# Sonkyo Benchmark Wind Turbine Blade Vibration under Varying Temperature: Shaker Tests with Added Masses and Cut Cracks, -15 to +20 C (derived copy)

## Facts

- Provider: Ou, Tatsis, Dertimanis, Spiridonakos and Chatzi; derived copy by Emulated Inc
- License: CC-BY-4.0 (https://zenodo.org/records/3229743)
- Size: 9 files
- Stored at: Hugging Face, https://huggingface.co/datasets/Emulated-Inc/sci-blade-crack-severity-unseen-temperature
- Access: public, readable without an account
- Category: Physics
- Source: https://doi.org/10.1002/stc.2660
- Page: https://scigantic.com/archive/c233b32e-df79-56d0-a2b7-29d11d413743
- Keywords: Physics, benchmark, Hugging Face

## About

Vibration-based structural health monitoring data for a small wind turbine blade, taken from the Sonkyo benchmark of Ou, Tatsis, Dertimanis, Spiridonakos and Chatzi. A 1.75 m blade from a Windspot 3.5 kW turbine was excited by a shaker with white noise inside a climate chamber, in a healthy state, with one to three added masses, and with progressively cut cracks (13 cases in all). This derived copy keeps only the white-noise tests at chamber temperatures from -15 to +20 C. Six tar archives unpack to train/tests.csv (one row per test with case, state, added masses, crack lengths, chamber temperature and repeat number) and train/signals/ .npy arrays of shape (11, samples) at 1666.7 Hz holding eight accelerometers, the shaker force channel and two air-temperature channels; strain gauges, humidity and sine-sweep tests were left out. About 6.3 GB with SHA256SUMS (measured 2026-11-21); read with numpy and pandas. CC BY 4.0, as the source Zenodo record (DOI 10.5281/zenodo.3229743); cite Ou et al., Structural Control and Health Monitoring 28(6), e2660.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="Emulated-Inc/sci-blade-crack-severity-unseen-temperature", filename="SHA256SUMS", repo_type="dataset")
print(path)
```

## Data structure

Example file: `SHA256SUMS`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/c233b32e-df79-56d0-a2b7-29d11d413743
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/c233b32e-df79-56d0-a2b7-29d11d413743
- Over MCP: `get_schema_card` with id `c233b32e-df79-56d0-a2b7-29d11d413743` at https://api.scigantic.com/mcp

## Related topics

- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Physics datasets](https://scigantic.com/topics/physics)
