stanford university researchers have used artificial intelligence (ai) and machine learning to identify 21 solid electrolytes that have the potential to replace volatile liquids and make safer lithium-ion batteries for a number of consumer electronic products.
austin sendek explains the stranford university project. (youtube)
in a report on the stanford website, austin sendek, a doctoral candidate who was the study’s lead author, said, “liquid electrolytes are cheap and conduct ions really well, but they can catch fire if the battery overheats or is short-circuited by puncturing.”
rather than testing individual material in the lab, the researchers used ai to formulate predictive models based on experimental data. they devised an algorithm that would screen possible compounds at a rate that was “a million times faster” than could be done with standard screening methods.
among the screening criteria were stability, cost, abundance and the ability to conduct lithium ions through the battery’s circuits. the researchers picked candidates from the materials project, which is a database for scientists detailing the physical and chemical properties of thousands of materials.
in just a few minutes, the researchers went from 12,000 compounds to 21 promising solid electrolytes. those compounds will now undergo lab testing.
the research was published in energy and environmental science. the abstract read:
“we present a new type of large-scale computational screening approach for identifying promising candidate materials for solid state electrolytes for lithium ion batteries that is capable of screening all known lithium containing solids.
“to be useful for batteries, high performance solid state electrolyte materials must satisfy many requirements at once, an optimization that is difficult to perform experimentally or with computationally expensive ab initio techniques. we first screen 12,831 lithium containing crystalline solids for those with high structural and chemical stability, low electronic conductivity, and low cost.
“we then develop a data-driven ionic conductivity classification model using logistic regression for identifying which candidate structures are likely to exhibit fast lithium conduction based on experimental measurements reported in the literature. the screening reduces the list of candidate materials from 12,831 down to 21 structures that show promise as electrolytes, few of which have been examined experimentally.
“we discover that none of our simple atomistic descriptor functions alone provide predictive power for ionic conductivity, but a multi-descriptor model can exhibit a useful degree of predictive power. we also find that screening for structural stability, chemical stability and low electronic conductivity eliminates 92.2% of all li-containing materials and screening for high ionic conductivity eliminates a further 93.3% of the remainder. our screening utilizes structures and electronic information contained in the materials project database.”
learn more about the process in the video below:
|