AI-Driven Breakthrough Advances Titanium 3D Printing
Researchers at Johns Hopkins Applied Physics Laboratory (APL) and the Johns Hopkins Whiting School of Engineering are leveraging artificial intelligence to enhance metal 3D printing, optimizing the production of high-performance titanium alloy components. Their AI-driven approach accelerates the manufacturing process for Ti-6Al-4V, a widely used titanium alloy valued 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. The research focuses on laser-based additive manufacturing, specifically laser powder bed fusion, where AI-driven models have expanded the range of viable processing parameters. This allows for faster production while maintaining or improving material properties.
“For years, we assumed certain processing parameters were ‘off-limits’ because they led to poor-quality end products,” explained Brendan Croom, a senior materials scientist at APL. “By using AI to explore a broader range of possibilities, we discovered new processing regions that enhance printing speed without compromising material strength and ductility.”
This breakthrough has significant implications for industries reliant on high-performance titanium parts, including aerospace, shipbuilding, and medical devices. AI-driven simulations, developed by researchers such as Somnath Ghosh, are also being used to predict how 3D-printed materials perform under extreme conditions, supporting NASA’s Space Technology Research Institutes (STRIs) in their efforts to expedite material qualification for space applications.
The research builds on previous work from 2021, when the team developed a rapid material optimization framework to improve defect control in 3D printing, leading to a patent in 2020. Machine learning enabled the virtual exploration of thousands of processing configurations, reducing reliance on trial-and-error experimentation.
Through Bayesian optimization, AI identified optimal settings that had previously been dismissed, leading to stronger and denser titanium components. “This isn’t just about manufacturing parts more quickly,” Croom emphasized. “AI is helping us explore processing regions we wouldn’t have considered on our own.”
Future research aims to integrate real-time in situ monitoring, enabling additive manufacturing systems to adjust conditions dynamically during printing. “We envision a paradigm shift where future additive manufacturing systems can adapt on the fly, ensuring perfect quality,” said Steve Storck, chief scientist for manufacturing technologies at APL.
