Energy intensive power plants could see their carbon footprint reduced by over a third (36%) after scientists from the University of Surrey, UK, used the power of artificial intelligence (AI) to adjust a system based on a real coal-fired power station.
When power plants burn fuel, they produce carbon dioxide (CO2), which can be captured by bubbling the flue gas through limestone-rich water.
CO2 reacts with the calcium carbonate in the limestone, producing harmless carbonate as part of a process known as ‘enhanced weathering’.
To pump the water and the CO2, energy is required. The plant studied by the team had its own wind turbine but – during periods of calm weather – it took energy from the grid.
Using AI, researchers taught a model system to predict what would happen – so it could pump less water when there was less CO2 to capture, or when less renewable energy was available.
“Usually, carbon capture systems run constantly, at the same rate – regardless of the externally changing environment,” said Professor Jin Xuan, Chair of Sustainable Processes at the University of Surrey’s School of Chemistry and Chemical Engineering.
“But we showed that teaching the system to keep making small adaptations can produce big energy savings – and capture more carbon atthe same time.
According to the team, it hopes their findings can be used more widely throughout the industry, contributing towards US Sustainability Goals 7, 9, 12 and 13.
Dr Lei Xing, Lecturer in Chemistry and Chemical Engineering at the University, commented that, although the team tested its model on enhanced weathering, the principles apply more widely.
“Our model could help anybody trying to capture and store more CO2 with less energy – whatever the process they’re using.”
Energy management isn’t the only area of carbon capture that may benefit from AI. Machine learning and AI algorithms are being increasingly used to predict when equipment used in carbon capture processes needs maintenance.
AI can also assist in integrating carbon capture processes with renewable energy sources. By predicting the availability of renewable energy (such as solar or wind power), companies could adjust their carbon capture operations accordingly to use the cleanest and cheapest energy available.
Indian CO2 technologies firm GAS LAB Asia (Gas Lab) recently joined forces with AI-driven carbon capture solutions developer Carbonetics Carbon Capture (Carbonetics) as part of a ‘world-first’ alliance in AI-driven commercial carbon capture projects.
The agreement will see Carbonetics delivering its generative AI design technology to the partnership, aiming to reduce costs by harnessing the power of AI algorithms to help optimise factors such as temperature, pressure, flow rates and chemical reactions.
source: gasworld.com
Commentaires