NREL Rapid DC Pulse Battery Diagnostics: 50,000 Pulse Sequences from about 80 Commercial Li-ion Cells

Provider
Paul Gasper et al., National Renewable Energy Laboratory
License
CC-BY-4.0 (source)
Size
9 files
Format
JSON (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/bsebench-org/nrel-pulse-diagnostics-2025-raw)
Access
Free and public. No account with the data provider is needed.
DOI
10.17632/ksc4sv46x6.1
Category
Energy
Source
https://doi.org/10.17632/ksc4sv46x6.1

About this dataset

Data and code from the National Renewable Energy Laboratory study Searching for a Pulse, which evaluates rapid DC pulses for diagnosing lithium-ion battery health, state of charge and safety. About 50,000 independent DC pulse sequences were collected from roughly 80 cells of four commercial cell types with varying state of health (lab-aged, field-aged, or both), pulse state of charge, pulse design and current, temperature and hysteresis, alongside performance metrics for rate capability, mobility and stationary storage applications. Safety screening uses post-charge voltage relaxation and rapid X-ray CT. Machine learning models predict the target metrics from pulse data; analysis code is at github.com/NREL/battery_pulse_diagnostics. The mirror holds about 2.4 GB of original files. Hosted on Hugging Face by BSEBench as a raw, checksum-verified mirror of the original files with provenance JSON and SHA-256 manifests. Published on Mendeley Data by Gasper, Prakash, Knutson, Bethel, Ramirez-Meyers, Condon, Attia and Keyser under CC BY 4.0; cite J. Electrochem. Soc. (doi:10.1149/1945-7111/addd50).

How to load this dataset in Python

from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="bsebench-org/nrel-pulse-diagnostics-2025-raw", filename="data/battery_pulse_diagnostics.zip", repo_type="dataset")
print(path)

Data structure

File types in sampled files: JSON

Files

Example file: data/battery_pulse_diagnostics.zip

Analyze this dataset without downloading it

On Scigantic, NREL Rapid DC Pulse Battery Diagnostics: 50,000 Pulse Sequences from about 80 Commercial Li-ion Cells opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Energy datasets