AI Helps Identify Polymer Compound That Can Take the Heat in Film CapacitorsAI Helps Identify Polymer Compound That Can Take the Heat in Film Capacitors

Scripps Research, the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab), and several other collaborating institutions have successfully demonstrated a machine-learning technique to accelerate discovery of polymer materials for film capacitors — crucial components in electrification and renewable energy technologies. The technique was used to screen a library of nearly 50,000 chemical structures to identify a compound with record-breaking performance. The other collaborators include the University of Wisconsin–Madison, University of California, Berkeley, and University of Southern Mississippi.

High temperature for high power in EVs

Their research, reported in the journal Nature Energy on Dec. 5, 2024, highlights the rapidly growing demand for film capacitors that can be used in high-temperature, high-power applications such as electric vehicles (EVs), electric aviation, power electronics, and aerospace. Film capacitors are also essential components in the inverters that convert solar and wind generation into the alternating-current power that can be used by the electric grid.

AI-optimized polymer design

This study builds on their previous work that discovered a new type of polysulfate compound. Films made of these compounds shielded capacitors from destruction by harsh conditions such as high operating heat environments and high electric fields. 

“As a chemist, our previous findings presented an existential challenge: How could a powerful electromagnetic energy wave from physics be tamed by passing through a thin polysulfate film?” said K. Barry Sharpless, co-senior author of the new study. “Now, our new collaboration has enabled a significant advancement in this project, which seeks much better capacitor shields that could lead to crucial energy savings in common electric power applications. In short, our AI analysis quickly identified some key variables in the polymer design details that were predicted to add big improvements in the shielding properties of these polysulfate membranes. These earliest machine learning predictors for improving the capacitors are dramatically borne out by experiment.”

“For cost-effective, reliable renewable energy technologies, we need better performing capacitor materials than what are available today,” added Yi Liu, co-senior author of the study. “This breakthrough screening technique will help us find these ‘needle-in-a-haystack’ materials.”

Narrowing down 49,700 polymers to three

Researchers have traditionally looked for high-performance polymers through trial and error, synthesizing a few candidates at a time and then characterizing their properties.

To accelerate discovery, the research team developed and trained a set of machine-learning models, known as feed-forward neural networks, to screen a library of nearly 50,000 polymers for an optimal combination of properties, including high energy storage density, ease of synthesis, and the ability to withstand high temperatures and strong electric fields. The models identified three particularly promising polymers.

Interestingly, these three polymers had already been discovered by Sharpless, Liu, and team in a previous study. They had synthesized the compounds using a powerful technique, known as click chemistry, that rapidly and efficiently links together molecular building blocks into high-quality products. Sharpless was one recipient of the 2022 Nobel Prize in chemistry for his role in developing the click-chemistry concept.

The researchers fabricated film capacitors from these polymers and then evaluated both the polymers and capacitors. The team found that they had exceptional electrical and thermal performance. Capacitors made from one of the polymers exhibited a record-high combination of heat resistance, insulating properties, energy density, and efficiency.