Sensors combined with novel artificial intelligence (AI) technology may considerably reduce costly water losses incurred in municipal water systems.
The technology, devised by scientists at the University of Waterloo in association with industry partners, could make it possible to detect even minute leaks in pipes. It integrates AI software and advanced signal processing methods to detect obvious signs of leaks carried through sound in water pipes.
Hydrophone sensors, which are capable of recording the acoustic signatures, can be installed in present fire hydrants in an easy and cost-efficient manner without removing or taking them out of service.
This would allow cities to use their resources for maintenance and repairs much more effectively. They could be more proactive as opposed to reactive. Municipal water systems in Canada lose an average of over 13 per cent of their clean water between treatment and delivery due to leaks, bursts and other issues. Countries with older infrastructure have even higher loss rates. Major problems such as burst pipes are revealed by pressure changes, volume fluctuations or water simply bubbling to the surface, but small leaks often go undetected for years.
Roya Cody, Lead Researcher and PhD Candidate, Civil Engineering, University of Waterloo
Besides the economic expenses of wasting treated water, chronic leaks can also cause damage to the foundations of structures, pose serious health hazards, and deteriorate over time.
“By catching small leaks early, we can prevent costly, destructive bursts later on,” stated Cody.
At present, scientists are performing field tests with the hydrant sensors after the reliable detection of leaks as small as 17 l per minute in the laboratory. The team is also exploring ways to identify the sites of leaks, which would enable municipalities to detect, prioritize, and perform repairs.
Right now they react to situations by sending workers out when there is flooding or to inspect a particular pipe if it’s due to be checked because of its age.
Roya Cody, Lead Researcher and PhD Candidate, Civil Engineering, University of Waterloo.
The innovative sensor technology operates by pre-processing acoustic data through sophisticated signal processing methods to emphasize leak-related components, thus making it possible for machine learning algorithms to detect leaks by differentiating their signs from various other sources of noise present in a water distribution system.
Cody works with a research group in the Structural Dynamics Identification and Control Laboratory, including post-doctoral fellow Jinane Harmouche and Sriram Narasimhan, a civil and environmental engineering professor and Canada Research Chair in Smart Infrastructure at Waterloo. A paper on their study, titled “Leak detection in water distribution pipes using singular spectrum analysis,” was recently published in the Urban Water Journal.