Optimization of High Entropy Alloys using Artificial Intelligence methods

• Grant number: 23/14613-6
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: March 01, 2024
• End date: August 31, 2024
• Field of knowledge: Engineering - Materials and Metallurgical Engineering
• Principal Investigator: Francisco Gil Coury
• Grantee: Caroline Binde Stoco
• Supervisor: Yannick Champion
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Institution abroad: Laboratoire Science Et Ingénierie Des Matériaux Et Procédés, France
• Associated to the scholarship: 23/04907-2 - Production and Characterization of High Toughness HEAs by Genetic Algorithm, BP.MS

Abstract

The ever-advancing pace of technology is driving the imperative need for the development of novel materials capable of fulfilling the evolving demands across various service sectors. In this dynamic landscape, High Entropy Alloys (HEAs) emerge as a notable solution. However, a significant challenge lies in the selection of optimal compositions from within a vast and complex multicompositional space. To address this challenge effectively, computational tools, particularly the genetic algorithm, offer a promising avenue. Through a process of genetic crossover and mutation, this tool creates new alloy generations, progressively aligning their properties with desired parameters. In our current endeavor, the optimization process aims to attain a single-phase face-centered cubic (FCC) structure. This structural goal will be assessed through the integration of the CALPHAD method with machine learning techniques. Additionally, our optimization seeks to achieve elevated values for both the Hall-Petch constant (K) and the critical resolved shear stress (Ãy). These objectives are aligned with enhancing mechanical strength through grain refinement and solid solution strengthening, respectively. The culmination of this optimization process will yield the selection of a list of compositions of particular interest, using different selection criteria, that will help guide future research efforts by our research group.