DOMAIN KNOWLEDGE-GUIDED MACHINE LEARNING AND CASE STUDIES OF METAL OXIDATION [Plenary Lecture]

This presentation first briefly introduces the concept of materials/mechanics informatics, which integrates machine learning with materials/mechanics science and engineering to accelerate materials/mechanics, products and manufacturing innovations. Then, this presentation reports a domain knowledge-guided machine learning strategy and demonstrates it by studying the oxidation behaviours of ferritic-martensitic steels in supercritical water and oxidation behaviours of FeCrAlCoNi based high entropy alloys (HEAs) at high temperatures. This strategy leads to the development of formulas with high generalization and accurate prediction power, which are most desirable to science, technology, and engineering.
EXTENDED ABSTRACT