Collective thinking approach for improving leak detection systems

Abstract

Water mains, especially old pipelines, are consistently threatened by the formation of leaks. Leaks inherit increased direct and indirect costs and impacts on various levels such as the economic field and the environmental level. Recently, financially capable municipalities are testing acoustic early detection systems that utilize wireless noise loggers. Noise loggers would be distributed throughout the water network to detect any anomalies in the network. Loggers provide early detection via recording and analyzing acoustic signals within the network. The city of Montreal adopted one of the leak detection projects in this domain and had reported that the main issue that hinders the installed system is false alarms. False alarms consume municipality resources and funds inefficiently. Therefore, this paper aims to present a novel approach to utilize more than one data analysis and classification technique to ameliorate the leak identification process. In this research, acoustic leak signals were analyzed using Fourier Transform, and the multiple frequency bandwidths were determined. Three models were developed to identify the state of the leak using Naïve Bayes (NB), Deep Learning (DL), and Decision Tree (DT) Algorithms. Each of the developed models has an accuracy ranging between 84% to 89%. An aggregator approach was developed to cultivate the collective approaches developed into one single answer. Through aggregation, the accuracy of leak detection improved from 89% at its best to 100%. The design, implementation approach and results are displayed in this paper. Using this method helps municipalities minimize and alleviate the costs of uncertain leak verifications and efficiently allocate their resources.

Leak detection in water distribution networks: an introductory overview

“…The aforementioned techniques have presented great success in distinguishing leaks from other noises within the water network. Additionally, when the aforementioned techniques are coupled with a collective thinking code, their accuracy may reach 100% (El-Zahab et al 2017).…”

“…Those algorithms can be paired with a wide variety of technologies such as infrared, ground penetrating radar, and noise loggers. Some of the algorithms that are used include support vector machines, artificial neural networks, and genetic algorithms (El-Abbasy et al 2016;El-Zahab et al 2017;Fahmy and Moselhi 2009;Al Hawari et al 2015. In the seventh place comes the keyword "zigzag pipeline" which refers to pipelines that are not linear and have some turns and unique shapes within their structure.…”

“…Accordingly, analysis can be conducted in a timely fashion as well or using software. In-pipe systems allow for the immediate detection of leaks and that is why they are a growing leak detection topic recently (El-Abbasy et al 2016;El-Zahab et al 2017;Srirangarajan et al 2013;Stoianov et al 2007aStoianov et al , 2007b.…”

Leak Detection Using Flow-Induced Vibrations in Pressurized Wall-Mounted Water Pipelines

“…The most commonly-used PMSs are based on pressure and flow sensors, that use transient-based analysis for abnormality detection [10]- [17]. This type of monitoring system is easy to install and gives a better sensitivity in leakage detection as compared to other techniques such as using acoustic emission measurements [18]- [22], groundpenetrating radars [23]- [27] and infra-red thermography [28], [29]. All these solutions provide their own unique and intrinsic advantages, but a common disadvantage they all share is their high material, maintenance and deployment costs, specifically their need for sensor deployment at multiple locations in order to cover the entire network, which causes further logistical difficulties.…”

Do prepaid water meters improve the quality of water service delivery? The case of Nakuru, Kenya

“…The water infrastructure worldwide is riddled with leaks, which contribute to a variety of losses within the water network. Losses can be in the form of direct water dissipation, production energy losses, and losses in treatment costs (Samer et al 2017). Another challenge to water service providers expanding their services has been their lack of sufficient assets to obtain traditional financing from a bank (Heymans et al 2014).…”