刮板输送机断链智能监测技术研究

李灵锋; 张洁; 陈茁; 查天任; 尹瑞

doi:10.13272/j.issn.1671-251x.2024110068

刮板输送机断链智能监测技术研究

李灵锋^1,,
张洁¹,
陈茁¹,
查天任^1, ,,
尹瑞^{2, 3}

1.
河北建材职业技术学院机电工程系，河北秦皇岛　066004
2.
中煤张家口煤矿机械有限责任公司，河北张家口　076250
3.
河北省高端智能矿山装备技术创新中心，河北张家口　076250

基金项目: 国家重点研发计划项目（2017YFF0210606）；河北省高等学校科学研究项目（ZD2022018）。

详细信息

作者简介:
李灵锋（1978—），男，河北新乐人，副教授，硕士，主要研究方向为电气自动化技术，E-mail：53829362@qq.com

通讯作者:
查天任（1991—），男，江苏南通人，工程师，硕士，研究方向为电气和计算机技术，E-mail：y18032557723@126.com。

中图分类号: TD67
计量
- 文章访问数: 68
- HTML全文浏览量: 8
- PDF下载量: 3
出版历程
- 收稿日期: 2024-11-17
- 修回日期: 2025-03-14
- 网络出版日期: 2025-02-27
- 刊出日期: 2025-03-14

Research on intelligent technology for broken chain monitoring on scraper conveyors

1.
Mechanical and Electrical Engineering Department, Hebei Construction Material Vocational and Technical College, Qinhuangdao 066004, China
2.
China Coal Zhangjiakou Coal Mining Machinery Co., Ltd., Zhangjiakou 076250, China
3.
Hebei Province High-end Intelligent Mine Equipment Technology Innovation Center, Zhangjiakou 076250, China

摘要

摘要:
针对现有基于AI算法的煤矿井下刮板输送机断链监测技术在线学习能力低、检测精度差、稳定性低、复杂场景适应性和可靠性差等问题，通过在极限学习机（ELM）中增加增量式在线训练，设计了可实现离线样本和实时在线样本训练的在线贯序极限学习机（OSELM）网络，进而提出了基于OSELM的刮板输送机断链智能监测技术。将经过大量煤矿井下刮板输送机链条监控图像（离线样本）训练的OSELM网络算法写入AI摄像仪，将AI摄像仪安装于刮板输送机机尾，实时感知刮板输送机链条运行状态并进行在线学习，由AI摄像仪输出控制决策，并通过刮板输送机集中控制系统平台实时显示识别结果。井下工业性试验结果表明，OSELM网络具有较高的自主学习能力、较强的泛化性和鲁棒性，对刮板输送机断链识别的平均精度均值、准确率和精确率分别为98.6%，99.3%，91.7%，检测速度达205.6帧/s，整体效果优于深度神经网络融合网络、RT−DETR、YOLOv5、YOLOv8、ELM等模型，实现了刮板输送机链条状态的精准、实时检测。
- 刮板输送机 /
- 链条状态识别 /
- 断链监测 /
- AI摄像仪 /
- 在线贯序极限学习机网络
Abstract:
To address the issues of existing AI algorithm-based broken chain monitoring technologies for underground coal mine scraper conveyors, including poor online learning ability, low detection accuracy, instability, and inadequate adaptability and reliability in complex scenarios, an online sequential extreme learning machine (OSELM) network was developed by integrating incremental online training into the extreme learning machine (ELM). This approach enabled both offline and real-time online learning. Based on this, an OSELM-based intelligent broken chain monitoring technology for scraper conveyors was proposed. The OSELM network algorithm, trained on a large dataset of underground scraper conveyor chain monitoring images (offline samples), was embedded into an AI camera. The AI camera was installed at the tail of the scraper conveyor to monitor the operation status of the chain in real-time while performing continuous online learning. The AI cameras output control decisions, with recognition results displayed in real-time on the centralized control system platform for the scraper conveyor. The results of industrial tests in underground mining environments demonstrated that the OSELM network exhibited strong self-learning ability, high generalization ability, and robustness. The mean average precision, accuracy, and precision for chain breakage identification on the scraper conveyor reached 98.6%, 99.3%, and 91.7%, respectively, with a detection speed of 205.6 frames per second. The overall performance outperforms models such as Deep Neural Network Fusion Network, RT-DETR, YOLOv5, YOLOv8, and ELM, achieving precise and real-time detection of the chain status of scraper conveyors.
- scraper conveyor /
- chain status identification /
- broken chain monitoring /
- AI camera /
- online sequential extreme learning machine

