基于深度学习的矿用输送带损伤检测方法

张梦超, 周满山, 张媛, 于岩, 李虎

张梦超,周满山,张媛,等.基于深度学习的矿用输送带损伤检测方法[J].工矿自动化,2021,47(6):51-56.. DOI: 10.13272/j.issn.1671-251x.2021040010
引用本文: 张梦超,周满山,张媛,等.基于深度学习的矿用输送带损伤检测方法[J].工矿自动化,2021,47(6):51-56.. DOI: 10.13272/j.issn.1671-251x.2021040010
ZHANG Mengchao, ZHOU Manshan, ZHANG Yuan, YU Yan, LI Hu. Damage detection method for mine conveyor belt based on deep learning[J]. Journal of Mine Automation, 2021, 47(6): 51-56. DOI: 10.13272/j.issn.1671-251x.2021040010
Citation: ZHANG Mengchao, ZHOU Manshan, ZHANG Yuan, YU Yan, LI Hu. Damage detection method for mine conveyor belt based on deep learning[J]. Journal of Mine Automation, 2021, 47(6): 51-56. DOI: 10.13272/j.issn.1671-251x.2021040010

基于深度学习的矿用输送带损伤检测方法

基金项目: 

国家重点研发计划资助项目(2018YFC0604702)

山东省自然科学基金资助项目(ZR2018BEE014)

详细信息
  • 中图分类号: TD528/634

Damage detection method for mine conveyor belt based on deep learning

  • 摘要: 针对目前输送带损伤检测方法缺乏对输送带撕裂以外其他损伤类型研究的问题,提出一种基于深度学习的矿用输送带损伤检测方法,通过Yolov4-tiny目标检测网络对输送带损伤类型进行分类。Yolov4-tiny目标检测网络以CSPDarknet53-tiny作为主干特征提取网络,借鉴Resnet残差思想,使用残差块防止深层网络中高层语义特征丢失,同时采用特征金字塔网络实现高低层语义信息融合,达到提高检测精度的目的;将CSPDarknet53-tiny中的2个有效特征层输入预测网络Yolo Head,通过得分排序和非极大值抑制算法对预测框进行筛选,从而预测输送带损伤类型。实验结果表明,Yolov4-tiny目标检测网络在输送带损伤数据集上对表面划伤、撕裂、表面破损和击穿4种损伤类型检测的平均精度分别为9936%,9485%,8930%,8676%,平均精度均值达9257%;与Faster-RCNN,RFBnet,M2det,SSD,Yolov3,EfficientDet和Yolov4目标检测网络相比,Yolov4-tiny目标检测网络在数据集上取得了最快的检测速度,帧速率达101 帧/s,实现了较好的速度与精度的平衡,且占用计算资源相对较少;通过对数据集外新鲜样本的检测,验证了本文方法具有较好的泛化能力。
    Abstract: In order to solve the problem that the current conveyor belt damage detection methods lack research on damage types other than conveyor belt tear, a damage detection method for mine conveyor belt based on deep learning is proposed. And the conveyor belt damage types are classified by the Yolov4-tiny target detection network. The Yolov4-tiny target detection network uses CSPDarknet53-tiny as the backbone feature extraction network, draws on the Resnet residual idea, uses residual blocks to prevent the loss of high-level semantic features in the deep network. At the same time, the method uses feature pyramid network to obtain the fusion of high-level and low-level semantic information to achieve the purpose of improving detection precision. The two effective feature layers in CSPDarknet53-tiny are input into the prediction network Yolo Head, and the prediction frames are filtered by the score ranking and non-maximum suppression algorithm to predict the types of conveyor belt damage. The experimental results show that the average precision of the Yolov4-tiny target detection network on the conveyor belt damage data set for the four damage types of surface scratches, tears, surface damage and breakdown is 99.36%, 94.85%, 89.30%, and 86.76% respectively, and the mean average precision is 92.57%. Compared with Faster-RCNN, RFBnet, M2det, SSD, Yolov3, EfficientDet and Yolov4 target detection networks, the Yolov4-tiny target detection network achieves the fastest detection speed on the data set with a frame rate of 101 frames/s. The network achieves better balance between speed and precision, and occupies relatively less computing resources. The detection of fresh samples outside the data set verifies that the method in this paper has good generalization ability.
  • 期刊类型引用(15)

    1. 游磊,向兆军,孙柳军. 基于线结构光的矿用输送带纵向撕裂检测技术. 矿业安全与环保. 2025(01): 180-186 . 百度学术
    2. 张舒,叶涛,陈云. 改进YOLOv5的矿用输送带损伤检测方法. 起重运输机械. 2024(02): 31-36 . 百度学术
    3. 张释如,余文瑾,王锐. 基于CNN-SVM的输送带纵向撕裂检测方法研究. 煤炭技术. 2024(07): 201-204 . 百度学术
    4. 张克亮. 基于MT-CNN的矿井带式输送机输煤量检测技术. 中国矿业. 2024(06): 137-142 . 百度学术
    5. 王振珺. 基于CenterNet算法的带式输送机输送带破损检测方法与应用. 建井技术. 2024(03): 85-89 . 百度学术
    6. 杨泽霖,杨立清,郝斌. 基于对抗修复网络的输送带表面缺陷检测. 工矿自动化. 2024(09): 108-114+166 . 本站查看
    7. 张宏飞,冯永利,黄金凤. 改进YOLOv5的输送带缺陷检测. 电子测量技术. 2024(22): 161-168 . 百度学术
    8. 秦彤,李晓明. 改进YOLOv4的输送带纵向撕裂检测. 计算机系统应用. 2023(03): 186-194 . 百度学术
    9. 张俊科,吴敬兵,吴晓晓. 基于YOLOv5的岸边集装箱桥式起重机钢丝绳损伤检测方法. 起重运输机械. 2023(16): 30-36 . 百度学术
    10. 王学立,赵辰燃,李青,何显能,甘梅. 基于多模态的输送带撕裂大模型算法设计. 煤矿安全. 2023(09): 202-207 . 百度学术
    11. 郭洁,井庆贺,闫寿庆,王鑫,谢苗,吴意兵. 基于MFCC声音特征信号提取的托辊故障诊断. 中国安全科学学报. 2023(S2): 116-121 . 百度学术
    12. 熊念强,文锋,李清,陈磊,周冉. 带式输送机胶带撕裂检测技术综述. 煤炭工程. 2022(07): 79-85 . 百度学术
    13. 陈云,吴敬兵,叶涛. 基于目标检测的输送带损伤检测方法. 自动化与仪表. 2022(11): 64-69 . 百度学术
    14. 陈亮,杨迪. 改进Centernet的输送带损伤检测. 平顶山学院学报. 2022(05): 20-23+33 . 百度学术
    15. 周宇杰,徐善永,黄友锐,唐超礼. 基于改进YOLOv4的输送带损伤检测方法. 工矿自动化. 2021(11): 61-65 . 本站查看

    其他类型引用(12)

计量
  • 文章访问数:  222
  • HTML全文浏览量:  23
  • PDF下载量:  61
  • 被引次数: 27
出版历程
  • 刊出日期:  2021-06-19

目录

    /

    返回文章
    返回