XJTU Battery Dataset: 55 LISHEN NCM 18650 Cells Cycled under Six Charge-Discharge Strategies
- Provider
- Fujin Wang et al., Xi'an Jiaotong University
- License
- CC-BY-4.0 (source)
- Size
- 7 files
- Format
- JSON (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/bsebench-org/xjtu-pinn4soh-2024-raw)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.5281/zenodo.10963339
- Category
- Energy
- Source
- https://doi.org/10.5281/zenodo.10963339
About this dataset
Lithium-ion battery aging dataset from Xi'an Jiaotong University, released with the Nature Communications paper on physics-informed neural networks (PINN) for state-of-health (SOH) estimation and prognosis. It covers 55 LISHEN 18650 NCM cells (LiNi0.5Co0.2Mn0.3O2, 2000 mAh nominal, 3.6 V, cut-offs 4.2 V and 2.5 V) cycled at room temperature under six charge and discharge strategies on an ACTS-5V10A-GGS-D platform, with voltage, current, temperature and capacity sampled at 1 Hz. The data come as the original Battery Dataset.zip archive (about 2.4 GB) with a Data Introduction PDF; Python preprocessing code is on the author's GitHub (Battery-dataset-preprocessing-code-library). 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 Zenodo by Fujin Wang under CC-BY-4.0; cite Wang et al., Nat Commun 15, 4332 (2024).
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="bsebench-org/xjtu-pinn4soh-2024-raw", filename="Battery Dataset.zip", repo_type="dataset")
print(path)Data structure
File types in sampled files: JSON
Files
Example file: Battery Dataset.zip
Analyze this dataset without downloading it
On Scigantic, XJTU Battery Dataset: 55 LISHEN NCM 18650 Cells Cycled under Six Charge-Discharge Strategies 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
- DOE Geothermal Data Repository: Imperial Valley Dark Fiber Project Continuous DAS Data
- University of Malaya Battery Test Data: LFP, Panasonic NCR18650B and Murata VTC6 Cells under Drive Cycles and HPPC (bsebench copy)
- Synthetic Li-ion Voltage-Capacity Curves with Degradation-Mode Labels (Graphite/LFP, NCA, NMC)
- Stanford-SLAC High-Power Li-ion Characterization Dataset: Molicel P42A Cells for Stochastic Battery Modeling (Onori lab, bsebench copy)
- Empa Aurora: 199 Robot-Assembled NMC and LFP Coin Cells Cycled 1,000 Times (BattINFO RO-Crate)
- EV Lithium-Ion Battery State of Charge Dataset: 604,750 Samples from Regulated Charge-Discharge Cycling (SR University, bsebench copy)
- NREL Rapid DC Pulse Battery Diagnostics: 50,000 Pulse Sequences from about 80 Commercial Li-ion Cells
- Attia et al. Closed-Loop Optimization of Extreme Fast Charging: Toyota Research Institute Cell Cycling Data (bsebench copy)