About this Symposium

Meeting

MS&T24: Materials Science & Technology

Symposium

Integrated Computational Materials Engineering for Physics-Based Machine Learning Models

Sponsorship

TMS: Integrated Computational Materials Engineering Committee

Organizer(s)

William E. Frazier, Pacific Northwest National Laboratory
Lei Li, Pacific Northwest National Laboratory
Yucheng Fu, Pacific Northwest National Laboratory
Philip E. Goins, Army Research Laboratory
Zhengtao Gan, The University of Texas at El Paso

Scope

This symposium will include topics pertaining to the improvement and deployment of computational materials approaches through linkages with experimental data, simulations at other length scales, and surrogate models. Applications related to microstructural evolution, mechanical behavior, degradation during processing and in-service are of particular interest. Topics may include:

- Integrated models of material deformation and microstructural evolution in metallic materials.
- Integrated models of microstructural evolution and material degradation.
- Approaches for the simulation of grain growth, recrystallization, twinning, phase transformations, or related phenomena coupling multiple scale modeling approaches.
- Verification/validation of machine learning models [e.g., physics-informed or data-driven methods] of microstructural evolution and/or response to deformation, aging, and irradiation.
- Novel couplings of experimental methods and data with mesoscale modeling approaches.
- Models using physics-informed or generative machine learning approaches to model the formation of microstructures or microstructural evolution processes.

Abstracts Due

05/15/2024

PRESENTATIONS APPROVED FOR THIS SYMPOSIUM INCLUDE

A Multiscale Simulation Investigation of Cavity Evolution in a Ni TPBAR Coating

Advanced Coupling of an FFT-Based Mesoscale Modeling Method to a Macroscale Finite Element Method

B-1: Statistically Equivalent Virtual Microstructures for Modeling of Complex Polycrystalline Alloys Using a Generative Adversarial Network (GAN)-Enabled Computational Platform

Deep Generative Model for Reproducing Microstructure of Low-Carbon Steel During Continuous Cooling

Deep Learning for Early Detection and Localization of Damage in Metal Plates

Developing Data-Driven Strength Models Incorporating Temperature and Strain-Rate Dependence

Hybrid Machine Learning Informed Design Guidelines for Structural Gradient Alloys with Enhanced Performances

Phase-Field Modeling of Grain Evolution and Recrystallization in Friction Stir Processing

PRISMS-MultiPhysics: An Open-Source Coupled Phase Field-Crystal Plasticity Framework and its Application to Simulate Twinning in Magnesium Alloys

Thermodynamic Integration for Dynamically Unstable Systems Using Interatomic Force Constants without Molecular Dynamics

Utilizing Convex Neural Networks to Predict the Yield Surfaces of Polycrystalline Samples with Complex Crystallographic Textures

Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement