Sensors and artificial intelligence (AI) could help detect leaks in water distribution pipes, according to a research paper published in the Urban Water Journal.
Developed by researchers at the University of Waterloo and industry partners, the new system has the potential to detect even small leaks in pipes.
The technology combines sophisticated signal processing techniques and AI software to identify signs of leaks carried via sound in water pipes.
“This would allow cities to use their resources for maintenance and repairs much more effectively,” said lead researcher Roya Cody, a civil engineering PhD candidate at the Canadian university. “They could be more proactive as opposed to reactive.”
Municipal water systems in Canada currently lose an average of over 13% of their clean water between treatment and delivery due to leaks, bursts and other issues. In the UK, the figure is about 23%.
As the University of Waterloo explains, major problems such as burst pipes are revealed by pressure changes, volume fluctuations or water simply bubbling to the surface. However, small leaks often go undetected for years because they do not produce any appreciable flow or pressure changes at the monitored locations.
Changes in the monitoring data, background noise, and the uncertainties in interpreting sensory information all add further complexity when it comes to detecting leaks.
So why do we need to trace smaller leaks at all?
It’s not just about saving the water company money, or the environmental benefits of not wasting treated water: chronic leaks can create health hazards, do damage to the foundations of structures, and get worse over time.
The new system works by pre-processing acoustic data using advanced signal processing techniques to highlight components associated with leaks. Machine learning algorithms can then identify leaks by distinguishing their signs from the many other sources of noise in a water distribution system.
Researchers are currently doing field tests with the technology after reliably detecting leaks as small as 17 litres a minute in the lab.
They are also working on ways to pinpoint the location of leaks, which would allow water companies to identify, prioritise and carry out repairs.