A distributed analysis of vibration signals for leakage detection in Water Distribution Networks

Abstract. It is well known that Water Distribution Networks (WDNs) are very inefficient and, in Italy, 40% of water lost during distribution. In this paper, we present a solution for detecting leakages WDNs, based on three main components: i) an innovative sensing element to be deployed at the sensor nodes, which analyses vibrations acoustic range classifying external noise sources, induced by leakages, means suitable machine learning techniques; ii) Internet Things (IoT) system sensors, junctions comparing measurements collected different critical points network; iii) algorithm processing data. After definition WDN structure, introduce some numerical simulation tools studying our and modeling proposed solution. Given geometry, physical properties (pipe lengths, diameters, roughness, reservoir shapes levels, pump valve characteristic curves) nodal demands, tool able compute pipes or nodes over time. parallel, simulate IoT coupled WDN, logging partial information about status, corresponds demand readings edge junction together with (optional) elements. On basis data, analyze possibility identifying network, even without knowing exact complete topology WDN. Our exploits techniques devised indirectly retrieve topological information, correlating balance flows as varies