AI Is the Answer to Safer Lithium-ion Batteries!
After battery fires sparked the recall of almost two million Samsung Galaxy Note7 smartphones, researchers from Stanford University have found a way to develop safer alternatives to flammable liquid electrolytes used in lithium-ion batteries. The volatile liquids utilized in most electronic devices could be replaced by solid electrolytes. The list of almost two dozen electrolytes was inspired by techniques adapted from artificial intelligence (AI) and machine learning.
Published in Energy & Environmental Science, the study featured a method that utilized AI and machine learning to create predictive models from experimental data. "Electrolytes shuttle lithium ions back and forth between the battery's positive and negative electrodes," stated Austin Sendek, the lead author of the study and a doctoral candidate in applied physics. "Liquid electrolytes are cheap and conduct ions really well, but they can catch fire if the battery overheats or is short-circuited by puncturing."
A computer algorithm was trained to identify good and bad solid compounds based on existing data, performing like a facial-recognition algorithm that could identify faces after being exposed to several examples. "The main advantage of solid electrolytes is stability," Sendek explained. "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."
The search for viable solid compounds containing lithium to build the model lasted over two years. "The number of known lithium-containing compounds is in the tens of thousands, the vast majority of which are untested," Sendek said. "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."
Upon completing their screening, Sendek and his team found 21 materials that they could then evaluate in real-world conditions. "We screened more than 12,000 lithium-containing compounds and ended up with 21 promising solid electrolytes," Sendek said. "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."
"Our approach has the potential to address many kinds of materials problems and increase the effectiveness of research investments in these areas," said Evan Reed. An assistant professor of materials science and engineering and a senior author on the paper, Reed believes identifying the most viable materials will also lead to promising results. "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."