| Citation: |
YANG Hailong，YUAN Yiping，FAN Panpan，et al. Foreign object recognition for mine conveyor belt iron separators based on transfer learning with EfficientNet[J]. Coal Science and Technology，2025，53（S1）：443−453. DOI: 10.12438/cst.2024-0772
|
In mining operations, metal objects such as anchor bolts, anchor cables, excavator teeth, and pallets often get mixed into the raw coal conveyor belts. These foreign objects must be removed by iron separators to prevent collisions or punctures that could disrupt the normal operation of the conveyor belts. A foreign object recognition method suitable for low illumination and dust-fog environments is proposed for iron separators, which often encountered in mining belt conveyors. First, abnormal and normal images from iron separators on open-pit coal mine conveyor belts were collected. Contrast Limited Adaptive Histogram Equalization was applied to pre-process low-illumination images, enhancing image contrast and clarity. To simulate real dust-fog conditions, a random fogging method was employed, improving the model's generalization ability. Then, using the transfer learning based EfficientNet-B2 network, incorporating multiple mobile inverted bottleneck convolutional modules into the network architecture. This allowed for the stacking and analysis of feature maps at different levels, extracting deep feature signals from the images. The high-dimensional feature maps were reduced to low-dimensional vectors through global average pooling, and the final image classifications—qualified or abnormal—were output through a fully connected layer. The experimental dataset comprises 3 000 images of iron separators collected from an open-pit coal mine and 600 fogged images. The proposed foreign object monitoring algorithm was applied to monitor the iron separators on the conveyor belts of an open-pit coal mine. Comparative experiments were conducted, and results show that the proposed model achieves faster stable iterations and lower loss values, outperforming other existing convolutional neural network models across various performance metrics. Specifically, it achieved an accuracy of 99.79%, precision of 99.07%, recall of 99.01%, and F1-Score of 0.990 4. These results indicate that the model can accurately and effectively classify the adsorption states of iron separators.
| [1] |
吴群英,蒋林,王国法,等. 智慧矿山顶层架构设计及其关键技术[J]. 煤炭科学技术,2020,48(7):80−91.
WU Qunying,JIANG Lin,WANG Guofa,et al. Top-level architecture design and key technologies of smart mine[J]. Coal Science and Technology,2020,48(7):80−91.
|
| [2] |
ZHANG K X,KANG L,CHEN X X,et al. A review of intelligent unmanned mining current situation and development trend[J]. Energies,2022,15(2):513. doi: 10.3390/en15020513
|
| [3] |
鞠晨. 煤矿井下自动电磁除铁技术研究[J]. 煤炭科学技术,2019,47(S2):147−151.
JU Chen. Research on automatic electromagnetic iron remove technology in coal mine[J]. Coal Science and Technology,2019,47(S2):147−151.
|
| [4] |
DA ROCHA R B,REIS É L,RIBEIRO J P. Wet high-intensity magnetic separators (WHIMS) for recovering iron from tailings deposited in dams[J]. Mineral Processing and Extractive Metallurgy Review,2021,42(1):17−23. doi: 10.1080/08827508.2019.1672061
|
| [5] |
杜雨馨,张贺,王树臣,等. 综掘系统视觉处理技术研究现状及发展趋势[J]. 工矿自动化,2023,49(11):22−38,75.
DU Yuxin,ZHANG He,WANG Shuchen,et al. Research status and development trend of visual processing technology for fully mechanized excavation systems[J]. Journal of Mine Automation,2023,49(11):22−38,75.
|
| [6] |
赵端,李涛,董彦强,等. 基于边缘智能的煤矿外因火灾感知方法[J]. 工矿自动化,2022,48(12):108−115.
ZHAO Duan,LI Tao,DONG Yanqiang,et al. Coal mine external fire detection method based on edge intelligence[J]. Journal of Mine Automation,2022,48(12):108−115.
|
| [7] |
EBRAHIMI M,ABDOLSHAH M,ABDOLSHAH S. Developing a computer vision method based on AHP and feature ranking for ores type detection[J]. Applied Soft Computing,2016,49:179−188. doi: 10.1016/j.asoc.2016.08.027
|
| [8] |
XU J K,WANG E Y,ZHOU R. Real-time measuring and warning of surrounding rock dynamic deformation and failure in deep roadway based on machine vision method[J]. Measurement,2020,149:107028. doi: 10.1016/j.measurement.2019.107028
|
| [9] |
ZHANG Z L,LIU Y,HU Q,et al. Multi-information online detection of coal quality based on machine vision[J]. Powder Technology,2020,374:250−262. doi: 10.1016/j.powtec.2020.07.040
|
| [10] |
YAN P C,SUN Q S,YIN N N,et al. Detection of coal and gangue based on improved YOLOv5.1 which embedded scSE module[J]. Measurement,2022,188:110530. doi: 10.1016/j.measurement.2021.110530
|
| [11] |
胡长斌. 基于视频数据的托辊异常检测研究[D]. 西安:西安科技大学,2021.
Research on Abnormal Detection of Roller Based on Video Data[D]. Xi’an:Xi’an University of Science and Technology,2021.
|
| [12] |
SUN S Y,MA H W,WANG K D,et al. Research on the detection method of coal mine roadway bolt mesh based on improved YOLOv7[J]. Electronics,2023,12(14):3050. doi: 10.3390/electronics12143050
|
| [13] |
ZHANG M C,JIANG K,CAO Y S,et al. A deep learning-based method for deviation status detection in intelligent conveyor belt system[J]. Journal of Cleaner Production,2022,363:132575. doi: 10.1016/j.jclepro.2022.132575
|
| [14] |
樊红卫,刘金鹏,曹现刚,等. 低照度尘雾下煤、异物及输送带早期损伤多尺度目标智能检测方法[J]. 煤炭学报,2024,49(S2):1259−1270.
