header

Machine Learning to Predict Aluminum Segregation to Magnesium Grain Boundaries

16 Pages Posted: 29 Apr 2021 Publication Status: Published

See all articles by Joseph Messina

Joseph Messina

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences

Renjie Luo

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences

Ke Xu

Beihang University (BUAA) - Department of Physics

Guanghong Lu

Beihang University (BUAA) - Department of Physics

Huiqiu Deng

Shandong University - Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials; Hunan University - School of Physics and Electronics

Mark A. Tschopp

U.S. Army Research Laboratory

Fei Gao

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences

Abstract

Magnesium alloys are good candidates for a number of applications due to their high strength-to-weight ratio, but other properties like corrosion resistance, formability, and creep are still a concern. In magnesium-aluminum alloys, M17Al12 phase precipitates at the grain boundaries (GBs) can have important implications on the mechanical and corrosion behavior. In order to better understand the effects, atomistic segregation of aluminum to GBs must be evaluated first. This study uses atomistic simulations to quantify aluminum segregation energetics for training a machine learning model. Aluminum atoms were iteratively placed at various atomic sites near 30 different 〈0001〉 symmetric tilt grain boundaries (STGBs) in magnesium. The results show how aluminum segregation is affected by GB structure and the local atomic environment. The ability to compute grain boundary physical properties of interest using machine learning techniques can have broad implications for the area of grain boundary science and engineering.

Keywords: machine learning, grain boundary segregation, magnesium alloys, molecular dynamics (MD)

Suggested Citation

Messina, Joseph and Luo, Renjie and Xu, Ke and Lu, Guanghong and Deng, Huiqiu and Tschopp, Mark A. and Gao, Fei, Machine Learning to Predict Aluminum Segregation to Magnesium Grain Boundaries. Available at SSRN: https://ssrn.com/abstract=3836795 or http://dx.doi.org/10.2139/ssrn.3836795

Joseph Messina

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences

Ann Arbor, MI
United States

Renjie Luo

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences

Ann Arbor, MI
United States

Ke Xu

Beihang University (BUAA) - Department of Physics

Guanghong Lu

Beihang University (BUAA) - Department of Physics

37 Xue Yuan Road
Beijing 100083
China

Huiqiu Deng

Shandong University - Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials ( email )

Hunan University - School of Physics and Electronics ( email )

Changsha
China

Mark A. Tschopp

U.S. Army Research Laboratory

Aberdeen Proving Ground, MD
United States

Fei Gao (Contact Author)

University of Michigan at Ann Arbor - Department of Nuclear Engineering and Radiological Sciences ( email )

MI 48109
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
58
Abstract Views
399
PlumX Metrics