Creating Safer Batteries with Artificial Intelligence

A research team from Stanford University claims that they have identified more than 20 solid electrolytes with the help of techniques that have been adapted from machine learning and AI. The team members claim that they can replace the volatile liquids, mostly used in smartphones or laptops and several other electronic devices with great ease. A doctoral candidate and a team member, Austin Sendek, says, “Electrolytes shuttle lithium ions back and forth between the battery’s positive and negative electrodes. Liquid electrolytes are cheap and conduct ions well, but they can catch fire if the battery overheats or gets short-circuited by puncturing.”

He further adds that, “The main advantage of solid electrolytes is stability. Solids are far less likely to blow up or vaporize than organic solvents. They’re also much more rigid and would make the battery structurally stronger.”

To shorten up the time and in place of testing individual compounds quite randomly, the team chose AI with machine learning and built predictive models from experimental database. They prepared a computer algorithm to memorize how to differentiate between good and bad compounds on the basis of pre-existing data. The researchers are of the opinion that this one works just like the facial recognition algorithm that slowly learns to identify faces after screening multiple examples.

Scientists turn to AI to create safer batteries

Sendek further explains, “The number of known lithium-containing compounds is in the tens of thousands, the vast majority of which are untested. 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.”

To make up this model, Sendek spent more than 24 months to assemble all data about solid substances like lithium. The model made use of numerous criteria to finalize on the best materialize such as stability, cost, abundance, stability, as well as its ability to send these lithium ions and resend electrons via the battery’s circuit. Sendek then concludes, “We screened more than 12,000 lithium-containing compounds and ended up with 21 promising solid electrolytes. 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.”