GAO Han，ZHAO Peipei，YU Zheng，et al. Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer[J]. Coal Science and Technology，2024，52（7）：199−208
. DOI: 10.12438/cst.2023-1336| Citation: |
GAO Han，ZHAO Peipei，YU Zheng，et al. Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer[J]. Coal Science and Technology，2024，52（7）：199−208 . DOI: 10.12438/cst.2023-1336
|
Conveyor belt is one of the most important transportation equipment in underground coal mines. Anchor rod, channel steel, large gangue, and other foreign objects that are mixed with the conveyor belt during conveying operations cause the belt to tear, clog the coal drop opening, and cause other serious safety incidents. They seriously affect the efficiency of transportation and even threaten the lives of workers. Aiming at the existing conveyor belt foreign object detection algorithm’s problems such as weak characterization of slender objects and poor weak semantic feature extraction, a foreign object detection algorithm based on low-level feature enhancement with Transformer is designed, notated as FET–YOLO. Firstly, to address the problem that existing detection networks have difficulty in extracting features of elongated objects, deformable convolution is introduced to enhance the network’s adaptability to the shape characteristics of elongated foreign objects, and the MobileViT module is used to increase the differentiation between the foreign objects and the background in the image, in order to extract features that are more consistent with the diversity of the elongated foreign objects and to weaken the interference of background noise.Secondly, constructing a low-level feature enhancement module LFEM, to improve the representation of weak semantic features of foreign objects in the detection network in order to reduce the probability of wrong detection.Finally, the introduction of gsconv reduces the information loss due to changes in the size of the feature map and ensures that the network extracts features efficiently while reducing the number of model parameters. The training set and validation set are produced by using the video of conveyor belt work in an underground coal mine. The proposed algorithm is compared to three other conveyor belt detection algorithms, and the experimental results show that the proposed algorithm can better solve the problems of poor detection of elongated objects and difficulty in weak semantic feature extraction in conveyor belt foreign object target detection, with higher detection accuracy. For images with a resolution size of 640×640, the performance metrics mAP@0.5 can be up to 0.875, mAP@0.5:0.95 can be up to 0.543, and the detection speed is 75 fps.
| [1] |
中矿煤炭产业景气指数研究课题组,吴吟. 2022–2023年中国煤炭产业经济形势研究报告[J]. 中国煤炭,2023,49(3):2–10.
China Mining Coal Industry Prosperity Index RESEARCH Group,WU Yin. Research report on the economic situation of China's coal industry in,2022–2023[J]. China Coal,2023,49(3):2–10.
|
| [2] |
程德强,徐进洋,寇旗旗,等. 融合残差信息轻量级网络的运煤皮带异物分类[J]. 煤炭学报,2022,47(3):1361−1369.
CHENG D Q,XU J Y,KOU Q Q,et al. Lightweight network for coal belt foreign object classification with fusion of residual information[J]. Journal of Coal,2022,47(3):1361−1369.
|
| [3] |
刘富强,钱建生,王新红,等. 基于图像处理与识别技术的煤矿矸石自动分选[J]. 煤炭学报,2000,45(5):534−537. doi: 10.3321/j.issn:0253-9993.2000.05.020
LIU Fuqiang,QIAN Jiansheng,WANG Xinhong,et al. Automatic sorting of coal mine gangue based on image processing and recognition technology[J]. Journal of Coal,2000,45(5):534−537. doi: 10.3321/j.issn:0253-9993.2000.05.020
|
| [4] |
程健,王东伟,杨凌凯,等. 一种改进的高斯混合模型煤矸石视频检测方法[J]. 中南大学学报(自然科学版),2018,49(1):118−123. doi: 10.11817/j.issn.1672-7207.2018.01.016
CHENG J,WANG D W,YANG L K,et al. An improved video detection method for coal gangue with Gaussian mixture model[J]. Journal of Central South University(Natural Science Edition),2018,49(1):118−123. doi: 10.11817/j.issn.1672-7207.2018.01.016
|
| [5] |
余乐. 一种煤和煤矸石图像识别的新方法[J]. 现代计算机(专业版),2017(17):66−70.
YU Le. A new method for image recognition of coal and coal gangue[J]. Modern Computer(Professional Edition),2017(17):66−70.
|
| [6] |
李明,鹿朋,朱美强,等. 基于改进YOLO-tiny的闸板阀开度检测[J]. 煤炭学报,2021,46(S2):1180−1190.
LI M,LU P,ZHU M Q,et al. Gate valve opening detection based on improved YOLO-tiny[J]. Journal of Coal,2021,46(S2):1180−90.
|
| [7] |
赵永强,饶元,董世鹏,等. 深度学习目标检测方法综述[J]. 中国图象图形学报,2020,25(4):629−54. doi: 10.11834/jig.190307
|
| [8] |
He K, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. Ieee Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397.
|
| [9] |
REN S,HE K,GIRSHICK R,et al. Faster R–CNN:Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Trans Pattern Anal Mach Intell,2017,39(6):1137−1149. doi: 10.1109/TPAMI.2016.2577031
|
| [10] |
吕志强. 复杂环境下煤矿皮带运输异物图像识别研究 [D]. 徐州:中国矿业大学,2020.
LV Zhiqiang. Research on foreign body image recognition in coal mine belt transportation under complex environment [D]. Xuzhou: China University of Mining and Technology,2020.
|
| [11] |
吴守鹏,丁恩杰,俞啸. 基于改进FPN的输送带异物识别方法[J]. 煤矿安全,2019,50(12):127−30.
WU Shoupeng,DING Enjie,YU Xiao. Foreign body identification method in conveyor belt based on improved FPN[J]. Safety in Coal Mines,2019,50(12):127−30.
|
| [12] |
LIU W,ANGUELOV D,ERHAN D,et al. SSD:Single Shot MultiBox Detector[C]// proceedings of the 14th European Conference on Computer Vision(ECCV). Amsterdam,NETHERLANDS,2016:21–37.
|
| [13] |
REDMON J,FARHADI A J A E–P. YOLOv3:An Incremental Improvement [J]. Arxiv,2018.
|
| [14] |
BOCHKOVSKIY A,WANG C–Y,MARK LIAO H–Y. YOLOv4:Optimal Speed and Accuracy of Object Detection [J]. Arxiv,2020.
|
| [15] |
Redmon J, Farhadi A, Ieee. YOLO9000: Better, Faster, Stronger[C]. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6517-6525.
|
| [16] |
CHEN Y,SUN X,XU L,et al. Application of YOLOv4 Algorithm for Foreign Object Detection on a Belt Conveyor in a Low-Illumination Environment[J]. SENSORS,2022,22(18):6851. doi: 10.3390/s22186851
|
| [17] |
来文豪,周孟然,王锦国,等. 多光谱波段筛选的煤矸石快速定位[J]. 中国激光,2021,48(16):190–200.
LAI W H,ZHOU M R,WANG J G,et al. Rapid localization of coal gangue by multispectral waveband screening[J]. China Laser,2021,48(16):190–200.
|
| [18] |
ZHANG M C,CAO Y S,JIANG K,et al. Proactive measures to prevent conveyor belt Failures:Deep Learning-based faster foreign object detection[J]. Engineering Failure Analysis,2022,141:14.
|
| [19] |
XIAO D,LIU P P,WANG J C,et al. Mining belt foreign body detection method based on YOLOv4_GECA model [J]. Scientific Reports,2023,13(1).
|
| [20] |
ZHU X,HU H,LIN S,et al. Deformable ConvNets v2:MORE Deformable,Better Results [C]//,2019 IEEE/CVF conference on computer vision and pattern recognition(CVPR 2019). Shanghai,2019:9300–9308.
|
| [21] |
Li H, Li J, Wei H, et al. Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles[J]. arXiv preprint arXiv: 2206.02424, 2022.
|
| [22] |
Mehta S , Rastegari M. MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer[J]. arXiv preprint arXiv: 2110.02178, 2021.
|
| [23] |
Han K, Wang Y, Tian Q, et al. GhostNet: More Features from Cheap Operations[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [C]. Seattle. IEEE,2020:1577–1586.
|
| [24] |
YAN P,SUN Q,YIN N,et al. Detection of coal and gangue based on improved YOLOv5.1 which embedded scSE module* [J]. MEASUREMENT,2022,188.
|
| [25] |
桂方俊,李尧. 基于CBA–YOLO模型的煤矸石检测[J]. 工矿自动化,2022,48(6):128−33.
GUI Fangjun,LI Yao. Coal gangue detection based on CBA–YOLO model[J]. Automation of Industry and Mine,2022,48(6):128−33.
|
| [26] |
许鹏. 基于边缘计算的煤矿井下皮带异物检测关键技术研究 [D]. 徐州:中国矿业大学,2021.
XU P. Research on key technology of detecting foreign matter in coal mine belt based on edge computing [D]. Xuzhou:China University of Mining and Technology,2021.
|
| [27] |
GE Z,LIU S,WANG F,et al. YOLOX:Exceeding YOLO Series in,2021 [J]. Arxiv,2021.
|
| [28] |
CARION N,MASSA F,SYNNAEVE G,et al. End-to-End Object Detection with Transformers [J],Arxiv 2020.
|
| [1] | ZHANG Fan, ZHANG Jiarong, CHENG Haixing. Research review on intelligent object detection technology for coal mines based on deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2025, 53(S1): 284-296. DOI: 10.12438/cst.2024-0428 |
| [2] | ZHANG Fukai, SUN Yiran, WU Xufeng, LI Aijun, LI Peiyang, WANG Dengke, YUAN Guan, ZHAO Shan, ZHANG Haiyan. Real time counting method for coal mine drill pipes based on deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2025, 53(6): 493-504. DOI: 10.12438/cst.2024-0366 |
| [3] | ZHOU Yunzhuo, XU Zijing, BI Lin. The recognition of dust emission from open-pit mining roads based on cascaded convolutional networks by deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(S2): 312-320. DOI: 10.12438/cst.2023-1476 |
| [4] | WU Ligang, CHEN Le, LYU Yuanyuan, ZHANG Zhe. A lightweight-based method for real-time monitoring of lump coal on conveyor belts[J]. COAL SCIENCE AND TECHNOLOGY, 2023, 51(S2): 285-293. DOI: 10.12438/cst.2023-1217 |
| [5] | WANG Anmin, GAO Yuchao, ZOU Junchao, ZHAO Zeyuan, CAO Daiyong. Quantitative characterization of pore structure in coal measure shales based on deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2023, 51(S2): 183-190. DOI: 10.13199/j.cnki.cst.2022-1597 |
| [6] | GAO Yasong, ZHANG Buqin, LANG Liying. Coal and gangue recognition technology and implementation based on deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2021, 49(12): 202-208. |
| [7] | Shunling, JING Ying, LU Caiwu, GU Qinghua, ZHANG Xuefei. Study on recognition technology of truck loading condition in open-pitmine based on deep convolutional features[J]. COAL SCIENCE AND TECHNOLOGY, 2021, 49(10): 167-176. |
| [8] | ZHANG Zelin, ZHANG Zhiwei, HU Qi, WANG Li. Study on multi-product coal image classification method based on deep learning[J]. COAL SCIENCE AND TECHNOLOGY, 2021, 49(9): 117-123. |
| [9] | Li Xianguo Ming Zixu Miao Di Shen Lifang Zhang Can Jiang Hangqi, . Design on monitoring and control system of conveyor belt longitudinal tearing based on line laser and ARM[J]. COAL SCIENCE AND TECHNOLOGY, 2017, (2). |
| [10] | Study on Longitudinal Tearing Detection System of Conveyor Belt Based on ARM9[J]. COAL SCIENCE AND TECHNOLOGY, 2011, (12). |
| 1. |
李胜利. 网络并行高密度电法实测煤层“上三带”覆岩变形特征. 能源科技. 2025(03)
| |
| 2. |
徐东晶，窦旋，李业，夏志村. 山东矿区矿井导水裂隙带发育高度预测模型研究. 矿业科学学报. 2025(01): 86-94 .
| |
| 3. |
张胜军，丁亚恒，姜春露，李江. 深埋大采长工作面导水裂隙带发育高度研究. 中国矿业. 2025(05): 198-205 .
| |
| 4. |
李建文，赵文，吴振坤，徐小兵，王庆涛，段隆臣. 煤矿采空区覆岩“三带”智能识别方法. 煤田地质与勘探. 2024(04): 164-171 .
| |
| 5. |
王毅，周余，张丁丁，王禹，杨珍，王伟. 综采工作面采动覆岩导水裂隙带发育高度综合研究. 矿业安全与环保. 2024(05): 132-141 .
| |
| 6. |
刘奇，梁智昊，訾建潇. SMOGN过采样下导水裂隙带高度的MPSO-BP预测模型. 煤田地质与勘探. 2024(11): 72-85 .
| |
| 7. |
郭瑞瑞，靳志龙. 神东矿区浅埋煤层覆岩运移与导水裂缝带发育规律研究. 中国煤炭. 2022(S1): 224-234 .
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: