YOLO-Based Detection and Classification of High-Voltage Insulator Surface Contamination

Serikbay A. Akhmetov Y. Nurmanova V. Zollanvari A. Bagheri M.
2026 Institute of Electrical and Electronics Engineers Inc.

IEEE Transactions on Dielectrics and Electrical Insulation
2026 #33 Issue 1 623 - 632 pp.

Outdoor high-voltage (HV) insulators are prone to surface contamination, increasing flashover risk and threatening power transmission systems’ reliability. Timely inspection is essential, but conventional visual inspections are costly and inefficient for long transmission lines. An automated inspection using uncrewed aerial vehicle (UAV) images can be both efficient and low-cost. Given an appropriate training sample, a deep neural network, such as you only look once (YOLO), can be trained to localize insulators in diverse backgrounds and classify surface contamination. However, the wide variety of YOLO architectures proposed recently makes model selection challenging due to the accuracy and complexity tradeoffs. Rather than proposing a new model, this study focuses on selecting the “optimal” one. To this end: 1) a “laboratory” dataset of 15 000 insulator images with various surface contaminations is collected; 2) 21 YOLO architectures (YOLOv3–v11 and their variants) are trained, followed by a domain-specific (DS) model selection based on accuracy and complexity tradeoffs; and 3) the selected DS-YOLOv11m and DS-YOLOv11n are fine-tuned on a small “industry” dataset of 356 images from a local HV substation to validate DS pretraining in real-world scenarios. This work presents the first DS benchmarking of YOLOv3–v11 for insulator detection and contamination classification, resulting in a lightweight model optimized for real-time edge deployment. Evaluation of the fine-tuned models shows mAP@0.5 scores of 0.983 (DS-YOLOv11m) and 0.977 (DS-YOLOv11n). Although DS-YOLOv11n achieves slightly lower accuracy, it uses significantly fewer resources, reducing FLOPs by ~10.7 times. Finally, DS-YOLOv11n is deployed on a Raspberry Pi 5 to enable real-time contamination classification in edge computing scenarios.

Fine-tuning , insulator diagnostics , model selection , Raspberry Pi , surface pollution , uncrewed aerial vehicle (UAV) image detection , you only look once (YOLO)

Text of the article Перейти на текст статьи

Nazarbayev University, Electrical and Computer Engineering Department, Astana, 010000, Kazakhstan
Utah Valley University, Department of Electrical and Computer Engineering, Orem, 84058, UT, United States

Nazarbayev University
Utah Valley University

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026