Researchers at Washington State University have used artificial intelligence to discover a faster and more cost-effective method for 3D printing a high-performance metal alloy, eliminating the need to manually test over 100 million possible printing configurations. This breakthrough could make the alloy—widely used in aerospace and potentially other industries—printable on more common commercial equipment. The AI-driven approach may also prove useful for other scientific challenges involving vast numbers of potential experiments, such as drug discovery.
The team, from WSU's School of Electrical Engineering and Computer Science and the School of Mechanical and Materials Engineering, published their findings in the Proceedings of the AAAI Conference on Artificial Intelligence. The project also received the Innovative Deployed Application Award at the organization's annual conference.
"Ninety percent of commercial printers cannot print this metal alloy," said Jana Doppa, Huie-Rogers Endowed Chair Professor of Computer Science and Berry Distinguished Professor in Engineering, who led the research. "Given that we were able to find feasible process parameters, it allows us to use those commercial printers, and we are essentially democratizing the printing of this alloy."
A NASA Alloy Built for Extreme Heat
The material, GRCop-42, is an alloy composed of copper, chromium, and niobium. NASA developed it for demanding environments where both heat resistance and efficient heat transfer are critical. Due to its high thermal conductivity and strength at extreme temperatures, GRCop-42 is used in aerospace systems, including liquid rocket engine combustion chambers. Despite its desirable properties and broader potential, the alloy is difficult and costly to 3D print because the process typically requires high-power lasers and precise conditions.
In 2026, the team applied a sophisticated AI algorithm to search through more than 100 million possible printing configurations. After just 40 actual experiments, the system identified six successful parameter sets, including one that operated at a record-low power of 500 watts—a level achievable by many standard commercial printers. This finding could significantly lower the barrier to producing GRCop-42 components, making the alloy more accessible for a wider range of applications.
The AI methodology developed here is not limited to materials science. By efficiently navigating enormous parameter spaces with minimal experimental runs, the approach could accelerate innovation in fields ranging from pharmaceuticals to advanced manufacturing, where optimizing processes is often a bottleneck.
As 3D printing continues to evolve, integrating AI-driven optimization will likely become a standard practice, enabling the production of sophisticated materials with greater ease and affordability. This study marks a notable step toward that future, demonstrating that intelligent algorithms can unlock new possibilities in material science and beyond.