AI, 3D Printing Forge Heat-Resistant Aerospace Materials

Researchers use AI and additive manufacturing to redesign refractory alloys for advanced defense systems.

Published on Mar. 5, 2026

Got story updates? Submit your updates here. ›

Researchers at Arizona State University and UNSW Sydney have formed an international collaboration to use artificial intelligence and 3D printing to redesign refractory alloys - metals that can withstand extreme heat - for use in advanced defense systems like hypersonic aircraft and nuclear submarines. The team is using reinforcement learning, a form of AI, to explore thousands of possible alloy recipes and identify the most promising combinations that can be reliably 3D printed while retaining their heat-resistant properties.

Why it matters

Refractory alloys are essential for components in advanced defense systems that are exposed to extreme heat, stress and radiation. However, many current refractory alloys are difficult or impossible to manufacture reliably using 3D printing techniques. This mismatch can slow the domestic production of new parts. The researchers' work aims to address these manufacturing and supply-chain challenges by redesigning high-temperature alloys that can be produced using additive manufacturing.

The details

The researchers are using reinforcement learning, a form of AI, to explore thousands of possible alloy recipes and identify the most promising combinations that can be reliably 3D printed while retaining their heat-resistant properties. The AI system evaluates each candidate alloy virtually against criteria like strength at high temperatures, resistance to damage from oxygen, weight, cost, and printability. Alloys that perform well are rewarded, while those that fail are discarded. Over repeated cycles, the system learns which chemical combinations work best. The most promising AI-designed alloys are then manufactured and tested in the laboratory, with the real-world performance feeding back into the model to improve its predictions.

  • The researchers' collaboration is in its early stages, with the team currently building the AI model and assembling the experimental databases it will learn from.
  • Later this year, the first candidate alloy compositions will be selected for 3D printing and laboratory testing, with the results feeding back into the model.

The players

Houlong Zhuang

Associate Professor of Engineering at Arizona State University.

Vitor Rielli

Lecturer in Materials Science and Engineering at UNSW Sydney.

Security and Defence PluS Alliance

The research collaboration is funded by the Security and Defence PluS Alliance.

NASA

NASA's GRX-810 alloy, designed with computational methods and 3D-printed, is 1,000 times more durable at high temperatures compared with traditional alloys.

Got photos? Submit your photos here. ›

What they’re saying

“Designing a new alloy is a bit like mixing ingredients for a recipe, but at the atomic level. Instead of planning moves on a board, the AI system explores thousands of possible alloy recipes - for example, different combinations of chemical elements. Even tiny changes in the ingredients can completely change how the final material behaves.”

— Houlong Zhuang, Associate Professor of Engineering (Mirage News)

“For defense agencies, faster materials development means quicker deployment for next-generation engines, hypersonic vehicles and systems that protect against heat. AI-designed alloys can be optimized for strength, heat resistance and manufacturability.”

— Vitor Rielli, Lecturer in Materials Science and Engineering (Mirage News)

What’s next

The researchers are working with defense research agencies to ensure their work aligns with real-world needs and to lay the groundwork for larger-scale programs.

The takeaway

By using AI and additive manufacturing to redesign refractory alloys, the researchers aim to address manufacturing and supply-chain challenges, enabling faster deployment of next-generation defense systems that can withstand extreme heat, stress and radiation.