IoT secures drinking water supply for Mexican schoolchildren
NDS Cognitive Labs provided a solution to a water utility company that tracks the condition of water fountains in schools and parks through a Sigfox connection to determine when water filters need to be reordered .
25 August 2021Internet of Things (IoT) technology helps Mexico City schoolchildren access safe drinking water, with cloud-based software that manages water pressure, consumption and conditions at each standpipe . NDS Cognitive Labs, an artificial intelligence (AI) and technology services company, partnered with a Latin American water utility company to develop and deploy the IoT system.
The solution consists of wireless sensors on each fountain to capture water pressure data, along with NDS Cognitive Labs software that manages this data, as well as information from several local authorities regarding potential water contamination. for each site, so that the water company can visit specific fountains if necessary. The system collects sensor data via Sigfox based IoT or cellular network. The NDS software then analyzes the collected information and fills a dashboard with a map that allows users to get real-time readings regarding water quality, speed, pressure and usage.
The Greater Mexico City metropolitan area has 19 million people living at elevations of over 7,000 feet, many of whom face water shortages. The State of Mexico supplies bulk water from the Comisión Nacional del Agua (Conagua), which is managed by a variety of local agencies and municipalities. To transport this water, the country has nearly 11,000 kilometers (6,835 miles) of distribution lines, with several million water connections, some of them illegal.
NDS Cognitive Labs, based in the city, was launched 15 years ago to provide software solutions for smart buildings and smart agriculture (for example, a dairy production tracking system), according to Gustavo Parés. , CEO of the company. The company began working with GE Digital in 2015 to develop Industry 4.0 manufacturing solutions.
Company software providess AI and machine learning for data based on sensors that can be used by the operational teams of companies. “We wanted to take advantage of the way unstructured data supports structured data for decision making,” says Parés. In most cases, manufacturers face challenges with disparate systems used in manufacturing, with a separate computer system that does not have access to manufacturing data.
In 2019, NDS Cognitive Labs partnered with a water services company that provides infrastructure that collects and delivers drinking water throughout Mexico, including cisterns, pipes, and water fountains. The company had recently won a government contract from the State of Mexico to extend a source of drinking water to schools and parks. The goal, Parés says, was to ensure that children had access to high-quality running water in the places where they study and play.
Simply deploying water fountains, without intelligence technology, would not solve long-term drinking water problems, Parés says, because it would be too difficult for the water company to send employees to regularly visit each of the hundreds. of fountains to monitor the water pressure. and determine if the filters should be replaced. In addition, several entities, such as the local water authorities, carried out inspections at some sites, but the water company did not have access to these reports. Therefore, NDS Cognitive Labs began working with the company to build a single, unified system network.
“The first step we had was to map all the areas [where the fountains were installed]”Parés says,” to make sure we could do a centralized decision-making platform. The system had to be able to consume information accessible from a variety of public authorities. “The second challenge was how to make sure we have enough filters to deal with the water conditions.” Some fountains may require filter changes more often than others, depending on the water condition. filtered or the rate of use by people on site.
The resulting system consists of a mixture of manually recorded data and IoT-based filter information to identify filter replacement times. Each water cooler comes with an IoT sensor device that measures pressure, volume, and water consumption. The fountain pressure data is then analyzed to determine if a new filter is needed. An increase in pressure could indicate the need to replace the filter, while heavy water use could mean the same.
The system has a unique identification number linked to this fountain in the software. The data is periodically transmitted to the NDS server via cellular or Sigfox connectivity, depending on the location of the school. Sigfox, a French global network operator, provides IoT connectivity using low power extended transmission. If the fountain requires a new filter, the system can automate the ordering of a filter for that site. Additionally, the software manages water condition data based on local inspections, and water or health authorities share this information with the automated system.
Based on this information, the NDS Cognitive Labs solution can prompt service personnel to go to a specified fountain. The software comes with AI functionality to calculate the conditions for a fountain that may not have been inspected, based on its proximity to other fountains that have been inspected. “We take data from different sources and apply common ranges,” Pares explains. This method of mathematical interpolation, known as Kriging, estimates a variable based on geographic location.
The sensor data allows the water company to set acceptable thresholds based on pressure or volume, for example. While the software could generate 100 reports from the captured data, Parés says, “We had to focus on just two or three metrics.” The system has been deployed throughout central Mexico, including Mexico City. Eventually, it could be extended to the whole country, even if the government suspended the deployment for administrative and political reasons.
The partnership between NDS Cognitive Labs and the water company created a drinking water system that could serve thousands of children, with limited human intervention. “It was a good first approach,” says Parés. “The water company is the water specialist, but it does not have the resources to collect and manage this information.”