The Materials Genome Team of Shanghai Jiaotong University has made important progress in modeling and prediction of the volume effect of alloy solid solutions

Recently, the Materials Genome Team led by Professor Wang Hong from the School of Materials Science and Engineering, Shanghai Jiao Tong University published online on the volume effect machine learning (ML) of Binary Substitutional Alloy Solid Solution (BSMSS) in Acta Materialia, the top international journal in the field of metal materials.

"Machine-learning prediction of Vegard's law factor and volume size factor for binary substitutional metallic solid solutions"

Zhou Yuanxun, a doctoral student at Shanghai Jiao Tong University, is the first author of the paper, and Professor Wang Hong and Professor Zhang Lanting are the co-corresponding authors of the paper

The volume effect of BSMSS can be characterized by VLF and SF

Figure 1 Screenshot of the paper published

After collecting VLF and SF data about BSMSS reported in the literature, a dataset containing 182 initial features was first obtained through feature (input to the model) construction

Figure 2 Feature selection working framework

The prediction of alloy volume effect is of great significance for alloy design, such as high-entropy alloys, solid solution strengthening, misfit degree, etc.

This research work was supported by the National Key R&D Program (2021YFB3702303 and 2017YFB0701900) and the Yunnan Provincial Major Science and Technology Project for Rare and Precious Metal Materials Genetic Engineering (202002AB080001-1)

For the original link, see: https://doi.