HUST Dataset: 77 LFP/Graphite Cells Cycled with Multi-Stage Discharge Protocols for Health Prediction (Ma et al., bsebench copy)
- Provider
- Guijun Ma, Songpei Xu, Ye Yuan et al. (Huazhong University of Science and Technology)
- License
- CC-BY-4.0 (source)
- Size
- 14 files
- Format
- JSON (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/bsebench-org/hust-lfp-health-2022-raw)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.17632/nsc7hnsg4s.2
- Category
- Energy
- Source
- https://doi.org/10.17632/nsc7hnsg4s.2
About this dataset
Cycling data from Huazhong University of Science and Technology (HUST) for Ma et al., Real-time personalized health status prediction of lithium-ion batteries using deep transfer learning (2022). The dataset has 77 lithium iron phosphate (LFP)/graphite cells of 1.1 Ah nominal capacity and 3.3 V nominal voltage, cycled at a constant 30 °C with an identical charging protocol but different multi-stage discharge protocols, so the cells age along different trajectories until end of life. It is widely used as the HUST battery dataset for state-of-health (SOH) and remaining-useful-life (RUL) prediction and transfer learning. The BSEBench copy holds the original Mendeley version-2 download-all ZIP and the inner our_data.zip (about 2.35 GB) under raw/, with file listings, a DOI resolution record and an API snapshot. Licensed CC BY 4.0; cite Ma et al. 2022 and the Mendeley record doi:10.17632/nsc7hnsg4s.2.
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="bsebench-org/hust-lfp-health-2022-raw", filename="raw/nsc7hnsg4s-2.zip", repo_type="dataset")
print(path)Data structure
File types in sampled files: JSON
Files
Example file: raw/nsc7hnsg4s-2.zip
Analyze this dataset without downloading it
On Scigantic, HUST Dataset: 77 LFP/Graphite Cells Cycled with Multi-Stage Discharge Protocols for Health Prediction (Ma et al., bsebench copy) 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
- KIT Comprehensive Battery Aging Dataset, WLTC Driving-Cycle Subset: LG INR18650HG2 NMC/C-SiO Cell Logs (Luh and Blank, bsebench copy)
- GLASS: Generative-AI Large-Customer Smart-Meter Samples, 43 Million Synthetic 15-Minute Daily Load and Generation Profiles (TU Delft, OpenSynth)
- DOE Geothermal Data Repository: Utah FORGE: Triggered DAS Data from April 2024 Stimulations
- City University of Hong Kong LFP and NMC Capacity-Fade Data at Different Temperatures for SOH and RUL Time-Series Modeling (bsebench copy)
- Stanford Galvanostatic Discharge Tests of NCA, NMC and LFP Cells at Multiple C-Rates and Temperatures (Catenaro and Onori, bsebench copy)
- Satlas Renewable Energy Infrastructure: Onshore Wind Turbine Points and Solar Farm Polygons from Sentinel-2, 2016 Onward (Ai2)
- Imperial College LG M50T 21700 Silicon-Graphite Degradation Data: Rapid Loss of Active Silicon (Kirkaldy et al., bsebench copy)
- DOE Geothermal Data Repository: Soda Lake Geothermal: Raw 3D and 3C Seismic-Reflection Data from 2010 Survey