Author: Symeon Christodoulou, Anastasios Gagatsis, Agathoklis Agathokleous, Savvas Xanthos & Sofia Kranioti
File: Click Here
The work presented herein investigates the use of spatio-temporal analysis as a decision support tool for increasing the efficiency of maintenance strategies (“repair or replace” decisions) related to urban water distribution networks (UWDN). The analyses used utilize both classical statistical tools and neurofuzzy systems, but also spatial analysis and GIS-based data clustering for improved results. The study investigates UWDN in two urban locales, under both normal and abnormal operating conditions as manifested by the effects of intermittent water supply on the performance and fragility of such networks. The spatio-temporal analysis examines the resulting water losses, the inefficiencies and the overall maintenance cost during the aforementioned operating conditions and it is based on a six-year dataset (2003-2010) including thousands of pipe failure incidents. The spatio-temporal analysis, further to showing an increase in the number of water-leak incidents during and immediately after the years of enacting intermittent water supply policies, it allows for spatio-temporal clustering and pattern recognition, it helps devise repair-or-replace strategies and it reinforces the belief that intermittent supply increases the vulnerability of UWDN.