适用于工业部署的钢丝绳表面缺陷检测模型*

doi:10.16731/j.cnki.1671-3133.2025.11.015

现代制造工程 ›› 2025, Vol. 542 ›› Issue (11): 108-115.doi: 10.16731/j.cnki.1671-3133.2025.11.015

• 仪器仪表/检测/监控 • 上一篇下一篇

适用于工业部署的钢丝绳表面缺陷检测模型^*

黄毅¹, 舒勤¹, 邓康轶¹, 邓磊¹, 付玲², 张金来¹

1 长沙理工大学机械与运载工程学院,长沙 410114;
2 起重机械关键技术全国重点实验室,长沙 410013

收稿日期:2025-03-17 出版日期:2025-11-18 发布日期:2025-11-27
作者简介:黄毅,博士,教授,主要研究方向为工程机械智能化。舒勤,硕士研究生,主要研究方向为工程机械智能化、目标检测。邓康轶,硕士研究生,主要研究方向为工程振动。邓磊,硕士研究生,主要研究方向为高空作业车轨迹规划与避障。付玲,博士,主要研究方向为工程机械智能化。张金来,博士,讲师,主要研究方向为人工智能、自动驾驶。E-mail:2031688710@qq.com;jinlai.zhang@csust.edu.cn
基金资助:
^*国家自然科学基金项目(51875048);国家重点研发计划项目(2024YFB341110402);湖南省研究生科研创新项目资助项目(QL20230208)

Wire rope surface damage detection model for industrial deployment

HUANG Yi¹, SHU Qin¹, DENG Kangyi¹, DENG Lei¹, FU Ling², ZHANG Jinlai¹

1 College of Automotive and Mechanical Engineering, Changsha University of Science and Technology, Changsha 410114, China;
2 State Key Laboratory of Construction Machinery, Changsha 410013, China

Received:2025-03-17 Online:2025-11-18 Published:2025-11-27

摘要/Abstract

摘要： 建筑施工、港口运输和高层电梯等领域对钢丝绳表面质量有着强制性规定,因此检测模型在上述领域飞速发展,但现有检测模型存在参数量大、实时性差及部署困难等问题。为缓解上述问题,提出一种轻量化的起重机钢丝绳表面缺陷检测模型LMSM-YOLO(Lightweight Multi-Scale Matching-YOLO)。首先,设计轻量化自适应特征提取(Lightweight Adaptive Feature Extraction,LAFE)模块降低模型参数量,动态调整各位置权重,使模型更关注缺陷区域的特征;其次,使用快速多维度特征匹配(Fast Multi-Scale Feature Matching,FMSFM)模块促进高级语义信息和低级视觉特征融合,提高模型检测精度。实验表明,在私有数据集上与其他先进检测模型相比,LMSM-YOLO模型参数量、浮点计算量分别降低81.9 %、76.1 %,精确率达到94.7 %,兼顾实时性和高精度要求,更适合于工业环境的部署与应用。

关键词: YOLO, 起重机钢丝绳, 缺陷检测, 轻量化, 特征融合

Abstract: Construction,port transportation,high-rise elevator and other fields have mandatory regulations on the surface quality of wire rope,so the detection model has developed rapidly in the above fields,but the existing detection model has problems such as large number of parameters,poor real-time,difficult deployment and so on. To address the aforementioned issues,a lightweight crane wire rope surface defect detection model Lightweight Multi-Scale Matching-YOLO (LMSM-YOLO) was proposed. Firstly,the Lightweight Adaptive Feature Extraction (LAFE) module was designed to reduce the number of model parameters and dynamically adjust the weight of each position,so that the model pays more attention to the features of the defect area. Secondly,the Fast Multi-Scale Feature Matching (FMSFM) module was used to promote high-level semantic information and low-level visual features, thereby improving the detection accuracy of the model. Experiment results showed that compared with other advanced detection models on private data sets, LMSM-YOLO model reduced the number of parameters and floating point computation by 81.9 % and 76.1 % respectively,and the accuracy rate reaches 94.7 %. It takes into account the requirements of real-time and high precision,and is more suitable for deployment and application in industrial environment.

Key words: YOLO, crane wire rope, defect detection, lightweight, feature fusion

中图分类号:

TP391.41

黄毅, 舒勤, 邓康轶, 邓磊, 付玲, 张金来. 适用于工业部署的钢丝绳表面缺陷检测模型^*[J]. 现代制造工程, 2025, 542(11): 108-115.

