Abstract
Bolted connections are widely adopted as primary structural joints in engineering infrastructure. However, conventional manual inspection remains labor-intensive and time-consuming. Deep learning–based automated defect detection faces significant challenges due to pronounced image variability induced by variable camera angles, lighting conditions, partial occlusions, and complex backgrounds. This study addresses these issues by constructing a diverse bolt image dataset compiled from three sources: on-site acquisitions from suspension bridges, field photography of steel transmission towers, and controlled laboratory imaging of a custom-fabricated bolt assembly model. To enhance data robustness, we employed image enhancement techniques and generative adversarial networks (GANs) for data augmentation. A comparative analysis was conducted among three mainstream object-detection models—YOLOv5, YOLOv8, and YOLOv10—using recall, precision, and mean average precision (mAP) as evaluation metrics. Building upon the superior performance of YOLOv8 (mAP = 0.91, recall = 0.85, precision = 0.9), we proposed an enhanced architecture integrating a Swin-Transformer backbone and a novel Multi-Scale and Detail-Enhanced Module (MEDM) to specifically improve missing-bolt detection in challenging visual contexts. The improved model demonstrated consistent accuracy across diverse scenarios: 100% at 15°, 30°, and 45° viewing angles; > 94% under 30%, 50%, and 100% illumination levels; and > 97.2% for colored coatings (blue, red, white) against complex grassy and mixed backgrounds. In practical engineering deployment, the model achieved a 98.94% detection rate across 12,772 bolt sets, successfully identifying one instances of missing bolts. These findings validate the proposed approach’s effectiveness for real-world structural health monitoring.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Wang, T., Song, G., Liu, S., Li, Y. & Xiao, H. Review of bolted connection monitoring. Int. J. Distrib. Sens. Netw. 9, 871213. https://doi.org/10.1155/2013/871213 (2013).
Xinhua News Agency, The world’s longest-spanning railway arch bridge has been successfully closed. Accessed 05 Oct 2025 (2018).https://www.yidaiyilu.gov.cn/p/74297.html
Suda, M. et al. Development of ultrasonic axial bolting force inspection system for turbine bolts in thermal power plants. Jsme Int. J. ser. Solid Mech. Strength. Mater. 35, 216–219. https://doi.org/10.1299/jsmea1988.35.2_216 (1988).
Yang, J. & Chang, F. K. Detection of bolt loosening in C-C composite thermal protection panels: II. Experimental verification. Smart Mater. Struct. 15, 591–599 (2006). http://stacks.iop.org/SMS/15/591
Okugawa, M. Bolt loosening detection method by using smart washer adopted 4SID. Japan Soc. Mech. Eng. https://doi.org/10.2514/6.2004-1981 (2003).
Cha, Y. J., You, K. & Choi, W. Vision-based detection of loosened bolts using the Hough transform and support vector machines. Autom. Constr. 71, 181–188. https://doi.org/10.1016/j.autcon.2016.06.008 (2016).
Wang, B. L. & Yu, L. Loose fault detection for fastening bolts of medium and low speed maglev F_rail. Information Technology. 43, 88–92 + 97. 10. 13274/j. cnki. hdzj. 08. 021 (2019). (2019).
Zhao, X. X., Qian, S. S. & Liu, X. G. Image identification method for high-strength bolt missing on railway bridge based on convolution neural network. China Railway Sci. 39, 56–62. https://doi.org/10.3969/j.issn.1001-4632.2018.04.09 (2018).
Zhou, J. & Huo, L. Computer vision-based detection for delayed fracture of bolts in steel bridges. J. Sens. https://doi.org/10.1155/2021/8325398 (2021).
Li, X. X., Li, D., Ren, W. X. & Zhang, J. S. Loosening Identification of multi-bolt connections based on wavelet transform and ResNet-50 convolutional neural network. Sensors 22, 6825. https://doi.org/10.3390/s22186825 (2022).
Yang, Z., Zhao, Y. & Xu, C. Detection of missing bolts for engineering structures in natural environment using machine vision and deep learning. Sensors 23, 5655. https://doi.org/10.3390/s23125655 (2023).
Ni, Y., Mao, J. & Wang, Y. X. Z. Corroded and loosened bolt detection of steel bolted joints based on imp-roved you only look once network and line segment detector. Smart structures and systems 32, 23–35. https://doi.org/10.12989/sss.2023.32.1.023 (2023).
