Johns Hopkins researchers leverage powder bed fusion to unlock new processing domains for Ti-6Al-4V.
The material properties of parts made with additive manufacturing (AM) can differ from those of parts made with more conventional manufacturing techniques as a result of differences in in their microstructure. While this presents challenges in terms of repeatability and certification, it also presents an opportunity.
A team of researchers from the Johns Hopkins Applied Physics Laboratory (APL) and the Johns Hopkins Whiting School of Engineering have seized that opportunity by using artificial intelligence (AI) to identify AM processing techniques that improve both the speed of production and the strength of these advanced materials.
“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 in a press release. “At APL, we are advancing research in laser-based additive manufacturing to rapidly develop mission-ready materials, ensuring that production keeps pace with evolving operational challenges.”
The team leveraged AI-driven models to map out previously unexplored manufacturing conditions for laser powder bed fusion (L-PBF). According to the researchers, their results challenge long-held assumptions about process limits, revealing a broader processing window for producing dense, high-quality titanium with customizable mechanical properties. The findings focus on Ti-6Al-4V.
“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, in the same release. “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 ability to stretch or deform without breaking. Now, engineers can select the optimal processing settings based on their specific needs.”
The ability to manufacture stronger, lighter components at greater speeds could improve efficiency in shipbuilding, aviation and medical devices, in addition to contributing to a broader effort to advance additive manufacturing for aerospace and defense.
The team’s machine learning approach revealed a high-density processing regime previously dismissed due to concerns about material instability. With targeted adjustments, the team unlocked new ways to process Ti-6Al-4V.
“We’re not just making incremental improvements,” said Steve Storck in the press release. Storck is chief scientist for manufacturing technologies in APL’s Research and Exploratory Development Department. “We’re finding entirely new ways to process these materials,” he said, “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.”
Instead of manually adjusting settings and waiting for results, the team trained AI models using Bayesian optimization, a machine learning technique that predicts the most promising next experiment based on prior data. By analyzing early test results and refining its predictions with each iteration, AI rapidly homed in on the best processing conditions — allowing researchers to explore thousands of configurations virtually before testing a handful of them in the lab.
This approach allowed the team to quickly identify previously unused settings — some of which had been dismissed in traditional manufacturing — that could produce stronger, denser titanium. The results overturned long-held assumptions about which laser parameters yield the best material properties.
Read the rest of this story at ENGINEERING.com
