"Machine learning technology has made it possible to find alloys of different materials with better characteristics than those used so far"
Machine learning has opened up a new avenue for discovering new compositions of elements
The technology section of El País featured Jon Mikel Sánchez, an expert from the Alloys, Products and Metallic Circularity platform. Our researcher did his PhD thesis on high entropy alloys. In the article published in El País, he highlights that "applying artificial intelligence to discover new alloys is quite new. Discovering new materials by these methods is a significant step forward”.
Traditionally, an alloy has essentially been a mixture of a parent metal and small concentrations of other elements from the periodic table. Machine learning has opened up a new avenue for discovering new compositions of dozens of elements and their different concentrations. This has been a revolution in the development of high entropyalloys.
New high entropy alloys
Machines have discovered several alloys that match or even surpass those created by humans in some of their properties. By tracing millions of combinations between the different elements of the periodic table, they have managed to find around 1,000 candidates with the properties they were interested in, and analysed them for those that would theoretically have a low coefficient of thermal expansion (the expansion or contraction of the material with cold or heat).
As published in the journal, Science, a group of researchers have found four new alloys with a coefficient equal to or lower than the most temperature-immune combinations used so far, thanks to the calculation and analysis of the machines. Having proved its worth with thermal expansion, scientists intend to use machine learning to investigate other properties, such as magnetism, in other materials.
