留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于AI视频分析的煤矿瓦斯抽采钻场远程监督管理方法

胡金成 张立斌 蒋泽 姚超修 蒋志龙 王正义

胡金成,张立斌,蒋泽,等. 基于AI视频分析的煤矿瓦斯抽采钻场远程监督管理方法[J]. 工矿自动化,2023,49(11):167-172.  doi: 10.13272/j.issn.1671-251x.2023080031
引用本文: 胡金成,张立斌,蒋泽,等. 基于AI视频分析的煤矿瓦斯抽采钻场远程监督管理方法[J]. 工矿自动化,2023,49(11):167-172.  doi: 10.13272/j.issn.1671-251x.2023080031
HU Jincheng, ZHANG Libin, JIANG Ze, et al. Remote supervision and management method for coal mine gas extraction drilling site based on AI video analysis[J]. Journal of Mine Automation,2023,49(11):167-172.  doi: 10.13272/j.issn.1671-251x.2023080031
Citation: HU Jincheng, ZHANG Libin, JIANG Ze, et al. Remote supervision and management method for coal mine gas extraction drilling site based on AI video analysis[J]. Journal of Mine Automation,2023,49(11):167-172.  doi: 10.13272/j.issn.1671-251x.2023080031

基于AI视频分析的煤矿瓦斯抽采钻场远程监督管理方法

doi: 10.13272/j.issn.1671-251x.2023080031
基金项目: 江苏省产学研合作项目(BY2022109);天地科技股份有限公司科技创新创业资金专项项目(2020-TD-ZD010);中煤科工集团常州研究院科研项目(2022TY2012)。
详细信息
    作者简介:

    胡金成(1991—),男,安徽淮南人,实习研究员,硕士,主要从事智能矿山大数据分析与智能视频方面的研究,E-mail:hujincheng_cumt@126.com

  • 中图分类号: TD712

Remote supervision and management method for coal mine gas extraction drilling site based on AI video analysis

  • 摘要: 传统的煤矿瓦斯抽采钻场视频监控系统在钻孔施工及退钻杆期间,只具有监测和存储功能,重要的过程参数或信息只能由监测人员通过视频录像查看,存在记录施工信息易出错、钻场管理人员难以连续监控现场视频等问题。针对上述问题,提出了一种基于AI视频分析的煤矿瓦斯抽采钻场远程监督管理方法。该方法包括信息牌检测、OCR识别、退杆分析3种算法。信息牌检测用于检测当前施工环节,OCR识别用于识别信息牌上打钻流程与施工信息,退杆分析用于分析收孔阶段的退杆数,从而实现打钻作业的全过程分析与管控。在接收并开始打钻任务后,启用信息牌检测与OCR识别服务,根据依次识别到的开孔、收孔、封孔流程与施工参数,自动保存施工信息。当识别出开始收孔,启用退杆分析服务;当识别出结束收孔,停止退杆分析服务。实验结果表明:信息牌检测算法的识别准确率为96%。PaddleOCR识别算法平均用时17.51 ms,较EasyOCR、ChineseOCR识别算法分别降低了25.25,4.34 ms;PaddleOCR识别算法的准确率较其他2种识别算法分别提高了5.75%,2.29%,召回率较其他2种识别算法分别提高了9.77%,2.36%。退杆分析算法能够有效识别现场退杆数,准确率约为95%。

     