HUANG Yi, SHU Qin, DENG Kangyi, DENG Lei, FU Ling, ZHANG Jinlai. Wire rope surface damage detection model for industrial deployment[J]. Modern Manufacturing Engineering, 2025, 542(11): 108-115.

参考文献

[1] NI Y,ZHANG Q,XIN R.Magnetic flux detection and identification of bridge cable metal area loss damage[J].Measurement,2021,167:108443.
[2] ZHANG C,BI J,LV Y,et al.Numerical analysis and experimental research on detection of welding defects in pipelines based on magnetic flux leakage[J].Petroleum Research,2023,8(4):550-560.
[3] EFTEKHARI H,TEHRANCHI M M.Miniaturized magneto-optical imaging sensor for crack and micro-crack detection[J].Optik,2020,207:163830.
[4] TOGO R,WATANABE H,OGAWA T,et al.Deep convolutional neural network-based anomaly detection for organ classification in gastric X-ray examination[J].Computers in Biology and Medicine,2020,123:103903.
[5] XU Y,WU Z,ZHANG H,et al.Detection of prohibited and restricted object X-ray images based on Hi color space segmentation[J].Journal of X-Ray Science and Technology,2023,31(5):1093-1114.
[6] BENSAID N,BENLMNOUAR M F,BADJI R,et al.Microstructural and mechanical characterization of HSLA X70 welded joints using Eddy Current Testing (ECT)[C]//IOP Conference Series:Materials Science and Engineering.[S.l.]:IOP Publishing,2022,1233(1):012012.
[7] KYRKOU C.YOLOpeds:efficient real-time single-shot pedestrian detection for smart camera applications[J].IET Computer Vision,2020,14(7):417-425.
[8] CHIAN E,FANG W,GOH Y M,et al.Computer vision approaches for detecting missing barricades[J].Automation in Construction,2021,131:103862.
[9] AYMAN H,FAKHR M W.Recent computer vision applications for pavement distress and condition assessment[J].Automation in Construction,2023,146:104664.
[10] ZHOU P,ZHOU G,WANG S,et al.Visual sensing inspection for the surface damage of steel wire ropes with object detection method[J].IEEE Sensors Journal,2022,22(23):22985-22993.
[11] HOWARD A G,ZHU M,CHEN B,et al.Mobilenets:efficient convolutional neural networks for mobile vision applications[J].arXiv preprint arXiv:1704.04861,2017.
[12] REDMON J,FARHADI A.Yolov3:an incremental improvement[J].arXiv preprint arXiv:1804.02767,2018.
[13] YING Z,LIN Z,WU Z,et al.A modified-YOLOv5s model for detection of wire braided hose defects[J].Measurement,2022,190:110683.
[14] WANG Q,WU B,ZHU P,et al.ECA-Net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.[S.l.]:IEEE,2020:11534-11542.
[15] PAN F,HUANG Y,REN L,et al.Inspection of wire ropes based on magnetic flux leakage images by using YOLOv5[C]//2023 Global Reliability and Prognostics and Health Management Conference (PHM-Hangzhou).[S.l.]:IEEE,2023:1-7.
[16] CHEN S,SHI E,BAO Z.Research on improving method of RCT-YOLOv5s network for surface defect extraction of steel wire rope[C]//2023 International Conference on Computer Science and Automation Technology (CSAT).[S.l.]:IEEE,2023:529-534.
[17] MEDARAMATLA S C,SAMHITHA C V,REDDY S.Detection of damages in wire ropes using computer vision techniques[C]//2024 Third International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE).[S.l.]:IEEE,2024:1-7.
[18] YANG C,SUN X,LIU G.Obstacle Identification Based on Deep Learning for Inspection Robot of FAST Wire Rope[C]//2023 2nd International Conference on Automation,Robotics and Computer Engineering (ICARCE).[S.l.]:IEEE,2023:1-5.
[19] GUAN X,GUAN Z,ZHU S,et al.Research on the application of YOLOv8 model based on ODConv and SAHI optimization in dense small target crowd detection[C]//2024 IEEE 2nd International Conference on Control,Electronics and Computer Technology (ICCECT).[S.l.]:IEEE,2024:726-732.
[20] ZHANG X,LIU C,YANG D,et al.RFAConv:Innovating spatial attention and standard convolutional operation[J].arXiv preprint arXiv:2304.03198,2023.
[21] CHEN J,KAO S,HE H,et al.Run,don’t walk:chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.[S.l.]:IEEE,2023:12021-12031.
[22] TAO X,ZHANG D,WANG Z,et al.Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J].IEEE transactions on systems,man,and cybernetics:systems,2018,50(4):1486-1498.
[23] 汤文虎,吴龙,黎尧,等.基于改进Faster RCNN的钢线圈头部小目标检测算法[J].现代制造工程,2023(8):127-133.
[24] 阎馨,杨月川,屠乃威.基于改进SSD的钢材表面缺陷检测[J].现代制造工程,2023(5):112-120.
[25] VARGHESE R,SAMBATH M.Yolov8:a novel object detection algorithm with enhanced performance and robustness[C]//2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems(ADICS).[S.l.]:IEEE,2024:1-6.
[26] WANG C Y,YEH I H,LIAO H Y M. Yolov9:Learning what you want to learn using programmable gradient information[C]//European Conference on Computer Vision.Cham:Springer Nature Switzerland,2024:1-21.
[27] WANG A,CHEN H,LIU L,et al.Yolov10:real-time end-to-end object detection[J].Advances in Neural Information Processing Systems,2024,37:107984-108011.
[28] SELVARAJU R R,COGSWELL M,DAS A,et al.Grad-cam:visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE International Conference on Computer Vision.[S.l.]:IEEE,2017:618-626.

