Abstract
Industrial welding often exhibits some essential problems, such as unclear defect characteristics and complex background information. However, the existing defect detection models have relatively high costs and may be weak in weld surface defect detection. To address the problem, this paper proposes an improved lightweight YOLOv11 model for welding surface defect detection, called YOLO-Air. First, the model integrates the feature extraction module with the convolutional module to boost feature representation capability and optimize computational efficiency. Second, the GSConv and VOV-GSCSP modules are embedded in the neck network to reduce feature redundancy of spatial and channel dimensions, and then lower the computational load. Third, a lightweight detection head is designed as part of the detection network to further reduce model complexity. Lastly, we compare our proposed YOLO-Air model with the baseline on the Welding Defect Test-V2 and NEU-DET datasets. Experimental results demonstrate that the proposed model yields superior performance for weld surface defect detection. Specifically, it improves the mAP50 metric by 1.3%, while reducing the number of parameters by 17.3% and the computational complexity by 31.7%.All key experimental data have passed robustness tests.
Similar content being viewed by others
Data availability
The datasets generated during and/or analysed during the current study are not publicly available but are available from the corresponding author on reasonable request.
References
Wang, Y., Zhang, K., Wang, L. & Wu, L. An improved yolov8 algorithm for rail surface defect detection. IEEE Access 12, 44984–44997. https://doi.org/10.1109/ACCESS.2024.3380009 (2024).
Hu, S., Jiabin, Z., Bohao, Z. & Wei, Z. Review of surface defect inspection based on visual perception. Computer Integrated Manufacturing System 29, 169–191. https://doi.org/10.13196/j.cims.2023.01.015 (2023).
Yujie, M., Chuqing, C. & Jing, Z. Steel surface defect detection based on yolov8-soe. Opto-Electronic Engineering 52, 100–112. https://doi.org/10.12086/oee.2025.250032 (2025).
Liu, W. Ssd: Single shot multibox detector. In Computer Vision - ECCV 2016 (eds Leibe, B. et al.) 21–37 (Springer International Publishing, 2016).
Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788, https://doi.org/10.1109/CVPR.2016.91 (2016).
Wang, C.-Y., Bochkovskiy, A. & Liao, H.-Y. M. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7464–7475, https://doi.org/10.1109/CVPR52729.2023.00721 (2023).
Girshick, R. Fast r-cnn. In 2015 IEEE International Conference on Computer Vision (ICCV), 1440–1448, https://doi.org/10.1109/ICCV.2015.169 (2015).
He, K., Gkioxari, G., Dollár, P. & Girshick, R. Mask r-cnn. In 2017 IEEE International Conference on Computer Vision (ICCV), 2980–2988, https://doi.org/10.1109/ICCV.2017.322 (2017).
Sun, X., Wu, P. & Hoi, S. C. Face detection using deep learning: An improved faster rcnn approach. Neurocomputing 299, 42–50. https://doi.org/10.1016/j.neucom.2018.03.030 (2018).
Dang, Z. & Wang, X. Fd-yolo11: A feature-enhanced deep learning model for steel surface defect detection. IEEE Access 13, 63981–63993. https://doi.org/10.1109/ACCESS.2025.3559733 (2025).
Liu, H., Hu, R., Dong, H. & Liu, Z. Sfc-yolov8: Enhanced strip steel surface defect detection using spatial-frequency domain-optimized yolov8. IEEE Trans. Instrum. Meas. 74, 1–11. https://doi.org/10.1109/TIM.2025.3548193 (2025).
Bakirci, M. & Demiray, A. Tracking robotic arms with yolo11 for smart automation in industry 4.0. In 2025 International Russian Smart Industry Conference (SmartIndustryCon), 64–70, https://doi.org/10.1109/SmartIndustryCon65166.2025.10985968 (2025).
Lin, T.-Y. et al. Feature pyramid networks for object detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 936–944, https://doi.org/10.1109/CVPR.2017.106 (2017).
Yang, D., Ma, C., Yu, G. & Chen, Y. Automatic defect detection of pipelines based on improved ofg-yolo algorithm. Measurement 242, 115847. https://doi.org/10.1016/j.measurement.2024.115847 (2025).
Lu, M., Sheng, W., Zou, Y., Chen, Y. & Chen, Z. Wss-yolo: An improved industrial defect detection network for steel surface defects. Measurement 236, 115060. https://doi.org/10.1016/j.measurement.2024.115060 (2024).