  • 图  1  打钻作业流程

    Figure  1.  Process of drilling operation

    图  2  信息牌检测算法流程

    Figure  2.  Process of information board detection algorithm

    图  3  YOLOv5算法模型结构

    Figure  3.  Structure of YOLOv5 algorithm model

    图  4  OCR识别算法业务流程

    Figure  4.  Processes of OCR recognition algorithm

    图  5  退杆分析算法业务流程

    Figure  5.  Process of pip withdrawal analysis algorithm

    图  6  开孔作业对应的信息牌

    Figure  6.  Information board corresponding to the opening hole

    图  7  收孔作业对应的信息牌

    Figure  7.  The information board corresponding to the closing hole

    图  8  封孔作业对应的信息牌

    Figure  8.  Information board corresponding to the sealing hole

    图  9  OCR识别开孔结果

    Figure  9.  The result of opening hole by OCR recognition

    图  10  退杆分析效果

    Figure  10.  The effect of pipe withdrawal analysis

    表  1  OCR识别效果对比

    Table  1.   Comparison of OCR identification effects

    算法准确率/%召回率/%时间/ms
    EasyOCR88.1586.2642.76
    ChineseOCR91.6193.6721.85
    PaddleOCR93.9096.0317.51
    下载: 导出CSV
  • [1] 姜德义,魏立科,王翀,等. 智慧矿山边缘云协同计算技术架构与基础保障关键技术探讨[J]. 煤炭学报,2020,45(1):484-492.

    JIANG Deyi,WEI Like,WANG Chong,et al. Discussion on the technology architecture and key basic support technology for intelligent mine edge-cloud collaborative computing[J]. Journal of China Coal Society,2020,45(1):484-492.
    [2] 谭章禄,吴琦,肖懿轩,等. 智慧矿山信息可视化研究[J]. 工矿自动化,2020,46(1):26-31.

    TAN Zhanglu,WU Qi,XIAO Yixuan,et al. Research on information visualization of smart mine[J]. Industry and Mine Automation,2020,46(1):26-31.
    [3] 王清峰,陈航. 瓦斯抽采智能化钻探技术及装备的发展与展望[J]. 工矿自动化,2018,44(11):18-24.

    WANG Qingfeng,CHEN Hang. Development and prospect on intelligent drilling technology and equipment for gas drainage[J]. Industry and Mine Automation,2018,44(11):18-24.
    [4] 吴克介,黄强,许金,等. 基于跨平台架构的全矿井瓦斯抽采智能管控软件设计[J]. 工矿自动化,2022,48(11):125-132.

    WU Kejie,HUANG Qiang,XU Jin,et al. Design of intelligent control software for whole mine gas extraction based on cross-platform architecture[J]. Journal of Mine Automation,2022,48(11):125-132.
    [5] 盛文燕,李勇,郝允领,等. 一种用于煤矿钻场的钻杆自动计数智能管理系统:CN202110513582.3[P]. 2021-08-06.

    SHENG Wenyan,LI Yong,HAO Yunling,et al. An intelligent management system for automatic counting of drill pipe in coal mine drilling field:CN202110513582.3[P]. 2021-08-06.
    [6] 张栋,姜媛媛. 基于改进MobileNetV2的钻杆计数方法[J]. 工矿自动化,2022,48(10):69-75.

    ZHANG Dong,JIANG Yuanyuan. Drill pipe counting method based on improved MobileNetV2[J]. Journal of Mine Automation,2022,48(10):69-75.
    [7] 潘涛. 煤矿生产系统集成的层次结构及其标准化问题研究[J]. 工矿自动化,2014,40(9):19-23.

    PAN Tao. Research of integrated architecture of coal mine production system and its standardization problems[J]. Industry and Mine Automation,2014,40(9):19-23.
    [8] 孙继平. 煤矿监控新技术与新装备[J]. 工矿自动化,2015,41(1):1-5.

    SUN Jiping. New technologies and new equipment of coal mine monitoring[J]. Industry and Mine Automation,2015,41(1):1-5.
    [9] 徐辉,贺耀宜. 一种煤矿井下监控视频图像预处理方法[J]. 工矿自动化,2016,42(1):32-34.

    XU Hui,HE Yaoyi. An image preprocessing method for underground monitoring video[J]. Industry and Mine Automation,2016,42(1):32-34.
    [10] 张立亚. 矿山智能视频分析与预警系统研究[J]. 工矿自动化,2017,43(11):16-20.

