Metro de Madrid (Madrid Metro) in Spain has implemented a self-learning artificial intelligence (AI)-based ventilation system to reduce emissions and improve air quality across metro stations.
The AI-based system was developed and installed in collaboration with tech major Accenture.
During development, Madrid Metro Ventilation experts worked with Accenture Applied Intelligence to devise a system that will utilise an algorithm to identify the optimal balance of ventilation at each station.
The system leverages data on air temperature, station architecture, train frequency, passenger load and electricity price to determine the optimal levels.
It incorporates historic and simulated data, as well as outside and below-ground temperatures over the next 72 hours to carry out optimisation.
The deployment of the system is expected to enable the metro system to reduce carbon dioxide emissions by 1,800t. It will also help to reduce energy costs for ventilation by 25%.
Metro de Madrid Engineering and Maintenance Division head Isaac Centellas said: “With the help from Accenture, the innovative ventilation system has enabled us to achieve the dual benefits of lower energy costs and a reduced environmental impact.
“Ensuring the comfort of our passengers while being highly energy-efficient and environmentally friendly is a true win-win outcome.”
The ventilation system also features a simulation engine and a maintenance module. It detects fan operation failures and will allow Madrid Metro to carry out equipment maintenance.
Metro de Madrid network comprises 294km of track and 301 stations. About 2.3 million commuters use the metro system daily.