A Systematic YOLO‐Specific Model Selection for Mechanical Fault Identification in High‐Voltage Insulators

Regular monitoring of outdoor insulators is crucial to ensure the reliable functioning of the power grid. With recent progress in computer vision technologies, traditional manual and expensive visual inspections can now be replaced by automated analysis using images captured by unmanned aerial vehicles (UAVs). In such applications, a practitioner might opt to choose a state‐of‐the‐art object detection and classification deep learning architecture, including You Look Only Once (YOLO). The variety of existing YOLO architectures per se makes selecting the best application‐dependent YOLO model challenging. However, selecting the best architecture solely based on performance without considering the model complexity limits its deployment on resource‐limited embedded devices. Consequently, we conduct a rigorous, systematic model selection based on the performance–complexity trade‐off across 13 YOLO architectures to determine the most effective model for detecting common mechanical faults in insulators using images captured by UAVs. A dataset comprising 15,000 images of insulators, categorized into normal condition, bird‐pecking damage, cracks, and missing caps, has been compiled for training the models. Specifically, all considered YOLO architectures are compared using model complexity and the [email protected]:0.95. During the model selection stage, YOLOv8l proved to be the best model in terms of [email protected]:0.95, while YOLOv5n was the model of choice in terms of complexity at the expense of a slight reduction in performance. Alongside YOLOv8l and YOLOv5n, an “optimal” model (OP‐YOLO) was selected using a multicriteria decision‐making approach, balancing detection accuracy and computational efficiency. In particular, in terms of test‐set performance, YOLOv8l, YOLOv5n, and OP‐YOLO achieved 0.919, 0.901, and 0.896 [email protected]:0.95, respectively. Although YOLOv8l reported a higher [email protected]:0.95, YOLOv5n requires ∼20.9 times less memory and ∼40.2 times less floating‐point operations per second (FLOPs). Also, YOLOv5n outperforms the OP‐YOLO model, still requiring ∼12 times less memory and ∼19 times less FLOPs.