    ZHANG Liya. Research on intelligent video analysis and early warning system for mine[J]. Industry and Mine Automation,2017,43(11):16-20.
    [11] 吴文臻. 智能视频监控系统在煤矿井下的应用研究[J]. 煤炭技术,2016,35(4):271-273.

    WU Wenzhen. Application research of intelligent video surveillance system in coal mine[J]. Coal Technology,2016,35(4):271-273.
    [12] 程德强,钱建生,郭星歌,等. 煤矿安全生产视频AI识别关键技术研究综述[J]. 煤炭科学技术,2023,51(2):349-365.

    CHENG Deqiang,QIAN Jiansheng,GUO Xingge,et al. Review on key technologies of AI recognition for videos in coal mine[J]. Coal Science and Technology,2023,51(2):349-365.
    [13] 王国法,王虹,任怀伟,等. 智慧煤矿2025情景目标和发展路径[J]. 煤炭学报,2018,43(2):295-305.

    WANG Guofa,WANG Hong,REN Huaiwei,et al. 2025 scenarios and development path of intelligent coal mine[J]. Journal of China Coal Society,2018,43(2):295-305.
    [14] 孙继平,孙雁宇,范伟强. 基于可见光和红外图像的矿井外因火灾识别方法[J]. 工矿自动化,2019,45(5):1-5,21.

    SUN Jiping,SUN Yanyu,FAN Weiqiang. Mine exogenous fire identification method based on visible light and infrared image[J]. Industry and Mine Automation,2019,45(5):1-5,21.
    [15] 苗续芝,陈伟,毕方明,等. 基于改进FOA−SVM的矿井火灾图像识别[J]. 计算机工程,2019,45(4):267-274.

    MIAO Xuzhi,CHEN Wei,BI Fangming,et al. Mine fire image recognition based on improved FOA-SVM[J]. Computer Engineering,2019,45(4):267-274.
    [16] 付文俊,杨富强,彭伟,等. 红庆梁煤矿安全智能视频系统[J]. 煤矿安全,2018,49(12):96-98.

    FU Wenjun,YANG Fuqiang,PENG Wei,et al. Application of safety intelligent video system in Hongqingliang Coal Mine[J]. Safety in Coal Mines,2018,49(12):96-98.
    [17] 牛云鹏,张立亚,贺云龙. 智能大采高综采工作面视频分析系统的研究与应用[J]. 中国煤炭,2020,46(6):40-44.

    NIU Yunpeng,ZHANG Liya,HE Yunlong. Research and application of video analysis system of intelligent fully mechanized working face with large mining height[J]. China Coal,2020,46(6):40-44.
    [18] 金利国,赵存会. 煤矿探水视频管理系统[J]. 工矿自动化,2018,44(9):102-104.

    JIN Liguo,ZHAO Cunhui. Water detection video management system of coal mine[J]. Industry and Mine Automation,2018,44(9):102-104.
    [19] ZHOU Junchi,JIANG Ping,ZOU Airu,et al. Ship target detection algorithm based on improved YOLOv5[J]. Journal of Marine Science and Engineering,2021,9(8):908-922. doi: 10.3390/jmse9080908
    [20] KASPEREULAERS M,HAHN N,BERGER S,et al. Short communication:detecting heavy goods vehicles in rest areas in winter conditions using YOLOv5[J]. Algorithms,2021,14(4):114-125. doi: 10.3390/a14040114
    [21] 邢宇驰,李大军,叶发茂. 基于YOLOv5的遥感图像目标检测[J]. 江西科学,2021,39(4):725-732.

    XING Yuchi,LI Dajun,YE Famao. Remote sensing image target detection based on YOLOv5[J]. Jiangxi Science,2021,39(4):725-732.
  • 加载中
图(10) / 表(1)
计量
  • 文章访问数:  1126
  • HTML全文浏览量:  140
  • PDF下载量:  68
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-08-09
  • 修回日期:  2023-11-08
  • 网络出版日期:  2023-11-15

目录

    /

    返回文章
    返回