MFI-YOLO: Multi-Fault Insulator Detection Based on an Improved YOLOv8

Abstract

Insulators are essential components in power transmission lines. Due to the harsh variations in bad environments, insulators may experience faults. Detecting these insulator faults promptly and effectively is an urgent issue. To rapidly and accurately locate insulators and their faulty regions in aerial images of insulators with complex backgrounds and varying fault sizes, this paper proposes an improved YOLOv8 algorithm for the detection of multiple insulator fault types (MFI-YOLO). This algorithm achieved target feature extraction in complex background images by replacing the C2F network constructed by fusing the GhostNet and multi-scale asymmetric convolution (MSA-GhostBlock). Furthermore, in the feature fusion stage, a multi-scale feature fusion structure called ResPANet, based on residual skip connections, was constructed to replace the PANet. This enhancement aims to improve the network detection accuracy in multi-target scenarios. Finally, to evaluate the algorithm's performance, this study constructed a target detection dataset containing four types of insulators: normal, self-explosive, damaged, and flashover. Experimental results indicate that, compared to the original model, the improved model has increased mean accuracy from 89.2% to 93.9%. The designed model exhibits high detection accuracy in the insulator and its three fault categories, especially for some hard-to-detect fitting.