HTML全文

图 1 ELM网络拓扑

Figure 1. Topology of ELM network

下载: 全尺寸图片幻灯片

图 2 OSELM网络框架

Figure 2. OSELM network framework

下载: 全尺寸图片幻灯片

图 3 样本数据集（部分）

Figure 3. Sample dataset (partial)

下载: 全尺寸图片幻灯片

图 4 刮板输送机断链智能监测模型

Figure 4. Intelligent chain-broken monitoring model for scraper conveyor

下载: 全尺寸图片幻灯片

图 5 刮板输送机断链智能监测AI摄像仪布置

Figure 5. AI camera deployment for broken chain monitoring system on scraper conveyor

下载: 全尺寸图片幻灯片

图 6 刮板输送机集中控制系统主界面

Figure 6. Main interface of centralized control system for scraper conveyor

下载: 全尺寸图片幻灯片

图 7 断链监测可视化界面

Figure 7. Visualization interface of broken chain monitoring

下载: 全尺寸图片幻灯片

图 8 不同网络模型的断链识别可视化结果

Figure 8. Visualization results of broken chain identification using different networks

下载: 全尺寸图片幻灯片

表 1 不同断链监测网络模型性能对比

Table 1 Performance comparison of different network models for broken chain monitoring

模型	mAP50/%	准确率/%	精确率/%	检测速度/（帧·s⁻¹）
文献[18]	93.4	96.5	87.1	206.3
文献[19]	97.6	97.2	87.8	67.2
文献[20]	92.7	94.8	85.7	64.9
文献[21]	92.8	95.1	88.0	93.6
文献[22]	—	75.8	93.4	43.8
ELM	94.1	96.8	88.2	173.5
OSELM	98.6	99.3	91.7	205.6

下载: 导出CSV

参考文献(24)

