A Real-Time Edge Inference Method for Insulator Contamination Detection With YOLOv11-ssL

Insulators are a critical component of power transmission and distribution lines, requiring extensive in-service deployment. The accumulation of dust, bird droppings, rain, and snow leads to contaminated insulators, which can cause contamination flashovers, resulting in faults. Currently, manual contact-based detection of insulator contamination is costly and hazardous. In non-contact detection, image-based methods have developed rapidly, but the large data volume makes cloud transmission bandwidth-intensive and may result in high-latency, which hinders real-time detection. This paper aims to ensure the accuracy of contamination detection while reducing model complexity and parameter count, enabling low-cost real-time contamination inference on edge devices. The existing YOLOv11n-seg (a segmentation variant of YOLOv11) can already meet the accuracy requirements for insulator segmentation; therefore, this paper proposes the YOLOv11-ssL (a lightweight variant of YOLOv11) network to reduce the model size. First, to accurately capture insulator features, this paper designs a novel C3k2-star structure to enhance the information representation capability. Second, a Lightweight Shared Convolutional Separated BN Detection Head (LSCSBD) structure is proposed to reduce the model size. Finally, Layer-adaptive Magnitude-based Pruning (LAMP) is applied to YOLOv11-ssL to prune weights, significantly reducing the model size and computational workload. After segmenting the insulator, this paper introduces the DEMIC-mRMR algorithm to select the color features most correlated with the insulator contamination level; further, Gaussian Process Regression (GPR), a non-parametric regression model, is used to predict the insulator contamination level effectively. Experimental results showed that YOLOv11-ssL reduces the computational load and the number of parameters by 44.1% and 82.8%, respectively, while maintaining a mean Average Precision (mAP) without substantial decrease, and achieves an inference frame rate of 1144.5. Meanwhile, the R2 of insulator contamination detection reached 0.8674, satisfying the requirements for real-time and accurate contamination detection on edge inspection devices.