Enhancing the specific modulus of Al–Li alloys: A machine learning approach to micro-alloying element identification

To enhance the specific modulus of aerospace structural materials, this study employs machine learning methods to optimize the micro-alloying composition of Al–Li alloys. A total of 151 alloy composition-elastic modulus samples were analyzed. Feature generation and selection techniques were then app...

Full description

Saved in:
Bibliographic Details
Main Authors: Lyu Jing, Li Yanan, Li Xiwu, Zheng Lei, Xiao Wei, Liu Qilong, Liu Rui, Li Zhihui, Xiong Baiqing
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Journal of Materials Research and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2238785425018459
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To enhance the specific modulus of aerospace structural materials, this study employs machine learning methods to optimize the micro-alloying composition of Al–Li alloys. A total of 151 alloy composition-elastic modulus samples were analyzed. Feature generation and selection techniques were then applied. As a result, eight features with strong correlations to the specific modulus were identified. Through hyperparameter optimization of the GBR model and subsequent predictions, Mn was identified as a beneficial micro-alloying element. Experimental validation demonstrated that Mn-containing Al–Li alloys exhibit higher specific modulus. Through microstructural characterization and DFT calculations, it was found that the Mn element significantly improves the elastic modulus of the alloy by forming dispersed phases and enhancing solid solution strengthening. This study highlights the effectiveness of machine learning in alloy composition design.
ISSN:2238-7854