基于深度学习的带式输送机非煤异物识别方法

胡璟皓, 高妍, 张红娟, 靳宝全

胡璟皓,高妍,张红娟,等.基于深度学习的带式输送机非煤异物识别方法研究[J].工矿自动化,2021,47(6):57-62.. DOI: 10.13272/j.issn.1671-251x.2021020041
引用本文: 胡璟皓,高妍,张红娟,等.基于深度学习的带式输送机非煤异物识别方法研究[J].工矿自动化,2021,47(6):57-62.. DOI: 10.13272/j.issn.1671-251x.2021020041
HU Jinghao, GAO Yan, ZHANG Hongjuan, JIN Baoquan. Research on the identification method of non-coal foreign object ofbelt conveyor based on deep learning[J]. Journal of Mine Automation, 2021, 47(6): 57-62. DOI: 10.13272/j.issn.1671-251x.2021020041
Citation: HU Jinghao, GAO Yan, ZHANG Hongjuan, JIN Baoquan. Research on the identification method of non-coal foreign object ofbelt conveyor based on deep learning[J]. Journal of Mine Automation, 2021, 47(6): 57-62. DOI: 10.13272/j.issn.1671-251x.2021020041

基于深度学习的带式输送机非煤异物识别方法

基金项目: 

山西省科技基础条件平台项目(201605D121028)

详细信息
  • 中图分类号: TD528.1

Research on the identification method of non-coal foreign object ofbelt conveyor based on deep learning

  • 摘要: 针对现有非煤异物图像识别法识别目标单一、模型缺乏定位能力等问题,提出一种基于深度学习的带式输送机非煤异物识别方法。该方法以目标检测算法YOLOv3为基础框架,采用Focal Loss函数替换YOLOv3模型中的交叉熵损失函数,对YOLOv3模型进行改进;通过调节最佳超参数(权重参数α和焦点参数γ)来平衡样本之间的比例,解决非煤异物样本不平衡问题,使模型在训练时更专注学习复杂目标样本特征,提高模型预测性能;搭建了异物数据集,并通过异物数据集对分类性能和速度进行实验。结果表明:Focal Loss函数在异物数据集中表现优于交叉熵损失函数,在γ=2,α=075时准确率提升5%,故最佳超参数为γ=2,α=075;改进后的YOLOv3模型对锚杆、角铁、螺母3种非煤异物的识别精确率分别提升了约47%,35%和68%,召回率分别提升了约66%,35%和60%;模型在2080Ti平台下每张图像预测类别与实际类别一致,且置信度在94%以上。
    Abstract: In order to solve the problems of single identification target and lack of positioning ability of the existing image identification methods of foreign objects, an identification method of non-coal foreign object of belt conveyor based on deep learning is proposed.This method uses the target detection algorithm YOLOv3 as the basic framework, and uses the Focal Loss function to replace the cross entropy loss function in the original model to improve the YOLOv3 model. By adjusting the optimal hyperparameters (weight parameter α and focus parameter γ) to balance the ratio between samples, the method solves the non-coal foreign object sample imbalance problem. Therefore, the model focuses more on learning complex target sample characteristics during training and improves the model forecast performance. A foreign object dataset is built and the classification performance and speed are tested by the foreign object dataset.The results show that the Focal Loss function performs better than the cross entropy loss function in the foreign object dataset, and the accuracy is increased by 5% when γ=2 and α=075. Therefore, the optimal hyperparameter is γ=2 and α=075.The improved YOLOv3 model's identification accuracy of the three non-coal foreign objects of bolts, angle ironsand nuts increases by about 47%, 35% and 68% respectively, and the recall rate increases by about 66%, 35% and 60% respectively. Under the 2080Ti platform, the predicted type of each image is consistent with the actual type, and the confidence level is above 94%.
  • 期刊类型引用(13)

    1. 王琍. 基于COMSOL的工作面瓦斯场与流动场耦合分析. 山东煤炭科技. 2024(01): 60-63 . 百度学术
    2. 邢震. 面向智能矿山的数字孪生技术研究进展. 工矿自动化. 2024(03): 22-34+41 . 本站查看
    3. 陈德山,杨婉欣,贾永磊,焦健. 高位钻孔抽采对采空区自燃“三带”的影响研究. 兰州石化职业技术大学学报. 2024(01): 1-5 . 百度学术
    4. 仵鹏程. 综放工作面停采期间防灭火方案设计及应用. 山西化工. 2024(07): 182-184 . 百度学术
    5. 邢震,韩安,陈晓晶,陈海舰,沈毅. 基于工业互联网的智能矿山灾害数字孪生研究. 工矿自动化. 2023(02): 23-30+55 . 本站查看
    6. 范加锋. 低位巷瓦斯抽采条件下采空区遗煤自燃规律研究. 工矿自动化. 2023(02): 102-108+124 . 本站查看
    7. 慕兰兰,传金平,杨小彬,聂朝刚. 砚北煤矿特厚易自燃煤层邻近采空区瓦斯抽采与煤自燃耦合研究. 矿业安全与环保. 2023(01): 25-36 . 百度学术
    8. 王海军,吴艳,马良,陈崇枫,孙保平,王相业,吴敏杰,刘善德. 陕北浅埋煤层一体化漏风通道探查技术. 煤矿安全. 2023(04): 83-90 . 百度学术
    9. 张立魁,杨伟,张海洋,孔令宇,赵亚明. 灾害复合工作面启封后CO变化规律研究. 煤炭技术. 2023(09): 187-190 . 百度学术
    10. 郭志锋,周钰博,岳治勇. 大直径钻孔瓦斯抽采对采空区遗煤自燃影响研究. 山东煤炭科技. 2023(10): 59-63 . 百度学术
    11. 王伟东. 高瓦斯厚煤层开采瓦斯与火协同防治技术研究. 煤炭技术. 2022(04): 101-103 . 百度学术
    12. 李芸卓,苏贺涛,季淮君. 采空区注氮对瓦斯爆炸危险区的影响数值模拟. 煤矿安全. 2021(03): 211-216 . 百度学术
    13. 任广意,谢军,王怡. 基于煤自燃大型模拟试验的采空区遗煤耗氧速率研究. 矿业研究与开发. 2020(10): 113-117 . 百度学术

    其他类型引用(3)

计量
  • 文章访问数:  164
  • HTML全文浏览量:  29
  • PDF下载量:  48
  • 被引次数: 16
出版历程
  • 刊出日期:  2021-06-19

目录

    /

    返回文章
    返回