Zhao, C., Shu, X., Yan, X., Zuo, X. & Zhu, F. Rdd-yolo: A modified yolo for detection of steel surface defects. Measurement 214, 112776. https://doi.org/10.1016/j.measurement.2023.112776 (2023).
Xu, L. et al. Intelligent identification of girth welds defects in pipelines using neural networks with attention modules. Eng. Appl. Artif. Intell. 127, 107295. https://doi.org/10.1016/j.engappai.2023.107295 (2024).
Gao, S., Chu, M. & Zhang, L. A detection network for small defects of steel surface based on yolov7. Digit. Signal Process. 149, 104484. https://doi.org/10.1016/j.dsp.2024.104484 (2024).
Liang, Y. et al. A stable diffusion enhanced yolov5 model for metal stamped part defect detection based on improved network structure. J. Manuf. Process. 111, 21–31. https://doi.org/10.1016/j.jmapro.2023.12.064 (2024).
Wang, X., Xuan, Y., Huang, X. & Yan, Q. Yolo-afk: Advanced fine-grained object detection for complex solder joints defect. IEEE Access 12, 166238–166252. https://doi.org/10.1109/ACCESS.2024.3495540 (2024).
Guo, R. et al. Steel surface defect detection based on improved gchs-yolo algorithm. IEEE Access 12, 190865–190875. https://doi.org/10.1109/ACCESS.2024.3516932 (2024).
Li, H. et al. Slim-neck by gsconv: A lightweight-design for real-time detector architectures. J. Real-Time Image Process. 21, 62 (2024a).
Chen, Y. et al. Dynamic convolution: Attention over convolution kernels. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11027–11036, (2020), https://doi.org/10.1109/CVPR42600.2020.01104.
Wang, J., Chen, Y., Dong, Z. & Gao, M. Improved yolov5 network for real-time multi-scale traffic sign detection. Neural Comput. Appl. 35, 7853–7865 (2023).
Li, H. et al. Slim-neck by gsconv: A lightweight-design for real-time detector architectures. J. Real-Time Image Process. 21, 62 (2024b).
Chen, J. et al. Run, don’t walk: Chasing higher flops for faster neural networks. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12021–12031, (2023) https://doi.org/10.1109/CVPR52729.2023.01157
Ancha, V. K., Gonuguntla, V. & Vaddi, R. Trsbi-yolo: Transformer based lightweight and high-performance model for pcb defects detection. J. Supercomput. 81, 1–25 (2025).
Junzhe, L., Chengyi, Z., Shipeng, L. & Dejun, N. Lightweight dcn-yolo for strip surface defect detection in complex environments. Comput. Eng. Appl. 59, 318–328. https://doi.org/10.3778/j.issn.1002-8331.2303-0100 (2023).
Zhong, H. et al. Steel surface defect detection based on an improved yolov5 model. In 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), 51–55, https://doi.org/10.1109/ICMSP58539.2023.10170867 (2023).
Linrong, Z., Guoyong, Z., Chengqun, C. & Yanhu, S. Detection method of steel surface defects based on cbe-yolov5. Electron. Meas. Technol. 46, 73–80 (2023).
Guo, Z., Wang, C., Yang, G., Huang, Z. & Li, G. Msft-yolo: Improved yolov5 based on transformer for detecting defects of steel surface. Sensors https://doi.org/10.3390/s22093467 (2022).
Funding
This work was supported by the Anhui Provincial Natural Science Projects in Universities (Research on Intelligent Sensing and Adaptive Control Technology for Building Robots) (No. 2024AH050234); the Open Research Project of the Anhui Simulation Design and Modern Manufacture Engineering Technology Research Center (Huangshan University) (No. SGCZXZD2101); the Provincial and Ministerial Key Laboratory of Chang’an University (No. 300102254501-202412); Anhui Jianzhu University Scientific Research Reserve Project: Key Technology Research on the Construction of a Knowledge Graph for Huizhou-Style Architecture (No. 2022XMK03); and the Anhui University Natural Science Key Research Project (No. 2024AH050245).
Author information
Authors and Affiliations
Contributions
C.P. and R.Z. conceived the study. C.P. developed the methodology and implemented the software. C.P. validated the results. C.P.and R.Z. conducted the formal analysis and curated the data. C.P.and Z.C. carried out the investigation. C.P. provided the resources. C.P. and Z.C. prepared the original draft. J.F., Z.C., and B.Y. revised and edited the manuscript. All authors reviewed 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
Zhang, R., Pan, C., Chen, Z. et al. An improved lightweight YOLOv11 algorithm for weld surface defect detection. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41568-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41568-2
