Machine learning approach to FINEMET-type soft magnetic alloys design
Background and Design Objectives
This work focuses on new soft magnetic materials design. We take advantage of materials informatics to build statistical model which is able to link processing procedures and materials properties together. Fe-based nanocrystalline alloys is main type of material to be studied. Data set is extracted from experimental results of publications.
Yuhao Wang*, Yefan Tian*, Tanner Kirk, Omar Laris, Joseph H. Ross, Jr., Ronald D. Noebe, and Raymundo Arróyave, “Machine learning-aided FINEMET-based soft magnetic nanocrystallines design and optimization”, Preparing (2019). [*Contributed equally]
Conferences & Workshops
Yefan Tian, Yuhao Wang, Tanner Kirk, Laris Omar, Joseph H. Ross, Jr., Ronald D. Noebe, and Raymundo Arroyave, “A machine learning approach for accelerating the design of FINEMET-type soft magnetic alloys”, 2019 Data Science in Materials Workshop, Poster Presentation (2019, Houston, TX).
Yefan Tian, Yuhao Wang, Joseph H. Ross, Jr., and Raymundo Arroyave, “Accelerated design of Fe-based soft magnetic materials using machine learning and stochastic optimization”, APS March Meeting 2019, Poster Presentation, T70.00267 (2019, Boston, MA).