Researchers use AI to strengthen 3D printed titanium alloys

Mar 12, 2025

According to Johns Hopkins Applied Physics Laboratory (APL), artificial intelligence is revolutionizing metal 3D printing by optimizing the production of high-performance titanium alloy parts. Researchers at APL and the Johns Hopkins Whiting School of Engineering have developed AI-driven methods to accelerate the manufacturing of Ti-6Al-4V, a widely used titanium alloy known for its strength and low weight.

“The nation faces an urgent need to accelerate manufacturing to meet the demands of current and future conflicts,” said Morgan Trexler, program manager for Science of Extreme and Multifunctional Materials at APL. “At APL, we are advancing research in laser-based additive manufacturing to rapidly develop mission-ready materials.”

Their study, published in Additive Manufacturing, focuses on laser powder bed fusion. AI-driven models identified a broader range of processing parameters than previously considered viable – allowing for faster production while maintaining or even improving material properties.

“For years, we assumed that certain processing parameters were ‘off-limits’ for all materials because they would result in poor-quality end product,” said Brendan Croom, a senior materials scientist at APL. “But by using AI to explore the full range of possibilities, we discovered new processing regions that allow for faster printing while maintaining – or even improving – material strength and ductility.”

The breakthrough could significantly impact industries that rely on high-performance titanium parts, such as aerospace, shipbuilding, and medical devices. AI-driven simulations, developed by researchers including Somnath Ghosh, are also helping predict how 3D printed materials perform in extreme environments. This aligns with efforts at NASA’s Space Technology Research Institutes (STRIs) to accelerate material qualification and certification for space applications.

In 2021, the team examined defect control in 3D printing and developed a rapid material optimization framework, which led to a 2020 patent. Using machine learning, researchers explored thousands of processing configurations virtually – reducing reliance on traditional trial-and-error methods.

By employing Bayesian optimization, AI quickly identified optimal settings that had previously been dismissed, enabling the production of stronger, denser titanium components. “This isn’t just about manufacturing parts more quickly,” said Croom. “AI is helping us explore processing regions we wouldn’t have considered on our own.”

Future work aims to expand AI’s capabilities, incorporating real-time in situ monitoring to adjust manufacturing conditions as printing occurs. “We envision a paradigm shift where future additive manufacturing systems can adjust as they print, ensuring perfect quality,” said Steve Storck, chief scientist for manufacturing technologies at APL.