Anglian Water will use AI driven software to manage roughly 317 biofilters, along with pumps and valves.

An ongoing collaboration with digital analytics company InfoTiles will see the proof-of-concept programme extended from 24 sites to 100.

This follows a successful pilot of the Norwegian company’s digital asset management technology.

Anglian Water is moving towards full integration of the technology, to create better-informed asset management decision-making and deeper understanding of maintenance prioritisation of water recycling assets.

Approximately 483 data points will be measured across all assets included in the scale-up. The water recycling centres will be chosen based on current model predictions and for their ability to send relevant asset data to the InfoTiles software.

Many of the sites vary in terms of system design and scale, as the technology has proved effective to use across different geographical locations within the region.

The initial 12-month software pilot monitored the rotating arms of 76 biofilters at 24 sites over a period of six months, to assess whether they were rotating when needed. It also measured sludge blanket levels in final settlement tanks to monitor optimal ranges for effective operation.

The data was collected through a mix of new and existing sensors via supervisory control and data acquisition control (SCADA) systems. This was combined with flow rates and publicly available weather data, to build a rich contextual overview of what was happening at Anglian’s water recycling plants in real-time.

Anglian Water’s existing SCADA systems were also combined into one event-streaming platform that aggregated, compared, and visualised reliability of the equipment.

The platform is able to visualise and model process data through machine-learning to show the likelihood of critical failures in wastewater treatment, such as potential stoppages and breakdowns.

When fully integrated, this will allow Anglian Water to easily trial and compare different sensor technologies for reliability and accuracy.

During the initial pilot phase, 14 machine-learning models were used to identify biofilter deviations and identify whether failure or slowdown was imminent. Four models were selected and brought forward for further development due to their ability to scale.

The focus is on anticipating, detecting, and resolving potential problems. By continually assessing the health and effectiveness of assets, maintenance teams could be deployed much more efficiently in the future.

The initial trial has shown promising signs of the feasibility of the technology for Anglian Water, with the data analysis already providing better insights. This is because, at fully operating capacity, the technology can reduce the number of active alarms by alerting operatives to issues before they become critical emergencies.

Anglian Water’s main goal of the collaboration is to reduce the risk of biofilter failure and augment its efforts to prevent the occurrence of serious pollution events from its water recycling centres. A further goal is to optimise the use of operational resources by reducing the number of emergency callouts during evenings and weekends and enabling maintenance decisions based on facts and forward planning.

Over the next 12 months, InfoTiles will work with Anglian Water personnel to further adapt its preventative maintenance processes and onboard internal data scientists to transfer knowledge of the user platform and data analysis.

The two companies were brought together through WaterStart, a US-based membership platform, which seeks to remove common barriers to the adoption of innovative technologies and connects utilities and municipalities with solution providers globally.

“Anglian Water is so proud to be involved in the success of the pilot programme, which will transform the way we manage our water recycling sites,” said spokesman Mark Stirling. “Collaborating with international companies through WaterStart has helped the team to work at pace to find and integrate solutions to improve the service provided.”

Adam Wood, chief product officer at InfoTiles, added, “Working with the operations team at Anglian Water has given us critical feedback to improve our platform and its ability to give operations teams actionable insights. A key learning has been the development of methods to leverage the data our utility customers already have available, which is important when considering relevance to assets in use throughout the UK.”