SA-YOLOv11s: A Slicing-Attention YOLOv11s with U-IoU for Oil Leakage Detection in Power Equipment

To address the challenges of low detection accuracy and high missed detection rates in insulating oil leakage detection for power equipment-arising from small and densely distributed oil stains, structural occlusion, and complex background interference-this paper proposes a detection method based on an enhanced YOLOv11s (You Only Look Once version 11 small) architecture. First, a dedicated dataset is constructed, encompassing four representative scenarios-small object detection, complex background, multi-object detection and equipment occlusion-to evaluate detection performance. Second, in terms of network design, a proposed attention module, SimAMWS (Simple Attention Module With Slicing), is introduced. This module enhances the model's sensitivity to subtle and irregular oil stains by utilizing slicing operations and localized energy-based weighting. For bounding box regression, a U-IoU (Unified Intersection over Union) loss is adopted, which incorporates a dynamic scaling mechanism during training to enable the model to focus more effectively on high-quality candidate boxes-leading to improved localization accuracy, particularly suited to the characteristics of oil leakage. Finally, comparative experiments are conducted against mainstream object detectors including SSD (Single Shot MultiBox Detector), Faster R-CNN (Region-based Convolutional Neural Network), YOLOv5s, YOLOv8s, and the baseline YOLOv11s. The proposed method achieves an mAP@0.5 (mean Average Precision at IoU = 0.5) of 97.7% and an mAP@0.5:0.95 of 66.9%, with an inference speed of 96.4 FPS. These results demonstrate that the proposed model delivers higher detection accuracy while maintaining high inference efficiency, making it well-suited for real-time oil leak detection in power equipment and supporting the development of intelligent operation and maintenance systems in the power industry.