Heat Treat Society Online Member Community

 View Only

Data-Driven Design of T5 Heat Treatments for Aluminum Alloys

  • 1.  Data-Driven Design of T5 Heat Treatments for Aluminum Alloys

    Posted 3 days ago

    The next meeting of the ASM Materials Informatics Technical Committee will feature a talk by Dongwon Shin on "Data-Driven Design of T5 Heat Treatments for Aluminum Alloys."

    The online meeting will be held:

    ASM Materials Informatics Technical Committee

    Wednesday, June 10, 2026, 1:00 PM US EDT

    Anyone with an interest in this topic is welcome to attend the meeting. To request the online Zoom link, please contact scott.henry@asminternational.org.

    Presentation Abstract

    Optimizing aluminum alloys for demanding structural applications requires balancing competing performance metrics-hardness, electrical conductivity, and cost-across a complex space of compositional and processing variables. This talk presents results from a large-scale experimental campaign that generated a comprehensive dataset of T5 age-hardening responses across multiple commercial aluminum alloy systems. These measurements served as the foundation for training machine learning models to predict hardness and electrical conductivity as functions of alloy chemistry and heat-treatment parameters. The trained models were then deployed in a multi-objective optimization framework to identify compositions and processing conditions that simultaneously maximize mechanical and electrical performance while minimizing material cost. The results demonstrate the power of data-driven approaches to accelerate alloy design and process optimization beyond what conventional trial-and-error methods can achieve.

    Dongwon Shin is a Senior R&D Staff Member in the Materials Science and Technology Division at Oak Ridge National Laboratory (ORNL), where he has worked since 2010. He holds a Ph.D. in Materials Science and Engineering from Pennsylvania State University (2007), a master's degree in Metallurgical Engineering from Pusan National University in South Korea, and a bachelor's degree in the same field from the same institution. His research spans machine learning and artificial intelligence for materials design, computational thermodynamics (CALPHAD), first-principles density functional theory (DFT) calculations, integrated computational materials engineering (ICME), and the phase stability and properties of energy and nuclear materials. Prior to joining ORNL, he completed a postdoctoral fellowship at Northwestern University. His contributions have earned numerous distinctions, including the 2022 Paramount Research Award from ORNL's Physical Sciences Directorate, a 2017 R&D 100 Award for developing AlCuMnZr (ACMZ) cast aluminum alloys, and the Alvin M. Weinberg Fellowship. He is an active member of both TMS and ASM International.



    ------------------------------
    Scott Henry
    Director of Content and Publishing
    Liaison to ASM Technical Committees
    ASM International
    ------------------------------