Blog

Mar 09, 2025

AI breakthrough speeds up titanium alloy production with higher strength

Using AI-driven models, the team identified new manufacturing conditions for laser powder bed fusion, a metal 3D-printing method. a day ago a day ago a day ago 2 days ago 2 days ago 2 days ago 2 days

Using AI-driven models, the team identified new manufacturing conditions for laser powder bed fusion, a metal 3D-printing method.

a day ago

a day ago

a day ago

2 days ago

2 days ago

2 days ago

2 days ago

2 days ago

2 days ago

2 days ago

9 minutes ago

2 hours ago

3 hours ago

3 hours ago

18 hours ago

21 hours ago

a day ago

a day ago

a day ago

a day ago

Bojan Stojkovski

Representational image of titanium alloy-made products.

Freepik/razihusin

A Johns Hopkins research team is using AI to enhance titanium alloys, improving strength and production speed for applications from deep-sea exploration to space travel.

Manufacturing high-performance titanium alloy parts for spacecraft, submarines, and medical devices has traditionally been a slow, resource-intensive process. Despite advances in metal 3D printing, optimizing production conditions has still demanded extensive testing and refinement.

To tackle this issue, researchers at the Johns Hopkins Applied Physics Laboratory (APL) identified processing techniques that enhance both production speed and strength of advanced materials.

The U.S. must rapidly scale manufacturing to meet the demands of current and future conflicts, according to Morgan Trexler, program manager for Science of Extreme and Multifunctional Materials at APL. To address this, APL is advancing laser-based additive manufacturing research, enabling the rapid development of mission-ready materials that keep pace with evolving operational challenges.

Using AI-driven models, the team identified new manufacturing conditions for laser powder bed fusion, a metal 3D-printing method. Their findings challenge existing assumptions, revealing a wider processing window for producing dense, high-quality titanium with customizable mechanical properties.

Co-author Brendan Croom explained that the discovery redefines how materials processing is approached. For years, certain processing parameters were considered off-limits due to the risk of poor-quality results. By using AI to explore a broader range of possibilities, the team identified new processing regions that enable faster printing while maintaining or even enhancing material strength and ductility. This development now allows engineers to optimize processing settings based on specific performance needs.

Furthermore, these findings could benefit industries relying on high-performance titanium parts by enabling the production of stronger, lighter components at higher speeds, enhancing efficiency in shipbuilding, aviation, and medical devices, while advancing additive manufacturing for aerospace and defense.

At the Whiting School of Engineering, researchers, including Somnath Ghosh, are applying AI-driven simulations to predict the performance of additively manufactured materials in extreme environments.

Ghosh co-leads a NASA Space Technology Research Institute (STRI) in collaboration with Carnegie Mellon, focused on developing advanced computational models to accelerate material qualification and certification. The goal is to reduce the time required to design, test, and validate new materials for space applications, aligning closely with APL’s efforts to refine titanium manufacturing processes.

When Steve Storck, chief scientist for manufacturing technologies in APL’s Research and Exploratory Development Department, joined the laboratory in 2015, he identified key limitations in the field. One major barrier to using additive manufacturing across the Department of Defense was materials availability, as each design required specific materials, yet robust processing conditions were lacking for most.

Titanium was one of the few materials that met DoD needs and had been optimized to match or exceed traditional manufacturing performance. The team recognized that expanding the range of materials and refining processing parameters was crucial to fully unlock the potential of additive manufacturing.

After several years of research, Storck’s team developed a rapid material optimization framework, leading to a 2020 patent and a 2021 study on defect impacts published in the Johns Hopkins APL Technical Digest. This framework laid the foundation for the latest study, where the team applied machine learning to explore a wide range of processing parameters, significantly improving efficiency and precision compared to traditional methods.

“We’re finding entirely new ways to process these materials, unlocking capabilities that weren’t previously considered. In a short amount of time, we discovered processing conditions that pushed performance beyond what was thought possible.” Storck noted.

Bojan Stojkovski Bojan Stojkovski is a freelance journalist based in Skopje, North Macedonia, covering foreign policy and technology for more than a decade. His work has appeared in Foreign Policy, ZDNet, and Nature.

Stay up-to-date on engineering, tech, space, and science news with The Blueprint.

By clicking sign up, you confirm that you accept this site's Terms of Use and Privacy Policy

2 days ago

2 days ago

2 days ago

2 days ago