Jul 26, 2026 · AI News

AI system discovers six new metal alloys for jet engines and nuclear power

Lab scientist examining six newly discovered heat-resistant metal alloy samples

Researchers at the University of Toronto have used an AI-driven active learning platform to identify six new metal alloys that retain strength under extreme heat and pressure, with potential applications in jet engines and nuclear power plants. The system functions as a self-driving laboratory, using AI to select promising metal combinations, directing robots to manufacture and test them and feeding results back into the model to complete the discovery in just weeks. The findings were published in the journal npj Advanced Manufacturing in June 2026.

How does the AI-driven alloy discovery platform work?

The platform combines computer modeling, machine learning, and robot-assisted manufacturing in a closed loop. Rather than manually testing thousands of metal combinations, the AI selects the most promising options, directs robots to manufacture them, tests their performance, and feeds the results back into the model to guide the next round of experiments.

According to the study’s first author, Ajay Talbot, the approach overcomes a common limitation of AI-driven materials design. Most machine learning models require large datasets to make accurate predictions, but such data often does not exist for unexplored material combinations. The way the team gets around that challenge is to use data-lean models that essentially feel their own way along. The active learning model strategically selects a few samples to manufacture and test, and the data from those experiments is fed back into the model to inform where to go next.

The system is also compatible with 3D metal printing, enabling the production of complex components that cannot be made using traditional methods. The study, published in npj Advanced Manufacturing, integrates active learning with laser-based additive manufacturing to accelerate the discovery of NiCoCr complex concentrated alloys, which are alloys made from three or more principal elements in significant proportions.

What alloys did the system discover?

The team focused on compositionally complex alloys made from nickel, cobalt, and chromium. The study identified six new printable alloys that are up to roughly 40% harder than the popular equiatomic NiCoCr (an alloy containing equal atomic proportions of nickel, cobalt, and chromium) at room temperature. Two of the new alloys showed complementary advantages:

  • An alloy composed of 12% nickel, 62% cobalt, and 26% chromium demonstrated exceptional hardness at temperatures up to 1,112 F (600 C), outperforming Inconel 625 by 4.5%. It retained about 50% higher hardness than NiCoCr at 600 C, making it suited for conditions found in the front section of a jet engine.
  • An alloy comprising 36% nickel, 14% cobalt, and 50% chromium was designed for even hotter sections of jet engines reaching 1,832 F (1,000 C). It showed 85% better oxidation resistance than Inconel 625, reducing oxidation mass gain by 85% at 1,000 C compared with conventional superalloys.

Inconel 625 is an industry-standard nickel-based alloy made from more than 10 elements and widely used in jet engines, steam generators, and other demanding environments. Oxidation resistance refers to a material’s ability to resist being burned away or degraded at extreme temperatures.

Why are these alloys important for jet engines and nuclear power?

There is enormous demand for materials that can stand up to huge swings of temperature and pressure, such as what you would find inside a jet engine or in the steam generators inside nuclear power plants, anywhere conventional steel just can’t survive, remarked Yu Zou, the study’s corresponding author and a Canada Research Chair at the University of Toronto.

The team is eventually aiming to ramp up to even higher temperatures, up to 2,192 F (1,200 C). Historical precedents show that material breakthroughs often reshape entire sectors. The development of superalloys in the mid-20th century enabled jet engines to operate at higher temperatures, transforming aviation. With AI now acting as an accelerator, the search for new materials that once took years can now be compressed into weeks, opening pathways to components that are lighter, stronger, and more resistant to the punishing conditions inside engines and reactors.

What is the next step for the research?

The researchers view the current results as an early demonstration of what the platform can achieve. The current nickel-cobalt-chrome system has just three elements in it, but it is useful for showing that this whole closed-loop discovery platform really works. The team plans to ramp up the complexity to develop alloys with up to 10 or 12 different elements, aiming to create materials for even more demanding service conditions.

The project was partially supported by the University of Toronto’s Acceleration Consortium, a group that uses AI and automation to accelerate materials discovery. Additional funding came from the Natural Sciences and Engineering Research Council of Canada, the Canadian Foundation for Innovation, the Digital Research Alliance of Canada, and the New Frontiers in Research Fund.

Who led the research?

The study was conducted at the University of Toronto’s Department of Materials Science and Engineering, with affiliations including the Acceleration Consortium, the Vector Institute for Artificial Intelligence, and the Schwartz Reisman Institute for Technology and Society. Cristian Cojocaru from the National Research Council Canada also contributed. The research was supported in part by the Canada First Research Excellence Fund.

FAQ

What did the University of Toronto AI system discover?

It discovered six new printable metal alloys based on nickel, cobalt, and chromium that retain strength under extreme heat and pressure, with two outperforming Inconel 625 in hardness and oxidation resistance tests.

How is the AI alloy discovery platform different from traditional methods?

It uses an active learning approach that combines machine learning with robot-assisted manufacturing in a closed loop, allowing the AI to select promising compositions, direct robots to produce and test samples, and use the results to guide the next experiments in weeks rather than years.

Where could these new alloys be used?

The alloys are designed for demanding applications such as jet engines and nuclear power plant steam generators, where components must withstand extreme temperatures and pressures beyond the limits of conventional steel.

Related coverage


This article summarizes reporting from naturalnews.com.