Glimpse’s first publication

Over 1,000 CT scans of lithium-ion and sodium-ion batteries

We’re excited to announce Glimpse’s first published paper! In this open-access work published in Data in Brief, we published an open dataset of over 1,000 computed tomography (CT) scans of commercially-available batteries. The dataset spans lithium-ion and sodium-ion chemistries and cylindrical, pouch, and prismatic form factors. We identified various battery quality issues such as low anode-cathode overhang and jellyroll buckling in these cells. Thus, this dataset can be used to study battery manufacturing variability and quality and to develop new computer vision routines for battery quality inspection.

To the best of our knowledge, this dataset is both the largest publicly-available dataset of battery test data and the largest dataset of industrial CT scans. While CT has a reputation for being slow, painful, and unwieldy, it doesn’t have to be! Glimpse’s technology transforms the massive volumes of data generated by this technique into a Quality Management Solution for rapidly obtaining insights into battery quality.

Glimpse’s mission is to enable battery quality at scale. By publishing this dataset, we hope to unlock both a broader understanding of the value of high-throughput CT scanning for battery quality control and exciting applications such as developing computer vision models for quantifying key battery quality metrics (e.g., insufficient electrode overhang).

You can find the published paper here and the dataset here. You can also easily view this dataset on the Glimpse Portal™ in “demo mode”. Note that the dataset is licensed under CC-BY-NC-SA-4.0, which allows for broad noncommercial usage. Please let us know if you do something exciting with this dataset!