Leak Detection Models: Using PI Data to fight Non-Revenue Water
Infrastructure, Water, Transportation
Leaks in Gippsland Water (GW) have historically been complicated to detect using existing flow data models. GW were looking to trial a different, real-time method of detecting common failure modes, utilising their existing remote telemetry system, data stored in the PI System and time-series analytics provided by Seeq Workbench.

While exploring this use case on defined assets, the leak events were classified by Nukon into two main categories:
• Short term leaks with high step-change in flows due to main breaks, and
• Long-term leaks, which were slow leaks due to cracks in pipes.
Darren Hickmott - Gippsland Water
Andrew May - NUKON