ACC
TW-YOLO: High-precision Steel Wire Rope Detection Algorithm Based on Triplet Attention
TOTAL VIEWS: 263
Abstract
Addressing the issue of insufficient accuracy in detecting small target defects in steel wire ropes in scenarios such as construction sites and elevators, this paper proposes a steel wire rope defect detection method called TW-YOLO, based on the YOLOv8 network model. Firstly, a Triplet Attention mechanism is introduced after the SPPF module layer of the backbone network to enhance the robustness of the model and its detection accuracy for small defects. Then, the damage function of the original model is replaced with WIOU to further improve the model's detection capability for small targets. In ablation experiments, compared to the original YOLOv8, the TW-YOLO model achieved a 4.45% improvement in detection accuracy for the break category of steel wire ropes and a 3.3% increase in mAP. In comparative experiments, TW-YOLO demonstrated high accuracy and low computational complexity.
References
[1] Wang H, Zheng H, Tian J, et al. Research on quantitative identification method for wire rope wire breakage damage signals based on multi-decomposition information fusion. J Saf Sustain. 2024;1(2):89-97.
[2] Chen Y, Qin W, Wang Q, et al. Influence of corrosion pit on the tensile mechanical properties of a multi-layered wire rope strand. Constr Build Mater. 2021;302:124387.
[3] Jiang X, Sun Y, Feng B, et al. New on-line MFL testing method and apparatus for winding mine hoist wire rope. Appl Sci. 2022;12(14):6970.
[4] Tian J, Bai Q, Wang X, et al. Experimental study on characterization of mine wire rope detection signal properties based on magnetic field model. Coal Sci Technol. 2024;52(2):279-91.
[5] Rossteutscher I, Blaschke O, Dötzer F, et al. Improved EMAT sensor design for enhanced ultrasonic signal detection in steel wire ropes. Sensors. 2024;24(22):7114.
[6] Zhao S, Li G, Wang C. Bridge cable damage identification based on acoustic emission technology: a comprehensive review. Measurement. 2024:115195.
[7] Liu Q, Tang Q, Su B, et al. Wire rope damage detection based on a uniform-complementary binary pattern with exponentially weighted guide image filtering. Vis Comput. 2024:1-14.
[8] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Com-puter Vision and Pattern Recognition (CVPR'05). IEEE; 2005. p. 886-93.
[9] Liu Q, Wang C, Li Y, et al. A fabric defect detection method based on deep learning. IEEE Access. 2022;10:4284-96.
[10] Zhou C, Lu Z, Lv Z, et al. Metal surface defect detection based on improved YOLOv5. Sci Rep. 2023;13(1):20803.
[11] Hu J, Wan W, Qiao P, et al. Power insulator defect detection method based on enhanced YOLOV7 for aerial inspection. Electronics. 2025;14(3):408.
[12] Wu T, Dong Y. YOLO-SE: improved YOLOv8 for remote sensing object detection and recognition. Appl Sci. 2023;13(24):12977.
[13] Misra D, Nalamada T, Arasanipalai AU, et al. Rotate to attend: convolutional triplet attention module. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision; 2021. p. 3139-48.
[14] Tong Z, Chen Y, Xu Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism. arXiv:2301.10051. 2023.
[15] Zhou P, Zhou G, Wang H, et al. Intelligent visual detection method for the early surface damage of mine hoisting wire ropes. Meas Sci Technol. 2024;35(11):115018.
[16] Lin T, Goyal P, Girshick R, et al. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision; 2017. p. 2980-8.
[17] Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector. In: Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer International Publishing; 2016. p. 21-37.
[18] Redmon J, Farhadi A. Yolov3: an incremental improvement. arXiv:1804.02767. 2018.
[19] Li C, Li L, Jiang H, et al. YOLOv6: a single-stage object detection framework for industrial applications. arXiv:2209.02976. 2022.
[20] Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 7464-75.
[21] Khanam R, Hussain M. Yolov11: an overview of the key architectural enhancements. arXiv:2410.17725. 2024.
[22] Tian Y, Ye Q, Doermann D. Yolov12: attention-centric real-time object detectors. arXiv:2502.12524. 2025.
How to cite this paper
TW-YOLO: High-precision Steel Wire Rope Detection Algorithm Based on Triplet Attention
How to cite this paper: Hui Wang, Haixing Wang, Qunpo Liu. (2025) TW-YOLO: High-precision Steel Wire Rope Detection Algorithm Based on Triplet Attention. Advances in Computer and Communication, 6(2), 48-54.
DOI: http://dx.doi.org/10.26855/acc.2025.04.001
More Articles
- Application Analysis of Multi-beam Bathymetry Technology Based on Genetic Algorithm
- Research on Methods for Improving the Explainability of Artificial Intelligence Based on Causal Reasoning
- Research on Intelligent Decision-making Methods for Complex Scenarios Based on Multimodal Large Models
- TrAdaBoostR2-based Domain Adaptation for Generalizable Revenue Prediction in Online Advertising Across Various Data Distributions
- Artificial Intelligence Driven Personalized Medicine: The Role of Multi-modal Engineering Systems
- SEW: School Event Website Development and Validation