To create new energy storage technologies – including safer, lighter batteries with higher energy density – a team led by BIDS Research Affiliate Daniela Ushizima (a Staff Scientist in the Applied Mathematics and Computational Research Division at Berkeley Lab) has been working with scientists from the National Fuel Cell Research Center (NFRC) at UC Irvine, and collaborators from UC Berkeley’s Department of Electrical Engineering & Computer Sciences and School of Information, to improve quality control and quality assessment of new designs of rechargeable lithium metal batteries.
Together, they created new deep learning algorithms to automate the inspection of batteries with data acquired using advanced instruments, such as those at Berkeley Lab’s Advanced Light Source. By using X-ray tomography as the input data, as well as prototypes defined by battery experts, they developed automated methods to detect battery defects in rechargeable lithium metal batteries and measure their growth during battery cycling.
Ushizim was a speaker finalist in Berkeley Lab’s National Energy Storage Summit Virtual Pitchfest on March 9, with a pitch entitled “Advancing Lithium Metal Battery Design with Deep Learning,” and Ushizima presented further information about this research during her talk, Lithium Metal Battery Characterization using X-ray Imaging and Machine Learning, at the American Physical Society Meeting on March 16. Ushizima is also affiliated with Berkeley Lab’s Energy Storage Center, where researchers are conducting research work across the entire energy storage landscape, including discovery science, applied research, deployment analysis, and policy research.