How robots and AI are helping develop better batteries

Sept. 30, 2022
A Carnegie Mellon team used an automated system and machine-learning software to develop fast-charging electrolytes that outperformed a standard one, James Temple reports for the MIT Technology Review.

PITTSBURGH - Around the start of the year, Carnegie Mellon researchers used a robotic system to run dozens of experiments designed to generate electrolytes that could enable lithium-ion batteries to charge faster, addressing one of the major obstacles to the widespread adoption of electric vehicles, James Temple reports for the MIT Technology ReviewContinue reading original article.

The Military & Aerospace Electronics take:

30 September 2022 - According to Temple, CMU used the system of automated pumps, valves, and instruments, known as Clio, mixed various solvents, salts, and other chemicals together, then measured how the solution performed on critical battery benchmarks. Those results were then fed into a machine-learning system, known as Dragonfly, that used the data to propose different chemical combinations that might work even better.

According to the study abstract, published in Nature, "Clio can efficiently and autonomously explore and optimize an objective over a given design space. We consider optimization for fast-charging, focusing initially on single objective optimization of the bulk ionic conductivity as an objective for improving battery rate-capability performance. While this aspect is a preliminary objective function, the workflow introduced in this paper can also enable effective multi-objective optimization25 of electrolytes in future studies. Clio autonomously optimized conductivity over solvent mass fraction and salt molality in a design space featuring: ethylene carbonate (EC), ethyl-methyl carbonate (EMC), and dimethyl carbonate (DMC) as a ternary solvent combination; and lithium hexafluorophosphate (LiPF6) as a single-salt system. Optimal electrolytes are passed through a sequence of fast-charging electrochemical tests conducted in graphite∣∣LiNi0.5Mn0.3Co0.2O2 pouch cells. These results are reported against a baseline electrolyte selected a priori from the design space."

Related: The progress and future of eVTOL avionics

Related: NASA's Advanced Air Mobility mission researches noise

Related: Honeywell has a new urban air mobility lab. Why does its avionics research matter for UAM?

Jamie Whitney, Associate Editor
Intelligent Aerospace

Voice your opinion!

To join the conversation, and become an exclusive member of Military Aerospace, create an account today!