What question did this study set out to answer?

This research aims to improve the accuracy and speed of substation wiring inspections using an optimized YOLOv8 architecture.

March 10, 2026Engineering ReportsOpen Access

SW ‐ YOLO : An Optimized YOLOv8 Architecture With ConvNeXt for Real‐Time and Accurate Substation Wiring Inspection

View Full Paper

Ask AI

Bookmark

Authors

Research demonstrates improved accuracy in wiring inspections for substations, suggesting enhanced power system safety.

This research aims to improve the accuracy and speed of substation wiring inspections using an optimized YOLOv8 architecture.
Introduced an improved convolutional block attention module within the YOLOv8 framework.
Implemented a comprehensive image enhancement strategy with affine transformations, contrast enhancement, and mosaic occlusion.
Enhanced feature extraction using the improved Convolutional NeXt module integrated into the YOLOv8 backbone.
Conducted ablation studies to validate the effectiveness of the new modules.
Achieved a mean Average Precision (mAP@0.5) of 96.5% and precision of 97.2% on a proprietary dataset.
Processed 158 frames per second, significantly outperforming existing baseline models like Faster R-CNN and YOLOv9.
Demonstrated substantial improvements in both accuracy and speed for substation panel wiring detection.

Lei et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark