|About this Abstract
||7th World Congress on Integrated Computational Materials Engineering (ICME 2023)
||First-principles and Data-driven Discovery of High-entropy Alloys for Corrosion Protection
||Andrew Neils, Nathan Post, Cheng Zeng, Jack Lesko
|On-Site Speaker (Planned)
Corrosion has a wide impact on society, causing catastrophically damage to structural engineered components. High-entropy alloys are emerging materials for superior corrosion performance. However, experimental search for corrosion-resistant materials is time consuming and expensive. Machine learning models trained on ﬁrst-principles data holds the promise in acceleration of materials design and discovery by predicting materials properties at a low computational cost. In this work, we use ﬁrst-principles calculations to identify thermodynamic and kinetic metrics for corrosion behaviors of metals. Based on those metrics, we then employ a data-driven approach to guide the autonomous discovery of high-entropy alloys for corrosion protection. Limitations and improvements of the proposed methods will be discussed.