基于深度学习的铁路货车关键零部件故障图像检测算法研究

赖陟斌; LAI Zhibin; 史红梅; SHI Hongmei

doi:10.48014/fcmet.20231109001

基于深度学习的铁路货车关键零部件故障图像检测算法研究

Research on Image Detection Algorithm for Failure of Key Parts of Railway Freight Wagon Based on Deep Learning

中国机械工程技术学报 2024年第3卷第1期页码[11-22] 下载全文[4.7MB] [HTML]

摘要

铁路货车零部件故障是造成货车事故的主要原因之一, 当前列检工作多采用“人眼识图”判断零部件故障, 无法实现故障自动识别。针对关键零部件故障自动识别的问题, 根据“先定位, 后识别”的思路提出基于深度学习和图像处理技术结合的图像检测算法。首先, 构建零部件检测数据集和零部件故障识别数据集。其次, 融合小目标检测层、卷积注意力模块, 提出改进的Small-Target-Detect-Layer and CBAM YOLOv5s (SC-YOLOv5s) , 实现多尺度关键零部件的定位、分类、裁剪。最后, 提出基于目标检测结果与先验知识的算法直接判断丢失类型故障, 改进的Mobile-NetV3分类算法实现滚动轴承甩油、锁紧板松动、摇枕弹簧断裂三种故障的自动识别, 以及图像处理方法实现交叉杆弯曲、滚动轴承前盖破损两种故障的自动识别。结果表明, SC-YOLOv5s算法的mAP@0. 5和mAP@0. 5: 0. 95分别可达99. 3%、74. 9%, 检测速度可达36. 09FPS; 改进的MobileNetV3算法对轴承甩油、锁紧板松动、摇枕弹簧断裂的识别准确率分别可达98. 63%、99. 34%、90. 21%; 图像处理法对交叉杆弯曲、滚动轴承前盖破损识别准确率分别可达95. 32%、82. 88%。

Abstract

The parts failure of railway freight wagon is one of the main causes of wagon accidents. Currently, train inspection work mostly uses "human eye recognition" to determine the part failures, which cannot realize the automatic fault identification. For the problem of automatic identification of key parts failure, an image detection algorithm based on is proposed based on the combination of deep learning and image processing technology according to the idea of "first locate, then identify". First, the parts detection data set and parts fault identification data set are constructed. Then, the Small-Target-Detect-Layer and CBAM YOLOv5s (SC-YOLOv5s) are integrated with the small target detection layer and Convolutional Block Attention Module to realize the localization, classification and cropping of multi-scale key parts. Finally, an algorithm based on object detection results and prior knowledge is proposed to directly determine the type of loss fault, and the improved MobileNetV3 classification algorithm is proposed to realize the automatic identification of three kinds of faults: oil dumping of rolling bearing, loosening of locking plate, and breakage of rocking pillow spring, as well as the image processing method to realize the automatic identification of two kinds of faults: bending of crossover rod and breakage of front cover of rolling bearing. The results show that SC-YOLOv5s mAP@0. 5 and mAP@0. 5: 0. 95 can reach 99. 3% and 74. 9% and the detection speed can reach 36. 09 FPS; the improved MobileNetV3 algorithm can reach 98. 63%, 99. 34%, and 90. 21% of the recognition accuracy of bearing oil dumping, locking plate loosening, and rocking pillow spring breakage; the recognition accuracy of the image processing method for crossbar bending and rolling bearing front cover breakage can reach 95. 32% and 82. 88%, respectively.