Chen, X. R., Zhou, Y., Zhao, Y. T. & Yan, X. F. An improved YOLOv5-based bolt missing detection method for mobile terminals. Mod. Manuf. Eng. 11, 108–114. https://doi.org/10.16731/j.cnki.1671-3133.2022.11.018 (2022).
Pan, X., Tavasoli, S. & Yang, T. Y. Autonomous 3D vision-based bolt loosening assessment using micro aerial vehicles. Computer-Aided Civil and Infrastructure Engineering 38, 2443–2454. https://doi.org/10.1111/mice.13023 (2023).
Lao, W., Cui, C., Zhang, D., Zhang, Q. & Bao, Y. Computer vision-based autonomous method for quantitative detection of loose bolts in bolted connections of steel structures. Struct. Control Health Monit. https://doi.org/10.1155/2023/8817058 (2023).
Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. Proc. IEEE/CVF Int. Conf. Comput. Vis. https://doi.org/10.48550/arXiv.2103.14030 (2021).
Aggarwal, A., Mittal, M. & Battineni, G. Generative adversarial network: An overview of theory and applications. Int. J. Inform. Manage. Data Insights. https://doi.org/10.1016/j.jjimei.2020.100004 (2021).
Liao, C. et al. Benchmarking multi-modal semantic segmentation under sensor failures: Missing and noisy m-odality robustness. Proc. Comput. Vis. Pattern Recognit. Conf. https://doi.org/10.48550/arXiv.2503.18445 (2025).
Vasiljevic, I., Chakrabarti, A. & Shakhnarovich, G. Examining the impact of blur on recognition by convolutional networks. (2016). https://doi.org/10.48550/arXiv.1611.05760
Wang, W., Chen, Z., Yuan, X. & Wu, X. Adaptive image enhancement method for correcting low-illumination images. Inf. Sci. 496, 25–41. https://doi.org/10.1016/j.ins.2019.05.015 (2019).
Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recongnition. (2016). https://doi.org/10.48550/arXiv.1506.02640
Sun, Y., Li, M., Dong, R., Chen, W. & Jiang, D. Vision-based detection of bolt loosening using YOLOv5. Sensors 22, 5184. https://doi.org/10.3390/s22145184 (2022).
Yu, F. et al. Imaging-based instance segmentation of pavement cracks using an improved YOLOv8 network. Struct. Control Health Monit. 1660649. https://doi.org/10.1155/stc/1660649 (2025).
Lei, W. et al. Vision-based real-time bolt loosening detection by identifying anti-loosening lines. Sensors 24, 6747. https://doi.org/10.3390/s24206747 (2024).
Sajjadi, M. S. M. et al. Assessing generative models via precision and recall. Advances in neural information processing systems. (2018). https://doi.org/10.48550/arXiv.1806.00035
Wang, B. A parallel implementation of computing mean average precision. ArXiv https://doi.org/10.48550/arXiv.2206.09504 (2022).
Yu, J., Jiang, Y., Wang, Z., Cao, Z. & Huang, T. Unitbox: An advanced object detection network. Proc. 24th ACM Int. Conf. Multimedia. https://doi.org/10.1145/2964284.2967274 (2016).
Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF international conference on computer vision. 10012–10022. (2021). https://doi.org/10.48550/arXiv.2103.14030
Du, W. F. Anti-corrosion coating treatment measures for highway and bridge guardrail. Total Corrosion Control 37, 121–124. https://doi.org/10.13726/j.cnki.11-2706/tq.2023.05.121.04 (2023).
Li, Q. S. Design for Nezha suspension bridge in Jiangyou city of Sichuan province. Transport Research 09, 47–50. https://doi.org/10.3869/j.issn.1002-4786.2011.09.016 (2011).
Funding
Project Supported by Sichuan Science and Technology Program, under grant No. (2025ZYDF080).
Author information
Authors and Affiliations
Contributions
Ying Gu (Y.G.): Conceptualization, methodology, investigation, supervision, project administration. Jingyu Song (J.Y.S): Data curation, data augmentation, formal analysis. Dongmei Peng (D.M.P): Model development, comparative experiments, validation. Chao Kong (C.K.) & Songbo Ren (S.B.R): Funding acquisition, visualization, writing–review & editing. All authors have reviewed and approved the final version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Gu, Y., Peng, D., Song, J. et al. Image-based detection of bolts and bolt-missing defects in multi-angle and complex background scenarios. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41036-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41036-x
