AI-driven system discovers six new metal alloys that could reshape jet engines and nuclear power

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 speed up discovery in just weeks.

One alloy composed of 12% nickel, 62% cobalt and 26% chromium demonstrated exceptional hardness at temperatures up to 1,112 F, outperforming industry-standard Inconel 625 by 4.5%.

Another alloy made of 36% nickel, 14% cobalt and 50% chromium showed 85% better oxidation resistance than Inconel 625 at temperatures reaching 1,832 F, targeting hotter sections of jet engines.

The research team plans to increase complexity in future work, aiming to develop alloys with up to 10 or 12 different elements, demonstrating that AI can compress years of materials discovery into weeks.

Researchers at the University of Toronto's Department of Materials Science and Engineering have used an artificial intelligence (AI)-driven discovery platform to identify six new metal alloys that retain strength under extreme heat and pressure, a breakthrough that could lead to more durable parts for jet engines, nuclear power plants and other demanding applications.

The team, led by Canada Research Chair Yu Zou, developed the alloys within just a few weeks using a method called active learning – which combines computer modeling, machine learning and robot-assisted manufacturing. The materials are also compatible with 3D metal printing, enabling the production of complex components that cannot be made using traditional methods. The findings were published in the journal npj Advanced Manufacturing in June 2026.

The system works like a self-driving laboratory. 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.

"There's 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 Zou, the study's corresponding author.