Insulator Defect Detection Based On Image Processing Using A Modified YOLOv8n Model

Muchamad Arfim  Muzaki; Subiyanto Subiyanto; Andika  Anantyo

doi:10.52436/1.jutif.2026.7.1.4679

Authors

Muchamad Arfim Muzaki Department of Electrical Engineering, Faculty of Engineering, Universitas Negeri Semarang, Indonesia
Subiyanto Department of Electrical Engineering, Faculty of Engineering, Universitas Negeri Semarang, Indonesia
Andika Anantyo Department of Electrical Engineering, Faculty of Engineering, Universitas Negeri Semarang, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.1.4679

Keywords:

Insulator Defect Detection, YOLOv8, Slim-Neck, Efficient Multi-Scale Attention (EMA)

Abstract

Insulators are critical components in power transmission and distribution systems, where any defects can lead to severe operational failures and power outages. To enhance inspection efficiency, unmanned aerial vehicles (UAVs) are increasingly used for aerial monitoring. However, the quality of images captured by drones is often compromised due to hardware limitations, motion blur, and complex environmental backgrounds, which significantly reduces the performance of deep learning-based defect detection methods. This study proposes an improved insulator defect detection model based on the YOLOv8n architecture, optimized for accuracy and efficiency in low-quality image scenarios and suitable for deployment in resource-constrained environments. The model introduces two major modifications. First, a Slim-Neck module employing Ghost-Shuffle Convolution (GSConv) replaces standard convolutions to substantially reduce computational cost while preserving rich feature representations. Second, an Efficient Multi-Scale Attention (EMA) module is integrated into the neck to enhance multi-scale feature fusion by maintaining per-channel information without dimensionality reduction, improving the model’s ability to extract discriminative features. Experimental results demonstrate that the proposed model achieves a precision of 92.0%, recall of 88.6%, mAP@0.5 of 92.1%, and an inference speed of 161.29 FPS. Furthermore, it reduces parameter count by 10.8% and computational load by 8.6% compared to the baseline, validating its suitability for real-time UAV-based inspections. The model also outperforms existing methods in detecting insulator defects, particularly in challenging conditions involving blur and complex backgrounds.

Downloads

Download data is not yet available.

References

A. Odo, S. McKenna, D. Flynn, and J. B. Vorstius, “Aerial Image Analysis Using Deep Learning for Electrical Overhead Line Network Asset Management,” IEEE Access, vol. 9, pp. 146281–146295, 2021, doi: 10.1109/ACCESS.2021.3123158.

H. Liang, C. Zuo, and W. Wei, “Detection and Evaluation Method of Transmission Line Defects Based on Deep Learning,” IEEE Access, vol. 8, pp. 38448–38458, 2020, doi: 10.1109/ACCESS.2020.2974798.

Z. Lu, Y. Li, F. Shuang, and C. Han, “InsDef: Few-Shot Learning-Based Insulator Defect Detection Algorithm With a Dual-Guide Attention Mechanism and Multiple Label Consistency Constraints,” IEEE Trans. Power Deliv., vol. 38, no. 6, pp. 4166–4178, Dec. 2023, doi: 10.1109/TPWRD.2023.3311643.

W. Rodgers, J. A. Cardenas, L. A. Gemoets, and R. J. Sarfi, “A smart grids knowledge transfer paradigm supported by experts’ throughput modeling artificial intelligence algorithmic processes,” Technol. Forecast. Soc. Change, vol. 190, p. 122373, May 2023, doi: 10.1016/j.techfore.2023.122373.

Y. Cao, H. Xu, C. Su, and Q. Yang, “Accurate Glass Insulators Defect Detection in Power Transmission Grids Using Aerial Image Augmentation,” IEEE Trans. Power Deliv., vol. 38, no. 2, pp. 956–965, Apr. 2023, doi: 10.1109/TPWRD.2022.3202958.

F. Alcayde-García, E. Salmerón-Manzano, M. A. Montero, A. Alcayde, and F. Manzano-Agugliaro, “Power Transmission Lines: Worldwide Research Trends,” Energies, vol. 15, no. 16, p. 5777, Aug. 2022, doi: 10.3390/en15165777.

