Researchers have identified dozens of electrolytes that could be alternative solutions to volatile liquids used in smartphones.
Researchers at Stanford University used machine learning and AI involvement to find suitable electrolytes. Their findings were published in the Energy & Environmental Science journal.
No ad to show here.
These new electrolytes could replace liquids used in batteries which power smartphones, laptops as well as other electronic devices.
Lead author of the paper Austin Sendek, a doctoral candidate in applied physics, commented on the findings in a press release.
“Electrolytes shuttle lithium ions back and forth between the battery’s positive and negative electrodes,” he explained. “Liquid electrolytes are cheap and conduct ions really well, but they can catch fire if the battery overheats or is short-circuited by puncturing.”
One of the main advantages of these solid electrolytes is their stability, which means that they’re less likely to explode than organic substances.
Using AI, the team built predictive models from their data. Once the system was built, they trained the programme to recognise stable and volatile substances based on The Materials Project database. This gave them access to physical and chemical properties for thousands of materials.
Researchers have discovered how to use certain electrolytes to potentially produce safer batteries for smartphones
“The number of known lithium-containing compounds is in the tens of thousands, the vast majority of which are untested,” said Sendek.
“Some of them may be excellent conductors. We developed a computational model that learns from the limited data we already have, and then allows us to screen potential candidates from a massive database of materials about a million times faster than current screening methods,” he continued.
Using several criteria to screen whether or not a specific material was a suitable candidate, the algorithm looked at its stability, cost, abundance as well as how well they conduct lithium ions. The AI also looked at how well the material could re-route electrons throughout the circuit.
“We screened more than 12 000 lithium-containing compounds and ended up with 21 promising solid electrolytes,” said Sendek. “It only took a few minutes to do the screening. The vast majority of my time was actually spent gathering and curating all the data, and developing metrics to define the confidence of model predictions.
“As the amount of data in the world increases and as computers improve, our ability to innovate is going to increase exponentially. Whether it’s batteries, fuel cells or anything else, it’s a really exciting time to be in this field,” concluded Evan Reed, an assistant professor of materials science and engineering and a senior author on the paper.
Featured image: Estitxu Carton via Flickr