适用于工业部署的钢丝绳表面缺陷检测模型^*

Wire rope surface damage detection model for industrial deployment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	高建平, 苟杨扬, 李浩天, 李哲, 谢成伟, 刘宁波. 基于改进YOLOv8n的车辆视线遮挡检测模型[J]. 现代制造工程, 2025, 540(9): 131-138.
[2]	徐立友, 何飞飞, 张帅, 王运玲, 王鹏飞. 白车身碳纤维复合材料前地板铺层设计优化研究^*[J]. 现代制造工程, 2025, 537(6): 92-101.
[3]	魏书豪, 徐红伟, 柯海森, 李孝禄, 丁建雄. 改进YOLOv8n的电磁离合器端面缺陷检测^*[J]. 现代制造工程, 2025, 536(5): 126-134.
[4]	贺昊辰, 王琨, 王纲, 李苏芙, 周霁宇, 陈泽欣. 基于GROOVE-YOLO的电表铅封螺钉旋转检测算法^*[J]. 现代制造工程, 2025, 534(3): 99-106.
[5]	李季村, 郑鹏, 李岩, 何青泽. 融合GhostBottleneck及注意力机制的铝型材表面缺陷检测算法研究^*[J]. 现代制造工程, 2025, 534(3): 115-123.
[6]	周思聪, 向峰, 李红军, 左颖. 基于自编码器GAN数据增强的工业小目标缺陷检测^*[J]. 现代制造工程, 2025, 533(2): 101-108.
[7]	唐冰慧, 杨伟东, 董文益, 张龙. 基于深度学习的陶瓷表面缺陷检测研究综述[J]. 现代制造工程, 2025, 541(10): 148-158.
[8]	郭康, 王志刚, 徐增丙. 基于AFF-Stablenet模型的小样本轴承故障诊断^*[J]. 现代制造工程, 2024, 528(9): 144-151.
[9]	叶楠, 张传棻, 王荣, 贺明荣, 张雁辉, 段书用. 极端服役多工况风电齿轮箱箱体轻量化设计^*[J]. 现代制造工程, 2024, 528(9): 152-159.
[10]	孙铁强, 秦愿伟, 宋超, 肖鹏程. 基于改进YOLOv7的钢卷端面缺陷检测^*[J]. 现代制造工程, 2024, 526(7): 117-125.
[11]	杨益, 程文明, 杜润, 饶雄. 仿生蛋形箱梁力学性能研究^*[J]. 现代制造工程, 2024, 525(6): 1-8.
[12]	曹节强, 李军利, 刘钢, 张立强. 基于形态学的自动铺丝纤维铺放准确性检测^*[J]. 现代制造工程, 2024, 524(5): 15-22.
[13]	马涛, 李敬兆. 基于MFA-UNet的铜制螺纹零件外表面缺陷检测^*[J]. 现代制造工程, 2024, 524(5): 113-120.
[14]	高山凤, 雷乐, 赵伦, 叶凯, 李承旺, 赵升升, 宋振东, 鲍丹阳. 航空铝钛合金自冲铆接成形机理及力学行为研究^*[J]. 现代制造工程, 2024, 523(4): 1-6.
[15]	曾飞, 李斌, 周健, 樊江峰. 改进YOLOv7算法的排水管道缺陷检测与几何表征^*[J]. 现代制造工程, 2024, 522(3): 110-118.