AI could improve leak detection, study says

Expensive water leaks could be tackled using sensors and new artificial intelligence (AI) technology, the University of Waterloo in Canada revealed.

The AI has been developed by the university’s researchers in collaboration with undisclosed industry partners. It combines sophisticated signal processing techniques and AI software to identify signs of leakage carried via sound in water pipes.

The University of Waterloo claims that the acoustic signatures are recorded by hydrophone sensors that can be inexpensively installed in existing fire hydrants without excavation or taking them out of service.

“This would allow cities to use their resources for maintenance and repairs much more effectively,” said Roya Cody, a civil engineering PhD candidate at Waterloo.

“They could be more proactive as opposed to reactive.”

According to its release, 13% of Canada’s clean water between treatment and delivery loss due to leaks, bursts and various other issues.

“By catching small leaks early, we can prevent costly, destructive bursts later on,” said Cody.

Researchers have now begun field tests of the hydrophone sensors after reliably detecting leaks as small as 17 litres a minute in the lab.

“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,” Cody concluded.

The study is a result of a collaboration with a team of researchers in the Structural Dynamics Identification and Control Laboratory.