MC-YOLO: A Lightweight Insulator Defect Detection Model Based on an Improved YOLOv8
DOI:
https://doi.org/10.4108/ew.13841Keywords:
Insulator Defect Detection, Lightweight Model, YOLOv8, MobileNetV3Abstract
Due to the fast growth of China’s electric power industry, the total length of high-voltage transmission lines has been continuously increasing. As a key component of high-voltage transmission systems, insulators play a critical role, and achieving efficient and accurate defect detection for insulators is of great significance. To address the practical challenges of limited size, limited computational resources, restricted energy supply, and complex environmental conditions on Unmanned Aerial Vehicle (UAV) platforms, this paper proposes a lightweight insulator defect detection model, MC-YOLO, based on an improved YOLOv8 architecture. Specifically, the original backbone network is replaced with the lighter MobileNetV3 module, reducing the model parameters and GFLOPs to 21.3% and 20% of those of the original model, respectively. In addition, a Convolutional Block Attention Module (CBAM) is integrated into the network neck structure to effectively improve the extraction of key features, resulting in a 1.2 percentage points improvement in detection accuracy. Finally, the loss function is changed to Wise-IoU (WIoU) v3, which increases the localization capacity of the model and further increases the accuracy by 1.4 percentage points. Experimental results demonstrate that the proposed MC-YOLO model achieves a lightweight design while maintaining high detection performance, providing a viable technical solution for edge deployment in real-world engineering applications.
Downloads
References
[1] National Energy Administration of China. Length of Transmission Lines of 220 kV and Above Reached About 920,000 Kilometers; 2024. Accessed: 2025- 09-21. https://www.nea.gov.cn/2024-07/19/c_1310782066.htm.
[2] Park KC, Motai Y, Yoon JR. Acoustic Fault Detection Technique for High-Power Insulators. IEEE Transactions on Industrial Electronics. 2017;(64-12).
[3] Qiu Z, Zhu X, Liao C, Shi D, Qu W. Detection of transmission line insulator defects based on an improved lightweight YOLOv4 model. Applied Sciences. 2022;12(3):1207.
[4] LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015;521(7553):436-44.
[5] Liu C, Wu Y. Research Progress on Visual Inspection Methods for Transmission Lines Based on Deep Learning. Proceedings of the Chinese Society for Electrical Engineering. 2023;43(19):7423-46.
[6] Wang Z, Wang Y, Wang Q, Kang S, Mikulovich VI. Two-Stage Insulator Fault Detection Method Based on Cooperative Deep Learning. Transactions of China Electrotechnical Society. 2021;36(17):3594-604.
[7] Chen Y, Liu H, Chen J, Hu J, Zheng E. Insu-YOLO: an insulator defect detection algorithm based on multiscale feature fusion. Electronics. 2023;12(15):3210.
[8] Song Z, Huang X, Ji C, Zhang Y. Transmission Line Insulator Defect Detection and Fault Early Warning Method Based on Flexible YOLOv7. High Voltage Engineering. 2023;49(12):5084-94.
[9] Zhang J, Wei X, Zhang L, Chen Y, Lu J. Insulator Detec-tion and Localization Using an Improved YOLOv7. Com-puter Engineering and Applications. 2024;60(4):183-91.
[10] Ultralytics. YOLOv8 Documentation; 2023. Accessed: 2025-09-05. https://docs.ultralytics.com/models/yolov8/.
[11] Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, et al. Searching for mobilenetv3. In: Proceedings of the IEEE/CVF international conference on computer vision; 2019. p. 1314-24.
[12] Woo S, Park J, Lee JY, Kweon IS. Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV); 2018. p. 3-19.
[13] Tong Z, Chen Y, Xu Z, Yu R. Wise-IoU: bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv:230110051. 2023.
[14] Ennaama S, Silkan H, Bentajer A, Tahiri A. Enhanced real-time object detection using YOLOv7 and MobileNetv3. Engineering, Technology & Applied Science Research. 2025;15(1):19181-7.
[15] Huang Y, Feng X, Han T, Song H, Liu Y, Bao M. GDS-YOLO: A Rice Diseases Identification Model With Enhanced Feature Extraction Capability. IET Image Processing. 2025;19(1):e70034.
[16] Vieira-e Silva AL, Chaves T, Felix H, Macêdo D, Simões F, Gama-Neto M, et al.. Unifying Public Datasets for Insulator Detection and Fault Classification in Electrical Power Lines; 2020. https://github.com/heitorcfelix/public-insulator-datasets.
[17] Zhang S, Bei Z, Ling T, Chen Q, Zhang L. Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning. Scientific Reports. 2024;14(1):25416.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Junlian Wang, Zhixiong Li, Jinquan Yang, Hongbing Ren, Wenchao Pan, Yang Feng, Lei Xiong, Chune Li, Yigong Zhang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
