Power Transformer Condition Monitoring Data from East China Grid

A 16.9 KB dataset of multi-sensor measurements for power transformer status monitoring. The data was collected from transformers at the Dongwu Station in the east China power grid and is used to classify five typical operating states. It was authored by Wenbo Zhang and last updated on April 20, 2026.

Use Cases

• Training models for transformer fault classification based on multi-source sensor data.
• Developing feature fusion methods for spatial and temporal signals like partial discharge and gas concentrations.
• Benchmarking deep learning architectures (e.g., CNN-LSTM hybrids) for industrial equipment monitoring.
• Studying the relationship between operational variables (voltage, current, gas) and transformer health states.

Strengths

• Data is derived from real-world transformers in the east China power grid, providing practical relevance.
• Includes multiple sensor modalities (acoustic, electrical, chemical) for a multi-faceted view of equipment condition.
• The dataset is shared under a permissive CC-BY-4.0 license, allowing for broad reuse and modification.

Limitations

• The dataset is very small at 16.9 KB, indicating limited scope and sample size.
• Row count and column-level documentation are unknown, complicating suitability assessment.
• The description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

figshare, authored by Wenbo Zhang.

Collection Method

Collected via a multi-channel sensor platform monitoring transformers at Dongwu Station.

Time Range

null

Freshness

Last updated 2026-04-20 17:41:22; freshness should be verified.

Geography

East China power grid, specifically Dongwu Station.