The KAIST research team led by Professor Seungchul Lee from the Department of Mechanical Engineering, in collaboration with Professor Hyoung Seop Kim’s team at POSTECH, have successfully overcome the strength–ductility dilemma of Ti-6Al-4V alloys using artificial intelligence, enabling the production of high strength, high ductility metal products.
The AI developed by the team accurately predicts mechanical properties based on various 3D printing process parameters while also providing uncertainty information, and it uses both to recommend process parameters that hold high promise for 3D printing. The study is published in Nature Communications.
Among various 3D printing technologies, laser powder bed fusion is an innovative method for manufacturing Ti-6Al-4V alloys, renowned for their high strength and bio-compatibility. However, this alloy made via 3D printing has traditionally faced challenges in simultaneously achieving high strength and high ductility.
Although there have been attempts to address this issue by adjusting both the printing process parameters and heat treatment conditions, the vast number of possible combinations made it difficult to explore them all through experiments and simulations alone.
The active learning framework developed by the team quickly explores a wide range of 3D printing process parameters and heat treatment conditions to recommend those expected to improve both strength and ductility of the alloy. These recommendations are based on the AI model’s predictions of ultimate tensile strength and total elongation along with associated uncertainty information for each set of process parameters and heat treatment conditions.
The recommended conditions are then validated by performing 3D printing and tensile tests to obtain the true mechanical property values. These new data are incorporated into further AI model training, and through iterative exploration, the optimal process parameters and heat treatment conditions for producing high-performance alloys were determined in only five iterations.
With these optimized conditions, the 3D printed Ti-6Al-4V alloy achieved an ultimate tensile strength of 1190 MPa and a total elongation of 16.5%, successfully overcoming the strength–ductility dilemma.
Professor Seungchul Lee said, “In this study, by optimizing the 3D printing process parameters and heat treatment conditions, we were able to develop a high-strength, high-ductility Ti-6Al-4V alloy with minimal experimentation trials. Compared to previous studies, we produced an alloy with a similar ultimate tensile strength but higher total elongation, as well as that with a similar elongation but greater ultimate tensile strength.
“Furthermore, if our approach is applied not only to mechanical properties but also to other properties such as thermal conductivity and thermal expansion, we anticipate that it will enable efficient exploration of 3D printing process parameters and heat treatment conditions.”
More information:
Jeong Ah Lee et al, Active learning framework to optimize process parameters for additive-manufactured Ti-6Al-4V with high strength and ductility, Nature Communications (2025). DOI: 10.1038/s41467-025-56267-1
The Korea Advanced Institute of Science and Technology (KAIST)
Citation:
AI framework overcomes the strength-ductility dilemma in additive-manufactured titanium alloys (2025, February 25)
retrieved 26 February 2025
from https://techxplore.com/news/2025-02-ai-framework-strength-ductility-dilemma.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
