Artificial intelligence: saving water the smart way

VA SYD is one of Sweden’s largest utilities, which invests heavily in sustainable water and wastewater treatment, and pushes for environmentally smart solutions in community building. The company supplies more than 546,000 customers with drinking water in the regions around Lund and Malmö in the south of Sweden.

At VA SYD, non-revenue water accounts for 10% of all water supplied to customers. The reason: leaks in the pipeline network. VA SYD now relies on artificial intelligence to more efficiently detect and reduce leaks in water pipes.

“Treating natural resources with respect is a way of life in Sweden, and water use should be no exception to this practice,” Victor Pelin said. “Even if here in Sweden there is not a water-scarcity problem in general, wasting water just feels wrong. Plus, lifting, treating and pressurising water consumes energy, and energy is a major cost factor,” Simon Granath added.

Granath and Pelin work as development engineers at VA SYD and have been responsible for the design and implementation of the leakage detection system.

VA SYD operates a total of around 5000 km of pipelines, 2000 km of which are for drinking water. Pinpointing leaks is a complex task.

“Until very recently, we could detect only the largest leaks that led to service disruptions. In fact, it is the smaller, slower leaks, often from small service pipes, that are responsible for the lion’s share of non-revenue water,” Granath said.

“We have to maintain a lot of pipelines in a large area, and we wanted to improve our ability to pinpoint leaks through smart metering zones. For this purpose, we set out to find an AI-based solution,” Pelin said.

VA SYD evaluated several systems over recent years, looking for a solution that was state of the art. It would also have to make optimum use of the available flowmeters and smart meters in the area that had been chosen for the proof of concept. In the end they chose Siemens’ SIWA LeakPlus system.

“But when it came to the implementation concept, we ran into some obstacles,” Granath said. “We had to find a way of using the AI-based leakage detection in an on-premises set-up instead of a cloud environment. We then had some in-depth discussions with Siemens, their cooperation partner BuntPlanet, and our IT and OT departments about the best approach to install the SIWA LeakPlus solution in our own data centres.

“To my knowledge, this is the first time something like this has been done in the Swedish water industry — and we managed to get the job done.”

The next step was to refine the hydraulic models for the pipelines and link the data from the metering systems and pump stations with SIWA LeakPlus using OPC UA. VA SYD was then ready to perform the first tests.

Pelin explained: “We used the system to simulate different leaks and then evaluated the data. We were able to detect leaks as small as 0.5 litres per second — a huge improvement over the previous solution, which provided no means of detecting small leaks at all.”

SIWA LeakPlus is one of the Siemens Water (SIWA) applications specifically developed for the water and wastewater industry. The solution uses an AI-based algorithm to identify and classify anomalies in the pipe network. To perform reliably, SIWA LeakPlus is first trained with historical flow and pressure data so that it learns to separate anomalies from regular operation and assign the correct cause to each anomaly.

“In the coming weeks, we will introduce a further developed variant of leak detection, which will allow us to determine the exact location of the leak,” Pelin said. “Then we will have the means to really go out there and fix all those small issues efficiently.”

With the proof of concept in its final stages, Pelin and Granath are also working on scaling up the solution to other parts of the network. The next area to benefit from SIWA LeakPlus will be the town of Lund, where VA SYD is currently installing additional flowmeters to provide more data from the pipeline network.

“A smarter leakage detection system requires less data from the pipelines, so we can reduce the number of installed meters. This immediately pays off,” Pelin said.

Economic benefits aside, SIWA LeakPlus has already helped VA SYD take the next steps towards another ambitious goal: by 2030 the company wants to become a climate-neutral, energy-saving water utility with zero unplanned service disruptions.

Image credit: ©stock.adobe.com/au/phonlamaiphoto