Smart water technology has the capacity to save millions of dollars by preventing water damage. Discover how we're working with Xylem to estimate wave arrival time, and safeguard Singapore.
The Straits Times in Singapore reported that Singapore's national plan to harness artificial intelligence (AI) technologies for social and economic benefits will position it to be a regional and global leader.
Damages from water loss have been reported at approximately 20%-30% of the total water supplied in different countries.
This is a costly problem due to the wastage of natural resources. And, in some cases, damages have reached nearly several million US dollars worth as water lost damages the environment, causing service disruption and increase unnecessary energy cost and carbon footprint.
Therefore, an effective leak detection and localization system has the potential to save a large quantity of water, as well as money.
What can smart water technologies do?
Given the importance of water sustainability, it makes sense that nations look to improve the reliability of their water resources.
This is where smart water technologies come in. Smart water technologies detect leaks, reduce non-revenue water, and much more.
Here in Singapore, we're working with Xylem, a leading global water technology company whose solutions move, treat, analyse and monitor water.
With Xylem's funding - and funding from the Singapore Economic Development Board - we've established a new PhD project that aims to improve the reliability of water leakage detection.
How are water leakages detected?
Leakages can be classified as either reported leakage, unreported leakage or background leakage.
- A reported burst event is usually visible on the ground, so it's easily detected by maintenance personnel or the public.
- An unreported burst event is the same, but unlike a reported burst, it does not surface to the ground.
- A background type leakage is a small leakage that's difficult or cannot be detected through normal methods, such as leakage through creeping joints.
As for leak detection, it can be classified into passive and active systems.
The former requires direct visual inspection or monitoring of sites. However the latter analyses signals, such as acoustic signals, vibration, flow and pressure measurement. Active systems can be further classified into mainly transient-based approaches, model-based approaches, and data-driven approaches.
Intelligent real-time water leakage detection
Due to the noisy and fluctuating nature of the pressure signals, estimating an accurate transient pressure wave arrival time is not a trivial task.
Among many methodologies proposed for detecting abrupt pressure changes, Discrete Wavelet Transform (DWT) and Cumulative Sum (CUSUM) were the two most popular approaches.
However, several limitations involved with these two approaches can easily lead to unsatisfactory results. Some of the existing methodologies were only tested on either a single pipeline, engineered events, or a small sample size. So these methodologies are only suitable and accurate for a limited number of scenarios.
Driven by these limitations, our project proposed to estimate the wave arrival time in water distribution networks (WDNs). The backbone of this approach is the integration of wavelet decomposition and a knee point detection algorithm, thus gaining the name WAvelet kNEe (WANE).
Based on the result, our estimation error is at least 15 seconds lesser than the other methodologies. With an improved wave arrival time estimation, WANE has the potential to minimize the response time of repair crews, service disruption time, and the associated water losses of a pipe break.
Our partnership with Xylem
I have a long-standing connection with Xylem that started when Xylem began conversations about collaboration at PhD level.
Xylem are a Fortune 1000 global water technology provider with one mission: to solve water through the power of technology and expertise. In doing so, they can make water more accessible and affordable, and communities more resilient.
In this high-tech environment, there are many opportunities for research projects.
We work with an excellent team for the project including:
- Dr Cheng Chin, Reader in Intelligent Systems Modelling and Design, brings expertise in electronics and artificial intelligence
- High-achieving graduates, Teck Kai Chan and Xing Yong Kek, were recruited as a PhD student for the project.
The project is progressing successfully, and we are exploring more collaborative research projects between Newcastle University in Singapore and Xylem.
Find out more
- Dr Cheng Chin – Reader in Intelligent Systems Modelling and Design
- How Newcastle University works with business