L. Zhang, B. Li, Y. Cui, Y. Lai, and J. Gao, “Research on improved YOLOv8 algorithm for insulator defect detection,” J. Real-Time Image Process., vol. 21, no. 1, pp. 1–14, 2024, doi: 10.1007/s11554-023-01401-9.

X. Liu, X. Miao, H. Jiang, and J. Chen, “Data analysis in visual power line inspection: An in-depth review of deep learning for component detection and fault diagnosis,” Annu. Rev. Control, vol. 50, pp. 253–277, 2020, doi: 10.1016/j.arcontrol.2020.09.002.

A. El-Hag, “Application of Machine Learning in Outdoor Insulators Condition Monitoring and Diagnostics,” IEEE Instrum. Meas. Mag., vol. 24, no. 2, pp. 101–108, Apr. 2021, doi: 10.1109/MIM.2021.9400959.

B. Chen, “Fault Statistics and Analysis of 220-kV and Above Transmission Lines in a Southern Coastal Provincial Power Grid of China,” IEEE Open Access J. Power Energy, vol. 7, pp. 122–129, 2020, doi: 10.1109/OAJPE.2020.2975665.

Z. Wang, Q. Gao, J. Xu, and D. Li, “A Review of UAV Power Line Inspection,” 2022, pp. 3147–3159. doi: 10.1007/978-981-15-8155-7_263.

J. Hu, W. Wan, P. Qiao, Y. Zhou, and A. Ouyang, “Power Insulator Defect Detection Method Based on Enhanced YOLOV7 for Aerial Inspection,” Electronics, vol. 14, no. 3, p. 408, Jan. 2025, doi: 10.3390/electronics14030408.

F. FJ, L. Meganathan, M. Esha, N. G. Minh Thao, and A. S. Arockia Doss, “Power Transmission Line Inspection Using Unmanned Aerial Vehicle - A Review,” in 2023 Innovations in Power and Advanced Computing Technologies (i-PACT), IEEE, Dec. 2023, pp. 1–5. doi: 10.1109/i-PACT58649.2023.10434671.

J. Ding et al., “Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 11, pp. 7778–7796, Nov. 2022, doi: 10.1109/TPAMI.2021.3117983.

J. Liu, C. Liu, Y. Wu, H. Xu, and Z. Sun, “An Improved Method Based on Deep Learning for Insulator Fault Detection in Diverse Aerial Images,” Energies, vol. 14, no. 14, p. 4365, Jul. 2021, doi: 10.3390/en14144365.

Y. Liu, D. Liu, X. Huang, and C. Li, “Insulator defect detection with deep learning: A survey,” IET Gener. Transm. Distrib., vol. 17, no. 16, pp. 3541–3558, Aug. 2023, doi: 10.1049/gtd2.12916.

Y. Gong et al., “Defect detection of small cotter pins in electric power transmission system from UAV images using deep learning techniques,” Electr. Eng., vol. 105, no. 2, pp. 1251–1266, Apr. 2023, doi: 10.1007/s00202-022-01729-8.

J. Liu, M. Hu, J. Dong, and X. Lu, “Summary of insulator defect detection based on deep learning,” Electr. Power Syst. Res., vol. 224, p. 109688, Nov. 2023, doi: 10.1016/j.epsr.2023.109688.

X. Lu, Q. Li, B. Li, and J. Yan, “MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12359 LNCS, pp. 541–557, 2020, doi: 10.1007/978-3-030-58568-6_32.

H. Zhang and R. S. Cloutier, “Review on One-Stage Object Detection Based on Deep Learning,” EAI Endorsed Trans. e-Learning, vol. 7, no. 23, p. 174181, Jun. 2022, doi: 10.4108/eai.9-6-2022.174181.

B. Li, M. Xu, Z. Xie, D. Qi, and Y. Yan, “Research on Insulator Defect Detection Based on Improved YOLOv7,” Lect. Notes Electr. Eng., vol. 1169 LNEE, pp. 173–180, 2024, doi: 10.1007/978-981-97-1072-0_17.

N. Zhang, J. Su, Y. Zhao, and H. Chen, “Insulator-YOLO: Transmission Line Insulator Risk Identification Based on Improved YOLOv5,” Processes, vol. 12, no. 11, p. 2552, Nov. 2024, doi: 10.3390/pr12112552.

L. Ding, Z. Q. Rao, B. Ding, and S. J. Li, “Research on Defect Detection Method of Railway Transmission Line Insulators Based on GC-YOLO,” IEEE Access, vol. 11, pp. 102635–102642, 2023, doi: 10.1109/ACCESS.2023.3316266.

Y. Zhang, J. Li, W. Fu, J. Ma, and G. Wang, “A lightweight YOLOv7 insulator defect detection algorithm based on DSC-SE,” PLoS One, vol. 18, no. 12, p. e0289162, Dec. 2023, doi: 10.1371/journal.pone.0289162.

J. Su, Y. Yuan, K. Przystupa, and O. Kochan, “Insulator defect detection algorithm based on improved YOLOv8 for electric power,” Signal, Image Video Process., vol. 18, no. 8–9, pp. 6197–6209, 2024, doi: 10.1007/s11760-024-03307-w.

S. Luan, C. Li, P. Xu, Y. Huang, and X. Wang, “MI-YOLO: more information based YOLO for insulator defect detection,” J. Electron. Imaging, vol. 32, no. 04, Jul. 2023, doi: 10.1117/1.JEI.32.4.043014.

D. Wei, B. Hu, C. Shan, and H. Liu, “Insulator defect detection based on improved Yolov5s,” Front. Earth Sci., vol. 11, Feb. 2024, doi: 10.3389/feart.2023.1337982.

Z. Li, C. Jiang, and Z. Li, “An Insulator Location and Defect Detection Method Based on Improved YOLOv8,” IEEE Access, vol. 12, pp. 106781–106792, 2024, doi: 10.1109/ACCESS.2024.3436919.

W. Han, Z. Cai, X. Li, A. Ding, Y. Zou, and T. Wang, “LMD-YOLO: A lightweight algorithm for multi-defect detection of power distribution network insulators based on an improved YOLOv8,” PLoS One, vol. 20, no. 2, p. e0314225, Feb. 2025, doi: 10.1371/journal.pone.0314225.

Z. Mei, H. Xu, L. Yan, and K. Wang, “IALF-YOLO: Insulator defect detection method combining improved attention mechanism and lightweight feature fusion network,” Measurement, vol. 253, p. 117701, Sep. 2025, doi: 10.1016/j.measurement.2025.117701.

Z. Xu and X. Tang, “Transmission line insulator defect detection algorithm based on MAP-YOLOv8,” Sci. Rep., vol. 15, no. 1, p. 10288, Mar. 2025, doi: 10.1038/s41598-025-92445-3.

D. Ouyang et al., “Efficient Multi-Scale Attention Module with Cross-Spatial Learning,” in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Jun. 2023, pp. 1–5. doi: 10.1109/ICASSP49357.2023.10096516.

H. Li, J. Li, H. Wei, Z. Liu, Z. Zhan, and Q. Ren, “Slim-neck by GSConv: a lightweight-design for real-time detector architectures,” J. Real-Time Image Process., vol. 21, no. 3, pp. 1–11, 2024, doi: 10.1007/s11554-024-01436-6.

P. K. Dexter Lewis, “Insulator Defect Detection,” IEEE Dataport, 2021, doi: https://dx.doi.org/10.21227/vkdw-x769.

Y. Chen, H. Liu, J. Chen, J. Hu, and E. Zheng, “Insu-YOLO: An Insulator Defect Detection Algorithm Based on Multiscale Feature Fusion,” Electronics, vol. 12, no. 15, p. 3210, Jul. 2023, doi: 10.3390/electronics12153210.

Z. Mei, H. Xu, L. Yan, and K. Wang, “IALF-YOLO: Insulator defect detection method combining improved attention mechanism and lightweight feature fusion network,” Meas. J. Int. Meas. Confed., vol. 253, no. PC, p. 117701, 2025, doi: 10.1016/j.measurement.2025.117701.