- Yorkshire Water, the University of Sheffield and Siemens Digital Industries join forces to use Artificial Intelligence (AI) and the Internet of Things (IoT) to reduce wastewater network blockages and reduce pollution
- Partnership has developed an innovative blockage predictor solution to improve the performance of the sewer network
- New solution identifies problems in the network quickly - enabling Yorkshire Water to rectify issues before they escalate
- AI tool found nine in 10 potential issues, three times more successful than existing pollution prediction processes. AI also reduced the number of false positive alerts by 50 per cent
Yorkshire Water, the University of Sheffield and Siemens Digital Industries have joined forces to use Artificial Intelligence (AI) and the Internet of Things (IoT) to reduce wastewater network blockages and reduce pollution.
The partnership has developed an innovative blockage predictor solution to improve the performance of the sewer network. It identifies problems quickly, enabling Yorkshire Water colleagues to attend and rectify any issues before they escalate.
An ongoing trial involving a variety of sewage assets across 70 sites in the region gave up to two weeks advance notice of blockages. The project is part of Yorkshire Water’s Pollution Incident Reduction Plan 2020-2025 which aims to reduce pollution incidents by 50 per cent by focusing on early intervention.
The AI in the new blockage predictor tool found nine in 10 potential issues, three times more successful than the existing Yorkshire Water pollution prediction processes that relied on statistical methods. The AI also reduced the number of false positive alerts by 50 per cent[1].
My team compared the findings of the AI against the current system and what was actually observed over 21,000 days of operation – and the AI came out on top.
Professor Joby Boxall
Professor of Water Infrastructure Engineering at The University of Sheffield
Smart sensors feed water level data into SIWA Blockage Predictor, an application on Siemens’ cloud-based, open Internet of Things (IoT) operating system, MindSphere. The analytics are embedded within a web application, enabling remote access on mobile devices or PCs and notifying users in advance of any issues.
AI evaluates the characteristics and performance of the sewer network in real time and predicts problems like a network blockage before they happen, enabling Yorkshire Water to fast-track engineers to inspect and resolve issues.
Heather Sheffield, Manager of Operational Planning and Technology, at Yorkshire Water said: “The results of the innovative trial across the region have been very positive. The data has allowed us to identify problems with our network quickly, giving our teams the opportunity to attend before pollution incidents occur.
“Our partnership with Siemens and the University of Sheffield illustrates our commitment to investing in cutting edge technology to provide a data driven approach. A key goal of our Pollution Incident Reduction Plan 2020-2025 is to reduce pollution incidents by 50 per cent by focusing on prediction and intervention to prevent pollution and avoid repeat incidents.
“The solution could have a significant role to play in reducing the number of pollution incidents, which can have a negative impact on the environment, as well as increasing our efficiency and providing improved value to our customers.”
Yorkshire Water is using the project as a testbed for emerging technologies to respond to the demands from the Environment Agency (EA) and water regulator Ofwat to reduce pollution incidents within performance commitments and produce more accurate and reliable reporting data in relation to discharges from CSOs.
Environment Minister Rebecca Pow said: “It’s encouraging to see water companies using new innovations like this to solve practical problems like preventing pollution from blockages in our sewerage systems.
“Water companies have a huge responsibility to manage wastewater in this country, and they have some way to go to drive pollution incidents down to zero by 2025.
“The health of our rivers and waterways is a huge priority for this government. That’s why we have asked every water company to implement a Pollution Incident Reduction Plan which the Environment Agency will monitor and, where needed, push for more progress.”
Professor Joby Boxall, Professor of Water Infrastructure Engineering at The University of Sheffield, explained: "By building a personalised fingerprint for the wastewater assets that reflects how the local network responds to rainfall and overlaying that on patterns of daily behaviour we have been able to establish what each asset’s ‘normal’ response is.
“Using an analytics tool called ‘fuzzy logic’ the system then applies a further level of intelligence to judge if the predicted level is significantly different to observed level based on how big the difference is, including expected response to any recent rainfall.
“My team compared the findings of the AI against the current system and what was actually observed over 21,000 days of operation – and the AI came out on top."
Adam Cartwright, Head of IoT Application Delivery at Siemens, added: “Artificial Intelligence is not magic, it requires experts in data science to come together with people who really understand the issue and engineers who can build software, connect hardware and knit together a solution that is secure against cyber attack. This project has been a textbook example of how all the strands should come together.
“I live in Yorkshire and I am proud that we have a genuine made in Yorkshire solution for our rivers.
“SIWA Blockage Predictor is one of a number of Siemens solutions for the UK water industry capable of improving both customer satisfaction and the environment.”
[1] Compared to the use of threshold derived alarms, the reduction would be over 95 per cent.
Civil and Structural Engineering at the University of Sheffield
Contact:
For further information please contact:
