Metering & Smart Energy International (África do Sul) online

Brazilian municipalities reduce water losses with new AI-based tech

Publicado em 22 março 2018

Por Nicholas Nhede

The São Paulo Research Foundation (FAPESP) in partnership with startup I.Systems has developed a technology to help reduce water losses in Brazil’s distribution networks.

The technology Leaf was developed under FAPESP’s Innovative research in small businesses programme PIPE.

The technology has to date been adopted by 35 companies and reduced water loss in distribution networks providing seven municipalities in Brazil.

The seven municipalities include Araruama, Armação dos Búzios, Arraial do Cabo, Cabo Frio, Iguaba Grande, São Pedro da Aldeia and Saquarema.

According to Igor Santiago, president of I.Systems, the technology took a week to adapt to trends within the network operated by Prolagos and supplying water to the seven municipalities.

The system has helped to reduce average water flow by 5.8% and 15% reduction in the minimum nighttime flow rate hence cut water losses throughout the network.

Coca Cola has also used the solution to reduce water waste due to leakage by 2% at its soft drink bottling plant in Femsa.

The system is based on artificial intelligence and makes use of factors such as time, date and consumer historical usage data to adjust water pressure according to demand in the distribution network.

The system is able to predict supply requirements for periods of up to 72 hours.

"Control of water pressure in a distribution network is considered one of the most important operational factors in water distribution.

"Low pressure may be insufficient to transport the water to the most distant or highest points in a city. High pressure increases leak losses and may lead to burst pipes," added Santiago.