Sydney Water has teamed up with National ICT Australia (NICTA) to predict water pipe breakages before they happen using NICTA's machine learning technology."
The utility company will use a computer modelling based approach which analyses water pipe data to estimate the likelihood of failure.
According to Sydney Water, Australia's water mains break on average 7000 times each year, and computer modelling could potentially save water utility companies $700 million a year in repairs and maintenance.
NICTA's infrastructure, transport and logistics director, Rob Fitzpatrick, said the technology was trialled in Wollongong and was able to predict breaks with "twice the precision" of the existing technology.
"NICTA is applying advance machine learning techniques to pipe failure data from Sydney Water," he said in a statement. Fitzpatrick added that the approach could be applied to other infrastructure failure prediction, such as bridges.
According to Sydney Water managing director Kevin Young, international water utility companies had expressed interest in the technology.
NICTA and Sydney Water are both covering the cost of the project, which is estimated at $700,000 in cash.
Follow Hamish Barwick on Twitter: @HamishBarwick
Follow Computerworld Australia on Twitter: @ComputerworldAU, or take part in the Computerworld conversation on LinkedIn: Computerworld Australia