Dramatically Enhanced Combination of Ultimate Tensile Strength and Electric Conductivity of Alloys via Machine Learning Screening

Zhang, Hongtao; Fu, Huadong; He, Xingqun; Wang, Changsheng; Jiang, Lei; Chen, Lei; Xie, Jun

doi:10.2139/ssrn.3646448

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with the fast development of artificial intelligence and machine learning (ML), the data-driven paradigm of materials informatics, which unifies the knowledge learned from experiments, theory, computations, and simulations, is rapidly becoming popular in materials science and engineering [1][2][3][4][5][6][7][8] . The data-driven paradigm combined with expert domain knowledge provides state-of-the-art methodologies to understand and predict complex behaviors of materials and great achievements have been obtained in materials informatics [9][10][11][12][13][14][15][16] . Materials data, especially experimental data of mechanical behaviors of materials, are small in size, whereas the influence factors, including testing conditions (or service environments), material compositions and microstructures, specimen size, etc., are considerably large, meaning that the dimensions of feature space, called search space also, are extremely high.…”

Section: Research Backgroundmentioning

confidence: 99%

Divide and conquer： Machine learning accelerated design of lead-free solder alloys with high strength and high ductility

Zhang

Wei

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

The attainment of both high strength and high ductility is always the goal for structure materials, because the two properties generally are mutually competing, called strength-ductility trade-off. Nowadays, the data-driven paradigm combined with expert domain knowledge provides the state-of-the-art methodology to design and discovery for structure materials with high strength and high ductility. To enhance both strength and ductility, a joint feature is proposed here to be the product of strength multiplying ductility. The strategy of “divide and conquer” is developed to solve the contradictory problem, that material experimental data of mechanical behaviors are, in general, small in size and big in noise, while the design space is huge, by a newly developed data preprocessing algorithm, named the Tree-Classifier for Gaussian Process Regression (TCGPR). The TCGPR effectively divides an original dataset in a huge design space into three appropriate sub-domains and then three Machine Learning (ML) models conquer the three sub-domains, achieving significantly improved prediction accuracy and generality. After that the Bayesian sampling is applied to design next experiments by balancing exploitation and exploration. Finally, the experiment results confirm the ML predictions, exhibiting novel lead-free solder alloys with high strength high ductility. Various material characterizations were also conducted to explore the mechanism of high strength and high ductility of the alloys.

show abstract

Section: Research Backgroundmentioning

confidence: 99%

Divide and conquer： Machine learning accelerated design of lead-free solder alloys with high strength and high ductility

Zhang

Wei

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Which resulting in the solidification of primary Fe phase directly in the immiscible range, and the dendritic Fe phase changes into Fe-rich spherical [7], thus coarsening the primary Fe phase. Hongtao Zhang et al [8] screened the existing data sets through machine learning method, and found that element In could significantly strengthen the Cu matrix and had little effect on its conductivity. In addition, the In element could reduce the solid solubility of Fe in the Cu matrix [9], and it had a larger binding energy with Fe [10], which could promote the diffusion of Fe.…”

Section: Introductionmentioning

confidence: 99%

Effect of in on Fe phase morphology and properties of Cu-Fe alloy

Yuan,

Liu,

Guo

et al. 2023

Materials Science and Technology

View full text Add to dashboard Cite

In this paper, Cu-6.2Fe-xIn (x = 0, 0.2, 0.4) alloy was prepared by melting casting and mechanical heat treatment. The Fe phase morphology of Cu-6.2Fe-xIn alloy was observed by SEM, EBSD and TEM. The results show that the addition of In element refines the primary Fe phase and optimises its distribution. After large plastic deformation, the Fe phase was fibrillated and the addition of In refines the Fe fibre and increases its density. The strength of Cu-6.2Fe-0.4In alloy with strain of 7 were 901 MPa, which was 201 MPa higher than that of Cu-6.2Fe alloy. The refining effect of In on the primary Fe phase was the main reason for the significant improvement of the strength of Cu-Fe-In alloy.

show abstract

Dramatically Enhanced Combination of Ultimate Tensile Strength and Electric Conductivity of Alloys via Machine Learning Screening

Cited by 2 publications

References 0 publications

Divide and conquer： Machine learning accelerated design of lead-free solder alloys with high strength and high ductility

Divide and conquer： Machine learning accelerated design of lead-free solder alloys with high strength and high ductility

Effect of in on Fe phase morphology and properties of Cu-Fe alloy

Contact Info

Product

Resources

About