Multi-scale target intelligent detection method for coal,foreign object and early damage of conveyor belt surface under low illumination and dust fog[J]. Journal of China Coal Society,2024,49(S2):1259−1270.
|
| [15] |
KU J G,WANG K P,WANG Q,et al. Application of magnetic separation technology in resource utilization and environmental treatment[J]. Separations,2024,11(5):130. doi: 10.3390/separations11050130
|
| [16] |
MANJU R A,KOSHY G,SIMON P. Improved method for enhancing dark images based on CLAHE and morphological reconstruction[J]. Procedia Computer Science,2019,165:391−398. doi: 10.1016/j.procs.2020.01.033
|
| [17] |
ZHANG Y F,DING L,SHARMA G. HazeRD:An outdoor scene dataset and benchmark for single image dehazing[C]//2017 IEEE International Conference on Image Processing (ICIP). Piscataway,NJ:IEEE,2017:3205−3209.
|
| [18] |
李郁峰,陈念年,张佳成. 一种快速高灵敏度聚焦评价函数[J]. 计算机应用研究,2010,27(4):1534−1536.
LI Yufeng,CHEN Niannian,ZHANG Jiacheng. Fast and high sensitivity focusing evaluation function[J]. Application Research of Computers,2010,27(4):1534−1536.
|
| [19] |
TAN M X,LE Q V. EfficientNet:Rethinking model scaling for convolutional neural networks[EB/OL]. 2019:1905.11946. https://arxiv.org/abs/1905.11946v5.
|
| [20] |
HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2018:7132−7141.
|
| [21] |
RUSSAKOVSKY O,DENG J,SU H,et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision,2015,115(3):211−252. doi: 10.1007/s11263-015-0816-y
|
| [22] |
HE K M,ZHANG X Y,REN S Q,et al. Delving deep into rectifiers:Surpassing human-level performance on ImageNet classification[C]//2015 IEEE International Conference on Computer Vision (ICCV). Piscataway,NJ:IEEE,2015:1026−1034.
|
| [23] |
ATILA Ü,UÇAR M,AKYOL K,et al. Plant leaf disease classification using EfficientNet deep learning model[J]. Ecological Informatics,2021,61:101182. doi: 10.1016/j.ecoinf.2020.101182
|
| [24] |
YIN L F,HONG P J,ZHENG G H,et al. A novel image recognition method based on DenseNet and DPRN[J]. Applied Sciences,2022,12(9):4232. doi: 10.3390/app12094232
|
| [25] |
RADOSAVOVIC I,KOSARAJU R P,GIRSHICK R,et al. Designing network design spaces[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE,2020:10428−10436.
|
| [1] | XUE Guanghui, ZHANG Zhenghao, ZHANG Guiyi, LI Ruixue. Improvement of point cloud feature extraction and alignment algorithms and lidar slam in coal mine underground[J]. COAL SCIENCE AND TECHNOLOGY, 2025, 53(5): 301-312. DOI: 10.12438/cst.2024-0296 |
| [2] | LI Heping, HONG Shaoqiu, CHENG Jian, AN Ning, ZHAO Hailong, XIU Haixin. Coalmine image matching by fusing multi-level feature enhancement and weighted grid statistics[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(11): 129-140. DOI: 10.12438/cst.2024-1224 |
| [3] | LI Deyong, WANG Guofa, GUO Yongcun, WANG Shuang, YANG Yuhao. Image recognition method of coal gangue in complex working conditions based on CES-YOLO algorithm[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(6): 226-237. DOI: 10.12438/cst.2023-1967 |
| [4] | ZHANG Xuhui, CHEN Xin, YANG WenJuan, LEI Mengyu, TIAN Chenhui, YANG Junhao. Research on visual positioning method of digging and anchoring equipment based on single laser beam information[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(1): 311-322. DOI: 10.12438/cst.2023-1674 |
| [5] | TIAN Zijian, WU Jiaqi, ZHANG Wenqi, CHEN Wei, ZHOU Tao, YANG Wei, WANG Shuai. An illuminance improvement and details enhancement method on coal mine low-light images based on Transformer and adaptive feature fusion[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(1): 297-310. DOI: 10.13199/j.cnki.cst.2023-0112 |
| [6] | YAN Zhirui, WANG Hongwei, GENG Yide. Coal-rock interface image recognition method based on improved DeeplabV3+ and transfer learning[J]. COAL SCIENCE AND TECHNOLOGY, 2023, 51(S1): 429-439. DOI: 10.13199/j.cnki.cst.2022-1392 |
| [7] | SONG Mingzhi, QIAN Jiansheng, HU Qingsong. Location fingerprint positioning of underground WLAN based on AKPCA algorithm[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(3): 248-256. |
| [8] | TANG Fuquan LI Linkuan LI Xiaotao LIU Shiwei, . Research on characteristics of mining-induced surface cracks based on UAV images[J]. COAL SCIENCE AND TECHNOLOGY, 2020, 48(10). |
| [9] | CHENG Tiedong, WU Yiwen, DAI Congcong, LUO Xiaoyan, YAN Lirong, ZHAO Kui, SHAO Fan. Study on method of acoustic emission signal denoising and feature extraction in whole process of rock failure[J]. COAL SCIENCE AND TECHNOLOGY, 2019, (12). |
| [10] | WEN Min-min SONG Jian-cheng SONG Yuan LIU Yuan WAN Zhi-qiang, . Design on Fault Pre-Warning System Applied for Mine Flameproof Type Dry Transformer[J]. COAL SCIENCE AND TECHNOLOGY, 2014, (5). |
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: