Deep learning-based fatigue crack detection method for weld-free joints of circular steel tube trusses
 
 
 
More details
Hide details
1
Faculty of Art and Design, Guang Xi Vocational & Technical College, Nanning 530226, China
 
 
Submission date: 2026-03-20
 
 
Final revision date: 2026-05-25
 
 
Acceptance date: 2026-08-18
 
 
Online publication date: 2026-11-19
 
 
Publication date: 2026-11-19
 
 
Corresponding author
Xinyi Wang   

1Faculty of Art and Design, Guang Xi Vocational & Technical College, Nanning 530226, China
 
 
 
KEYWORDS
TOPICS
ABSTRACT
Abstract: To improve the detection accuracy and efficiency of fatigue cracks in weld-free joints of circular steel tube trusses, andaddress crack omission, information loss, and secondary damage issues of traditional sensor-based methods in complex joint structures, this paper proposes a method based on improved YOLO11 and SegFormer. Aiming at YOLO11’s large parameters, limited inference speed, and poor adaptability to narrow, stress-concealed cracks, the YOLO-CD model is proposed: StarNet reduces computational costs for mobile scenarios; HSANet enhances capture of crack edge details and weak features to resist corrosion/weld interference; and the OSCD head optimizes multi-scale crack detection. The improved SegFormer-HF uses FFM and HLFDB to suppress downsampling information loss, improving segmentation consistency and completeness under complex backgrounds. A "detection-localization first, segmentation-refinement later" scheme combined with skeletonization algorithm realizes automated accurate calculation of crack length and width. Experiments on the constructed dataset (cracks under different fatigue stages/stress loads) show: YOLO-CD achieves 67.8% F1, 71.5% mAP50, 46.4% mAP50-95, with GFLOPs reduced by 47.6% vs. YOLO11; SegFormer-HF reaches 91.50% F1, 90.51% mIoU, 85.15% mPA, outperforming DeepLabv3+ and UNet.
FUNDING
2023 Guangxi Vocational & Technical College Research Project《Fatigue Performance Study of Overlapped CHS (Circular Hollow Section) Truss Joints with Hidden Weld Left Unwelded》 project number:20230211119.
REFERENCES (24)
1.
Han XJ, Zhao ZC. Structural surface crack detection method based on computer vision technology. Journal of Building Structures. 2018;39(S1):418-427.
 
2.
Yuan Q, Shi Y, Li M. A review of computer vision-based crack detection methods in civil infrastructure: Progress and challenges. Remote Sensing. 2024; 16(16):2910. https://doi.org/10.3390/rs1616....
 
3.
Hussain H, Kim DK. Advancements and future prospects of buckling restrained braces for corrosive-environments: A comprehensive literature review. Buildings. 2023;13(9):2156. https://doi.org/10.3390/buildi....
 
4.
Tang Qian-long, Tan Yuan, Peng Li-min, et al. On crack identification method for tunnel linings based on digital image technology. Journal of Railway Science and Engineering. 2019,16(12):3041-3049.
 
5.
Liu YF, Fan JS, Nie JG, et al. Review and prospect of digital-image-based crack detection of structure surface. China Civil Engineering Journal. 2021;54(6): 79-98.
 
6.
Vanian V, Zamanakos G, Pratikakis I. Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms. Computers & Graphics. 2022;106:277-287. https://doi.org/10.1016/j.cag.....
 
7.
Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence. 2016;39(6):1137-1149. https://doi.org/10.1109/TPAMI.....
 
8.
Zhou Zhong, YAN Longbin, Zhang Junjie, et al. Realtime detection of tunnel cracks based on YOLOX-G algorithm. Journal of Railway Science and Engineering. 2023, 20(7): 2751-2762.
 
9.
Chen LC, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European conference on computer vision (ECCV). 2018:801-818. https://doi.org/10.1007/978-3-....
 
10.
Wang Qingyuan, XU Ying, QIAN Sheng. Study on Damage Evolution of Concrete Specimens Based on Machine Vision and Digital Image Correlation Technology. Journal of Hunan University. 2023, 50(11):169-180.
 
11.
Protopapadakis E, Voulodimos A, Doulamis A, Doulamis N, Stathaki T. Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing. Applied intelligence. 2019; 49(7):2793-2806. https://doi.org/10.1007/s10489....
 
12.
Nishiyama S, Minakata N, Kikuchi T, et al. Improved digital photogrammetry technique for crack monitoring. Advanced Engineering Informatics. 2015;29(4):851-858. https://doi.org/10.1016/j.aei.....
 
13.
Li Z, Zhang T, Miao Y, et al. Automated quantification of crack length and width in asphalt pavements]. Computer‐Aided Civil and Infrastructure Engineering. 2024;39(21):3317-3336. https://doi.org/10.1111/mice.1....
 
14.
Zhou Ying, LIU Tong. Computer Vision-Based Crack Detection and Measurement on Concrete Structure. Journal of Tongji University. 2019;47(9): 1277-1285.http://dx.doi.org/10.11908/j.i....
 
15.
Tian Y, Wang Y. Crack detection method of highway side slope based on computer vision. In 2021 International Conference on Aviation Safety and Information Technology. 2021;742-746. https://doi.org/10.1145/351085....
 
16.
Wang Weidong, WU Zheng, QIU Shi, et al. Multi-objective cascade deep learning based crack measurement for ballastless track slab. Journal of Railway Science and Engineering. 2023;20(9):3592-3603.
 
17.
Khanam R, Hussain M. Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2024;2410.17725. https://doi.org/10.48550/arXiv....
 
18.
Varghese R, Sambath M. Yolov8: A novel object detection algorithm with enhanced performance and robustness. In 2024 International conference on advances in data engineering and intelligent computing systems (ADICS). 2024:1-6. https://doi.org/10.1109/ADICS5....
 
19.
Child R, Gray S, Radford A, et al. Generating long sequences with sparse transformers. arXiv preprint arXiv:2019;1904.10509. https://doi.org/10.48550/arXiv....
 
20.
Xie E, Wang W, Yu Z, et al. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems. 2021;34:12077-12090.
 
21.
Ma X, Dai X, Bai Y, Wang Y, Fu Y. Rewrite the stars. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024:5694-5703. https://doi.org/10.1109/CVPR52....
 
22.
Tian Z, Shen C, Chen H, He T. FCOS: A simple and strong anchor-free object detector. IEEE transactions on pattern analysis and machine intelligence. 2020;44(4):1922-1933. https://doi.org/10.1109/TPAMI.....
 
23.
Zhang J, Zeng Z, Sharma PK, et al. A dual encoder crack segmentation network with Haar wavelet-based high–low frequency attention. Expert Systems with Applications. 2024;256:124950. https://doi.org/10.1016/j.eswa....
 
24.
Chen G, Dai K, Yang K, et al. Bracketing image restoration and enhancement with high-low frequency decomposition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024:6097-6107. https://doi.org/10.1109/CVPRW6....
 
eISSN:2449-5220
Journals System - logo
Scroll to top