AI system could improve U.S. Army fuel cell efficiency

RESEARCH TRIANGLE PARK, N.C. As part of an effort to address the gap the U.S. Army faces in the need for long-lasting power and batteries for warfighters, the Army Research Office funded a research team who developed an artificial intelligence system that officials say identifies a material for creating more efficient fuel cells.

Photo courtesy of the U.S. Army.

The system relies on a collective of algorithmic bots each performing a distinct task and sifts through combinations of elements to create a map of phases — arrangements of atoms in relation to each other — that humans can then use to determine which might work as a new material.

It all comes down to a catalyst that would allow them to replace hydrogen, which is difficult to store, with methanol, which could be far more efficient. No known materials could act as efficient catalysts for methanol oxidation, so a new material is needed.

This would then require understanding the crystal structure of the material because each one behaves differently as a catalyst, which is difficult for machine learning to understand.

Researchers developed a system called CRYSTAL for crystal phase mapping and were able to identify a unique catalyst, composed of three elements crystallized into a certain structure, which is effective for methanol oxidation and could be incorporated into methanol-based fuel cells. According to researchers, the outcome of this research is to make battery power readily, and continuously, available to soldiers in a form that is safe and easily transportable.