[1]	李其钒,潘燕,韩正铜. 煤矿刮板输送机断链受力分析及强度条件[J]. 煤矿机械,2011,32(4):105-107. LI Qifan,PAN Yan,HAN Zhengtong. Force analysis and strength condition of chain scission of scraper conveyor[J]. Coal Mine Machinery,2011,32(4):105-107.
[2]	张伟. 刮板输送机卡链断链工况力学特性研究[J]. 机械管理开发,2024,39(7):78-79,116. ZHANG Wei. Mechanical characteristics of chain breaking condition of scraper conveyor[J]. Mechanical Management and Development,2024,39(7):78-79,116.
[3]	谢苗,杨润坤,卢进南,等. 刮板输送机卡链断链工况力学特性研究[J]. 机械强度,2022,44(2):394-401. XIE Miao,YANG Runkun,LU Jinnan,et al. Study on mechanical characteristics of scraper conveyor under chain-breaking condition[J]. Journal of Mechanical Strength,2022,44(2):394-401.
[4]	JIANG Shoubo,ZHANG Yuqi,ZENG Qingliang,et al. Analysis of scraper conveyor chain dynamics under falling coal impact conditions[J]. Machines,2024,12(9). DOI: 10.3390/MACHINES12090648.
[5]	XIE Chunxue,LIU Zhixiang,XIE Miao. Dynamic response analysis of scraper conveyor under the condition of chain broken[J]. Journal of Vibroengineering,2023,25(6):1053-1067. DOI: 10.21595/jve.2023.23192
[6]	葛世荣. 刮板输送机技术发展历程(三)——驱动与智能控制技术[J]. 中国煤炭,2024,50(4):1-12. GE Shirong. The development history of scraper conveyor technology (part three):intelligent drive and control technology[J]. China Coal,2024,50(4):1-12.
[7]	吴孙阳,张行,卢明立,等. 基于应力突变的刮板输送机断链检测系统[J]. 工矿自动化,2016,42(4):23-27. WU Sunyang,ZHANG Xing,LU Mingli,et al. Chain scission detection system of scraper conveyor based on stress mutation[J]. Industry and Mine Automation,2016,42(4):23-27.
[8]	ZHANG Xing,LI Wei,ZHU Zhencai,et al. Fault detection for the scraper chain based on vibration analysis using the adaptive optimal kernel time-frequency representation[J]. Shock and Vibration,2019,2019(1). DOI: 10.1155/2019/6986240.
[9]	HUA Yilian,ZHU Zhencai,ZHOU Gongbo,et al. Chain state monitoring for a heavy scraper conveyor using UWB-based extended Kalman filter technique with range constraint selection method[J]. IEEE Transactions on Instrumentation Measurement,2022,71:1-9.
[10]	高昌乐,闵令江. 刮板输送机断链监测系统设计与研究[J]. 煤炭科学技术,2019,47(增刊2):55-58. GAO Changle,MIN Lingjiang. Design and research of chain breakage monitoring system for scraper conveyor[J]. Coal Science and Technology,2019,47(S2):55-58.
[11]	崔卫秀,穆润青,解鸿章,等. 500 m超长工作面刮板智能输送技术研究[J]. 煤炭科学技术,2024,52(4):326-335. CUI Weixiu,MU Runqing,XIE Hongzhang,et al. Research on intelligent conveying technology of 500 m ultra-long face scraper[J]. Coal Science and Technology,2024,52(4):326-335.
[12]	ZOU Huadong,JIA Ruiqing. Visual positioning and recognition of gangues based on scratch feature detection[J]. Traitement Du Signal,2019,36(2):147-153.
[13]	WANG Zisheng,LI Bo,et al. Response analysis of a scraper conveyor under chain faults based on MBD-DEM-FEM[J]. Strojniški Vestnik - Journal of Mechanical Engineering,2021,67(10):501-515. DOI: 10.5545/sv-jme.2021.7300
[14]	苏士龙,梁大勇,杜志峰,等. 基于深度学习与神经网络融合的刮板输送机断链监测技术研究[J]. 煤矿机械,2021,42(12):161-164. SU Shilong,LIANG Dayong,DU Zhifeng,et al. Research on chain breaking monitoring technology of scraper conveyor based on deep learning and neural network fusion[J]. Coal Mine Machinery,2021,42(12):161-164.
[15]	毛清华,郭文瑾,苏毅楠,等. 改进RT−DETR的煤矿刮板输送机链条故障智能识别方法研究[J/OL]. 煤炭科学技术,2024:1-12. [2024-10-14]. http://kns.cnki.net/kcms/detail/11.2402.td.20241014.1415.004.html. MAO Qinghua,GUO Wenjin,SU Yinan,et al. Research on intelligent identification method of chain fault of coal mine scraper conveyor based on improved RT-DETR[J/OL].Coal Science and Technology,2024:1-12. [2024-10-14]. http://kns.cnki.net/kcms/detail/11.2402.td.20241014.1415.004.html.
[16]	翟伟,陈鹏飞,王李进. 基于YOLOv5的刮板输送机断链监测技术[J]. 山西焦煤科技,2024,48(6):8-10,14. ZHAI Wei,CHEN Pengfei,WANG Lijin. Chain breakage monitoring technology for scraper conveyor based on YOLOv5[J]. Shanxi Coking Coal Science & Technology,2024,48(6):8-10,14.
[17]	盛浩. 刮板输送机断链智能监测系统的研制[J]. 煤矿机械,2024,45(8):209-212. SHENG Hao. Development of intelligent monitoring system for broken chain of scraper conveyor[J]. Coal Mine Machinery,2024,45(8):209-212.
[18]	许联航,高捷,叶壮,等. 基于图像处理与磁探伤技术的工作面刮板输送机在线监测系统[J]. 煤炭科学技术,2023,51(增刊1):390-395. XU Lianhang,GAO Jie,YE Zhuang,et al. On line monitoring system of face scraper based on image processing and magnetic flaw detection technology[J]. Coal Science and Technology,2023,51(S1):390-395.
[19]	HUANG Guangbin,ZHU Qinyu,SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing,2006,70(1/2/3):489-501.
[20]	张伟,李军霞,吴磊,等. 基于1DCNN−ELM的带式输送机托辊轴承故障诊断研究[J]. 煤炭科学技术,2023,51(增刊1):383-389. ZHANG Wei,LI Junxia,WU Lei,et al. Research on fault siagnosis of idler conveyor based on 1DCNN-ELM[J]. Coal Science and Technology,2023,51(S1):383-389.
[21]	高洁,伊雨,赵雯宇,等. 基于POA−ELM的含煤地层异常构造分类[J]. 煤炭学报,2023,48(11):4135-4144. GAO Jie,YI Yu,ZHAO Wenyu,et al. Classification of coal-bearing strata abnormal structure based on POA-ELM[J]. Journal of China Coal Society,2023,48(11):4135-4144.
[22]	董东林,陈昱吟,倪林根,等. 基于WOA−ELM算法的矿井突水水源快速判别模型[J]. 煤炭学报,2021,46(3):984-993. DONG Donglin,CHEN Yuyin,NI Lingen,et al. Fast discriminant model of mine water inrush source based on WOA-ELM algorithm[J]. Journal of China Coal Society,2021,46(3):984-993.
[23]	毛清华, 赵健博, 李亚周, 等. 基于ELM神经网络的采煤机截割载荷软测量建模方法[J]. 西安科技大学学报, 2020, 40(5): 769-774. MAO Qinghua, ZHAO Jianbo, LI Yazhou, et al. Soft sensor modeling method of shearer cutting load based on ELM neural network[J]. Journal of Xi'an University of Science and Technology, 2020, 40(5): 769-774.
[24]	周芳,唐楠楠,李志诚. Sherman−Morrison公式的五种证明方法[J]. 理论数学,2024,14(1):34-40. DOI: 10.12677/PM.2024.141005 ZHOU Fang,TANG Nannan,LI Zhicheng. Five proof methods for the Sherman-Morrison formula[J]. Pure Mathematics,2024,14(1):34-40. DOI: 10.12677/PM.2024.141005

