Defect Detection Technology of Tension Clamps Based on UAV
DOI:
https://doi.org/10.71222/np3bbw75Keywords:
UAV inspection, tension clamp, defect detection, deep learning, infrared thermal imaging, transmission line maintenanceAbstract
The tension clamp, a critical component of transmission lines, can lead to major safety incidents if its defects are not addressed. Traditional manual inspections are inefficient and risky. This paper introduces an intelligent inspection technology for tension clamps using drones, which employs a quad-copter equipped with high-definition visible light and infrared dual-sensor systems. By integrating autonomous flight path planning, this system can collect data from multiple angles at close range. For typical defects such as cracks, rust, and overheating, a two-stage recognition model has been developed, combining YOLOv5 object detection with an improved ResNet34 classification algorithm, and incorporating attention mechanisms to enhance the extraction of features from small targets. Experiments show that on a test set of 2,368 annotated images, the system achieves a positioning accuracy of 96.2%, an average defect recognition accuracy of 92.7%, and reduces the detection time for a single base tower to 8 minutes. This technology significantly enhances inspection efficiency and safety, offering a new solution for the intelligent operation and maintenance of transmission lines.
References
1. F. Abdollahi-Mamoudan, C. Ibarra-Castanedo and X. P. V. Maldague, "Non-Destructive Testing and Evaluation of Hybrid and Advanced Structures: A Comprehensive Review of Methods, Applications, and Emerging Trends," Sensors, vol. 25, no. 12, p. 3635, 2025, doi: 10.3390/s25123635.
2. Y. Li et al., "Multifunctional double network hydrogel with multi-directional actuation and high-precision sensing," Sens. Actuators B Chem., vol. 422, p. 136669, 2025, doi: 10.1016/j.snb.2024.136669.
3. H. Ni, J. Chu, S. Huang, J. Zhou, Y. Wang and W. Zhu, "Selecting a Suitable Portable X-ray Equipment Based on the Non-destructive Testing of Crimped Power Fittings on Transmission Lines," 2023 IEEE 3rd Int. Conf. Power, Electron. Comput. Appl. (ICPECA), Shenyang, China, 2023, pp. 781-784, doi: 10.1109/ICPECA56706.2023.10075870.
4. C. Xu, M. Xin, Y. Wang and J. Gao, "Transmission line defect identification based on improved RetinaNet algorithm," 2023 4th Int. Conf. Mechatronics Technol. Intell. Manuf. (ICMTIM), Nanjing, China, 2023, pp. 591-598, doi: 10.1109/ICMTIM58873.2023.10246551.
5. Q. Zhang et al., "Improved YOLOv8-CR Network for Detecting Defects of the Automotive MEMS Pressure Sensors," IEEE Sens. J., vol. 24, no. 16, pp. 26935-26945, Aug. 15, 2024, doi: 10.1109/JSEN.2024.3419806.
6. Z. Qiu, J. Li, X. Zhu and Z. Zhou, "Detection of Crimping Defects in X-DR Images of Strain Clamps Based on Multi Attention Mechanism Fusion Network," IEEE Trans. Power Del., vol. 39, no. 4, pp. 2125-2137, Aug. 2024, doi: 10.1109/TPWRD.2024.3388022.
7. J. C. Jianye, Y. Gu, J. Liang, W. Qin, K. Zhu and T. Liu, "Research on X-ray Live Inspection Method for Tensile Clamps of Transmission Lines," 2022 7th Asia Conf. Power Electr. Eng. (ACPEE), Hangzhou, China, 2022, pp. 1441-1445, doi: 10.1109/ACPEE53904.2022.9784061.
8. Y. M. Nsaif, M. S. H. Lipu, A. Ayob, Y. Yusof and A. Hussain, "Fault Detection and Protection Schemes for Distributed Generation Integrated to Distribution Network: Challenges and Suggestions," IEEE Access, vol. 9, pp. 142693-142717, 2021, doi: 10.1109/ACCESS.2021.3121087.
9. J. Dadashizadeh Samakosh and F. Enayati, "Operation Recommendations for Tension Joints and Clamps on a 63 kV Over-head Transmission Line Conductor Based on Experimental Tests," Electr. Power Compon. Syst., vol. 51, no. 7, pp. 639–655, 2023, doi: 10.1080/15325008.2023.2180814.
10. Z. Wang, Y. Wang and B. Zhang, "Development and Experiment of Clamp Type Submarine Cable Inspection Robot," Ma-chines, vol. 11, no. 6, p. 627, 2023, doi: 10.3390/machines11060627.
11. X. Wang, F. He and X. Huang, "A new method for deep learning detection of defects in X-ray images of pressure vessel welds," Sci. Rep., vol. 14, p. 6312, 2024, doi: 10.1038/s41598-024-56794-9.
12. I. Maduako, C. F. Igwe, J. E. Abah et al., "Deep learning for component fault detection in electricity transmission lines," J. Big Data, vol. 9, p. 81, 2022, doi: 10.1186/s40537-022-00630-2.
13. Z. Liu et al., "Key target and defect detection of high-voltage power transmission lines with deep learning," Int. J. Electr. Power Energy Syst., vol. 142, p. 108277, 2022, doi: 10.1016/j.ijepes.2022.108277.
14. R. Liu et al., "Anomaly-GAN: A data augmentation method for train surface anomaly detection," Expert Syst. Appl., vol. 228, p. 120284, 2023, doi: 10.1016/j.eswa.2023.120284.
15. J. Li, L. Xu, W. Yin et al., "Defect Detection for Drill Pipe Thread Based on Eddy Current Testing," Sens. Imaging, vol. 25, p. 71, 2024, doi: 10.1007/s11220-024-00522-0.
16. D. Huang, Y. Shu, J. Ruan and Y. Hu, "Ultra High Voltage Transmission in China: Developments, Current Status and Future Prospects," Proc. IEEE, vol. 97, no. 3, pp. 555-583, Mar. 2009, doi: 10.1109/JPROC.2009.2013613.
17. Z. Zhang, F. Tang, Q. Cao, H. Pan, X. Wang and Z. Lin, "Deep Learning-Enriched Stress Level Identification of Pretensioned Rods via Guided Wave Approaches," Buildings, vol. 12, no. 11, p. 1772, 2022, doi: 10.3390/buildings12111772.
18. Y. Xie, S. Wang, C. Zhang, K. Ouyang and X. Jiang, "Study on Nondestructive Testing Methods for Crimping Quality of Steel Cored Aluminum Strand," 2018 10th Int. Conf. Meas. Technol. Mechatronics Autom. (ICMTMA), Changsha, China, 2018, pp. 78-80, doi: 10.1109/ICMTMA.2018.00026.
19. H. Shi, M. Ebrahimi, P. Zhou, K. Shao and J. Li, "Ultrasonic and phased-array inspection in titanium-based alloys: A review," Proc. Inst. Mech. Eng. E J. Process Mech. Eng., vol. 237, no. 2, pp. 511-530, 2022, doi: 10.1177/09544089221114253.
20. K. O. Papailiou, Overhead Lines, in Springer Handbook of Power Systems, K. O. Papailiou, Ed. Singapore: Springer, 2021. ISBN: 9789813299382.
