From your computer to maglev trains, from power tools to MRI scanners, rare earth permanent magnets are all around us. Modern life is difficult without them, so their importance cannot be overstated. However, extracting the rare earth elements that make them up is often labor intensive and energy consuming. Scientists are looking for a better way – and thanks to machine learning algorithms, they may have found it.
The company Materials Nexus has developed MagNex in collaboration with researchers from the Henry Rice Institute and the University of Sheffield. It is a permanent magnet free of rare earth elements. MagNex is manufactured from a material that costs one-fifth of a permanent magnet. The new magnet also saw a 70 percent reduction in carbon emissions (in terms of kilograms of CO2 per kilogram of material) compared to rare earth permanent magnets.
That's pretty awesome in itself, but there's a broader reason why it's exciting. The permanent magnets we have were developed in the 1970s and 80s from alloys of rare earth elements. Finding materials with the right properties was a long process, involving a lot of trial and error. MagNex development from design to testing was 200 times faster.
“We are really excited that our first interaction with the materials nexus has had such a hugely positive outcome,” Ian Todd Freng, professor of metallurgy and materials processing at the University of Sheffield, said in a statement.
A collection of Material Nexus approaches to using AI [artificial intelligence] The material discovery and world-class facilities at the Henry Rice Institute in Sheffield have allowed us to rapidly develop a new magnetic material for the production of advanced alloys. This achievement shows a bright future for materials and manufacturing. The next generation of materials, unlocked by the power of AI, is extremely promising for research, industry and our planet.”
The AI system identifies and analyzes the composition of more than 100 million potential alloys that will have the right properties to be permanent magnets, free of rare earth elements, and meet affordability and durability requirements. The potential of this approach for new content creation is enormous.
“This is a groundbreaking discovery using cutting-edge machine learning software, and its development has been enabled by funding from Innovate UK,” said Bruce Adderley, Director of Mac and Use – Net-Zero. “This could have a significant future impact on our net-zero ambitions, by eliminating the need for rare earth elements in high-performance permanent magnets, through renewable energy and low-carbon transport.”
Computers have already helped a lot in allowing us to discover new substances. And it seems that thanks to machine learning algorithms, these and similar methods are being used in labs, such as the Self-Driving Lab developed at the University of Toronto.