Artificial intelligence speeds up decisions on pipeline repairs

TECHNOLOGY UPDATE

Artificial intelligence is helping to speed up repairs to United Utilities' wastewater pipeline network by cuting the time taken to review closed-circuit TV (CCTV) inspection footage by 80%.

The water company said it generates, every year, thousands of hours of footage from its CCTV inspection of more than 1,000km of pipeline for damage. The process of reviewing footage has for more than 70 years remained largely manual – and very time consuming.

Through a partnership forged with Australian artificial intelligence (AI) company, Vapar, United Utilities has accelerated pipeline repairs by semi-automating the fault detection process from inspection footage.

Vapar first began working with United Utilities in the water firm’s second Innovation Lab held in 2019 to develop the accuracy of the AI. Vapar was then introduced into United Utilities’ routine maintenance inspection programme where, the company said, it reduced survey processing times from ten days to two days.

Programme delivery manager for United Utilities’ wastewater network, Katy Bevan, said Vapar had “massively reduced” the time needed to make decisions about cleaning and remedial activities and added: “We are also benefiting from lower costs, and the generation of performance management tools to support our targets.”

United Utilities said the complex nature of pipeline inspections makes it impossible for AI to be used alone tool and the outputs still require review by people.