Power Transformer Condition Data from East China Grid for Model Comparison

A small dataset of 5.5 KB containing performance comparison results for models monitoring power transformers. The data likely originates from a multi-channel sensor platform collecting variables like partial discharge acoustic signals, voltage, current, and oil-dissolved gas concentration. The dataset was authored by Wenbo Zhang and last updated on April 20, 2026.

Use Cases

• Benchmarking deep learning models for fault classification based on multi-source sensor data.
• Training ensemble classifiers for transformer state discrimination based on fused spatial and temporal features.
• Evaluating the performance of 2D-CNN and BiLSTM fusion methods for industrial time-series and image data.
• Studying small-sample fault recognition techniques in power system equipment monitoring.

Strengths

• Data is derived from real-world equipment at the Dongwu Station in the east China power grid.
• The dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.
• The description details a specific methodological approach for feature fusion and classification.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope or summary results rather than raw sensor streams.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for model training.

Provenance

Source

figshare, authored by Wenbo Zhang.

Collection Method

Collected via a multi-channel sensor platform from power transformers, as described in the associated paper.

Time Range

null

Freshness

Last updated 2026-04-20 17:41:37; freshness should be verified.

Geography

Data is from the east China power grid, specifically Dongwu Station transformers.