conducted at the Scientific Campus of the University of Lille, which is the size of a small town. The water network of the campus is monitored by a set of sensors that record and transmit, in real-time, the hydraulic parameters of the water system. Analysis of real-time data has allowed the verification of water balance and the estimation of water losses level in the network. The paper presents an improvement of the application of the minimum night flow method, which is based on the determination of flow thresholds. A leak alarm is generated if the night flow exceeds the thresholds. This data analysis methodology provides the capability to detect the pipe bursts quickly, thereby reducing the runtime of leakage. The application of the improved method allowed the detection of 25 unreported leaks and decreased the Non-Revenue Water (NRW) level by 36%.