Deep learning identifies accurate burst locations in water distribution networks

Xiao Zhou; Zhenheng Tang; Weirong Xu; Fanlin Meng; Xiaowen Chu; Kunlun Xin; Guangtao Fu

doi:10.1016/j.watres.2019.115058

Deep learning identifies accurate burst locations in water distribution networks

Water Res. 2019 Dec 1:166:115058. doi: 10.1016/j.watres.2019.115058. Epub 2019 Sep 6.

Authors

Xiao Zhou¹, Zhenheng Tang², Weirong Xu³, Fanlin Meng⁴, Xiaowen Chu², Kunlun Xin⁵, Guangtao Fu⁶

Affiliations

¹ College of Environmental Science and Engineering, Tongji University, 200092, Shanghai, China; Centre for Water Systems, College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, EX4 4QF, UK.
² Department of Computer Science, Hong Kong Baptist University, Hong Kong, China.
³ College of Environmental Science and Engineering, Tongji University, 200092, Shanghai, China.
⁴ Centre for Water Systems, College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, EX4 4QF, UK. Electronic address: m.fanlin@exeter.ac.uk.
⁵ College of Environmental Science and Engineering, Tongji University, 200092, Shanghai, China; Shanghai Institute of Pollution Control and Ecological Security, 200092, Shanghai, China. Electronic address: xkl@mail.tongji.edu.cn.
⁶ Centre for Water Systems, College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, EX4 4QF, UK; The Alan Turing Institute, 96 Euston Road, London, NW1 2DB, UK.

PMID: 31536886
DOI: 10.1016/j.watres.2019.115058

Abstract

Pipe bursts in water distribution networks lead to considerable water loss and pose risks of bacteria and pollutant contamination. Pipe burst localisation methods help water service providers repair the burst pipes and restore water supply timely and efficiently. Although methods have been reported on burst detection and localisation, there is a lack of studies on accurate localisation of a burst within a potential district by accessible meters. To address this, a novel Burst Location Identification Framework by Fully-linear DenseNet (BLIFF) is proposed. In this framework, additional pressure meters are placed at limited, optimised places for a short period (minutes to hours) to monitor system behaviour after the burst. The fully-linear DenseNet (FL-DenseNet) newly developed in this study modifies the state-of-the-art deep learning algorithm to effectively extract features in the limited pressure signals for accurate burst localisation. BLIFF was tested on a benchmark network with different parameter settings, which showed that accurate burst localisation results can be achieved even with high model uncertainties. The framework was also applied to a real-life network, in which 57 of the total 58 synthetic bursts in the potential burst district were correctly located when the top five most possible pipes are considered and among them, 37 were successfully located when considering only the top one. Only one failed because of the very small pipe diameter and remote location. Comparisons with DenseNet and the traditional fully linear neural network demonstrate that the framework can effectively narrow the potential burst district to one or several pipes with good robustness and applicability. Codes are available at https://github.com/wizard1203/waternn.

Keywords: Burst localisation; Deep learning; DenseNet; Pipe burst; Water distribution network.

MeSH terms

Algorithms
Deep Learning*
Neural Networks, Computer
Water Supply
Water*

Substances

Water