What question did this study set out to answer?

This study aims to enhance defect detection in substation equipment by improving detection accuracy and efficiency.

High-Performance and Lightweight Detection Network for Substation Equipment Defect Detection

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates enhanced defect detection in substation equipment, suggesting improved power system inspections.

This study aims to enhance defect detection in substation equipment by improving detection accuracy and efficiency.
Proposed an improved lightweight detection framework called GRID-YOLO.
Introduced a cross-stage hierarchical multi-cognitive spatial attention module and an enhanced multi-scale bidirectional feature pyramid network.
Constructed a dedicated dataset for substation equipment defect detection and conducted extensive comparative experiments.
GRID-YOLO achieved an mAP50 of 78.3%, surpassing the baseline by 6.1 percentage points.
mAP50–95, Recall, and F1-score reached 52.3%, 73.6%, and 77.6%, respectively.
Inference speed reached 506 FPS, demonstrating superior performance compared to other advanced detection models.

Hongliang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark