Published August 17, 2026
| Version v1
Dataset
Open
Multimodal Transformer Defect Recognition Dataset
Authors/Creators
- 1. State Grid Henan Electric Power Company, State Grid Henan Electric Power Research Institute
- 2. State Key Laboratory of Complex & Critical Software Environment, School of Computer Science and Engineering, Beihang University
Description
Overview
This dataset supports multimodal defect recognition for electrical (main) transformers. It comprises three heterogeneous modalities namely, inspection-log text, dissolved gas analysis (DGA) measurements, and appearance images, aligned to a unified ten-class defect recognition framework.
The unified defect recognition framework is:
Θ = {overheating, discharge, moisture ingress, solid-insulation aging, fire, oil leakage, rust and corrosion, cable defect, insulator crack, normal}
Each modality covers only a partially overlapping subset of these ten classes; this partial coverage is the phenomenon the accompanying paper's capability-mask mechanism is designed to handle.
Files
data.zip
Additional details
Funding
- State Grid Henan Electric Power Company Limited
- Research on Key Artificial Intelligence Technologies for Improving the Intelligence Level of Main Equipment Health Management 52170225001F