Predictive models use pressure data to help reduce pipe leakage

Water is an essential resource for life that is as valuable as it is limited. Therefore, making sure it is not wasted, especially in the context of water scarcity, is an important objective for those responsible for transporting it from sources of water reservoirs, swamps, springs, and other catchment sources. This is a journey that water makes through plumbing systems that are often outdated or do not meet the required performance and efficiency requirements.

With the aim of enhancing drinking water management, a team at the University of Cordoba has developed a predictive model that can implement pipe leakage due to excessive pressure, one of the main problems these distribution networks suffered.

The work, published in Energy Nexus, was carried out by a team in the Department of Applied Physics, Radiology, and Physics Medicine, consisting of researchers David Muñoz Rodríguez, Alberto Jesús Perea Moreno and María Gesús Aguilera Ureña. With Manuel J. Gonzalez Ortega of the University of Seville. and Andres Ortega Ballesteros, a student at the University of Cordoba, who completed his doctoral dissertation in this field.

As the authors explain, the pressure through which water circulates has a direct relationship with the appearance of leaks and the amount of water lost through them. Data on this variable allows the distribution network manager to detect abnormal patterns and adapt the pressure to the required levels and requirements that occur through the valve. This way you can prevent leaks and therefore unnecessary water loss.

The system proposed by the UCO team was developed according to Box Jenkins’ methodology, which is primarily used to analyze and predict the time series, and was generated and validated through actual data on the water distribution network of Noja, the Cantabrian town, with most population variations during the holiday period.

The resulting predictive model scalable to other similar networks allows companies operating water distribution networks to overcome key limitations. There is no real-time data, so guide you when performing dynamic pressure adjustments. The information provided by this system allows them to detect variations in advance and take precautions.

The advantages of this model are explained by researchers, as exceeding the reduced leakage and the resulting water loss. Adapting pressure on demand improves the quality of service users receive.

At the same time, the appearance of new failures is minimized, which reduces maintenance costs and extends the useful life of the pipeline network. This is a critical infrastructure that is dependent on proper functionality to supply drinking water, a truly valuable resource.