Prediction of Heusler Alloys with Giant Magnetocaloric Effect using Machine-Learning

Heusler alloys are intermetallic that offer a unique and broad array of properties. These properties are both scientifically intriguing and valuable for a variety of beneficial practical applications. One of these applications is magnetic cooling, taking advantage of the giant magnetocaloric effect (GMCE) in some Heusler alloys. Since the late 1990s, numerous scientific papers were published, attempting to harness Heusler alloys for green refrigeration. Manufacturing the alloys by additive manufacturing further offers control and enables tuning of their properties by controlling their microstructure. Although the scientific literature contains extensive information on these alloys’ chemistry and performance, it is the massive volume of scientific papers that makes it difficult, if not impossible, to keep up to date with relevant discoveries. To enable predicting the composition of excellent performing giant magnetocaloric Heusler alloys, manufactured by laser powder bed fusion (LPBF), we employed artificial intelligence, specifically unsupervised learning in the current work. We trained an unsupervised learning model using word embedding and the Word2vec algorithm on different data sets in the literature to extract hidden knowledge, relations, and interactions based on words that appear in similar contexts in the text while often having similar meanings. Properties inherent to giant magnetocaloric materials were addressed in the model. The outcome was the prediction of Heusler alloys, manufactured by LPBF, with an excellent giant magnetocaloric effect.