DOI

10.48014/fcmet.20231109001

文章类型

研究性论文

收稿日期

2023-11-09

接收日期

2023-11-28

出版日期

2024-03-28

关键词

铁路货车, 故障检测, 目标检测

Keywords

Railway freight wagon, failure detection, target detection

作者

赖陟斌, 史红梅^*

Author

LAI Zhibin, SHI Hongmei^*

所在单位

北京交通大学轨道交通智能检测技术研究所, 北京 100091

Company

Institute of Intelligent Detection Technology of Rail Transit, Beijing Jiaotong University, Beijing 100091, China

浏览量

860

下载量

311

参考文献

[1] 丁彦彬. 浅谈TFDS在货车运行安全管理中的应用[J]. 减速顶与调速技术, 2019(02): 23-25.
https://doi.org/10.3969/j.issn.1674-2427.2019.02.008
[2] 曾广胜, 麦强. 提升TFDS发现故障功能的思考[J]. 铁道运营技术, 2020, 26(01): 35-38.
https://doi.org/10.13572/j.cnki.tdyy.2020.01.011
[3] 赵峰. 货车TFDS图像自动识别系统分析[J]. 智慧轨道交通, 2022, 59(05): 49-52.
https://doi.org/10.3969/j.issn.2097-0366.2022.05.011
[4] 李江昆. TFDS车辆故障自动识别系统研究及应用[J]. 铁道车辆, 2021, 59(05): 125-127.
https://doi.org/10.3969/j.issn.1002-7602.2021.05.033
[5] 费垚东, 李柏林, 范宏. TFDS中螺栓故障的自动识别算法研究[J]. 机械设计与制造, 2021(10): 5.
https://doi.org/10.3969/j.issn.1001-3997.2021.10.021
[6] 雷蕾, 宋冬利, 张卫华, 等. 基于HCRD 的列车锁紧板偏转自动识别方法[J]. 铁道科学与工程学报, 2021, 18(07): 1895-1902.
https://doi.org/10.19713/j.cnki.43-1423/u.T20200854
[7] 孙明. 基于图像处理的货车转向架故障检测[D]. 石家庄: 石家庄铁道大学, 2018.
[8] Sun J, Xiao Z, Xie Y. Automatic multi-fault recognition in TFDS based on convolutional neural network[J]. Neurocomputing, 2017, 222: 127-136.
https://doi.org/10.1016/j.neucom.2016.10.018
[9] 李萍, 吴斌方, 刘默耘. 基于深度学习的铁路列车关键零部件图像故障检测[J]. 铁道科学与工程学报, 2019, 16(12): 3119-3125.
https://doi.org/10.19713/j.cnki.43-1423/u.2019.12.027
[10] 王苗, 张龙信. 基于YOLOv4的列车锁紧板图像故障检测[J]. 现代信息科技, 2021, 5(20): 42-43, 49.
https://doi.org/10.19850/j.cnki.2096-4706.2021.20.012
[11] 符潇. 基于U-Net的多阶段注意力感知列车图像识别与故障检测方法[D]. 长沙: 湖南大学, 2021.
https://doi.org/10.27135/d.cnki.ghudu.2020.001012
[12] Redmon J, Divvala S, Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection [C]. //2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, NV, USA: 2016: 779-788.
[13] Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger[C]. //2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, HI, USA: 2017: 6517-6525.
[14] Redmon J, Farhadi A. YOLOv3: An Incremental Improvement[ J]. arXiv preprint arXiv: 1804. 02767, 2018.
[15] Bochkovskiy A, Wang C Y, Liao H. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. arXiv preprint arXiv: 2004. 10934, 2020.
[16] Howard A, Sandler M, Chen B, et al. Searching for MobileNetV3[ C]. //2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul, South Ko- rea: IEEE, 2019: 1314-1324.
https://doi.org/10.1109/iccv.2019.00140
[17] Sandler M, Howard A, Zhu M, et al. MobileNetV2: Inverted residuals and linear bottlenecks[C]. //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 4510-4520.
https://doi.org/10.1109/cvpr.2018.00474

引用本文

赖陟斌, 史红梅. 基于深度学习的铁路货车关键零部件故障图像检测算法研究[J]. 中国机械工程技术学报, 2024, 3(1): 11-22.

Citation

LAI Zhibin, SHI Hongmei. Research on image detection algorithm for failure of key parts of railway freight wagon based on deep learning[J]. Frontiers of Chinese Mechanical Engineering and Technology, 2024, 3(1): 11-22.