施引文献(11)

期刊类型引用(11)

1.	王宝贵. 水力压冲一体化增透抽采瓦斯技术. 工矿自动化. 2024(01): 35-41 . 本站查看
2.	王安红. 低透气性煤层点式酸化压裂增透技术研究与应用. 能源与节能. 2024(07): 21-23+30 . 百度学术
3.	骆家宁，谢雄刚，杨家向，熊欣标，梁海彬，曹文梁. 煤巷条带超高压水力割缝增透试验. 湖南科技大学学报(自然科学版). 2023(01): 19-24 . 百度学术
4.	李晓绅，刘瑞鹏. 含夹矸煤层水力割缝瓦斯抽采技术研究及应用. 工矿自动化. 2023(04): 134-140 . 本站查看
5.	肖家乐，徐家杰，薛鲲. 薛湖煤矿矿井充水主控因素与矿井涌水量预测研究. 能源与环保. 2022(08): 308-314 . 百度学术
6.	张晓伟. 斜沟煤矿超高压水力割缝卸压增透最优参数研究. 煤炭与化工. 2022(09): 105-109 . 百度学术
7.	李川，吕英华，梁文勖. 超高压水力割缝卸压增透最优参数研究. 煤炭工程. 2022(S1): 111-115 . 百度学术
8.	贾男. 低透气性煤层多组分酸化压裂增透技术研究. 矿业安全与环保. 2021(03): 27-32 . 百度学术
9.	赵红星，贾男. 低透气性煤层点式酸化压裂增透技术研究与应用. 中国安全生产科学技术. 2021(09): 66-71 . 百度学术
10.	李文福，王向阳，付航航，康甲甲，何伟，马涛，李刚. 低渗煤层超高压水射流不同割缝间距的力学特征. 陕西煤炭. 2021(06): 39-43 . 百度学术
11.	高亚斌，韩培壮，郭晓亚，向鑫，王飞. 钻孔水射流冲击对瓦斯抽采的影响特性研究. 工矿自动化. 2020(10): 19-25 . 本站查看