A spatial data-driven decision analysis of pipe failure management in water supply system Widyo Nugroho (a*), Christiono Utomo (b), Nur Iriawan (c)
(a) Doctoral Student of Civil Engineering Department, Institut Teknologi Sepuluh Nopember, Surabaya 60111, East Java, Indonesia
(b) Associate Professor of Civil Engineering Department, Institut Teknologi Sepuluh Nopember, Surabaya 60111, East Java, Indonesia
(c) Professor of Statistical Department, Institut Teknologi Sepuluh Nopember, Surabaya 60111, East Java, Indonesia
*widyo.nugroho[at]outlook.com
Abstract
Sustainable management of water supply system not only requires new methodologies to monitor, repair, or replace the aging infrastructure, but more importantly, must be able to assess the condition of the networks and predict their behavior over time. Among other infrastructure systems, water supply networks are one of the most critical civil infrastructure systems. Therefore, effective maintenance, repair, and updating of the physical assets on the system are essential, especially in locations where there is the potential for widespread damage. This paper aims to develop a spatial data-driven framework for decision-making analysis in water pipe failure management by focusing on the physical and operational aspects. This study analyzes the distribution of values in spatial quantities on each variable that affects pipe failure in the water service zone. The non-homogeneous Poisson process is proposed as the failure point pattern approximation. The spatial Poisson regression model accommodates two cluster characters influenced by different variables and implies various treatment actions.
Keywords: water supply system, pipe failure, spatial point pattern
Topic: Symposium on Advance of Sustainable Engineering
