Intelligent monitoring method for conveyor belt misalignment based on deep learning
-
摘要:
针对现有输送带跑偏状态监测方法实用性、鲁棒性不足及数据集制作难度大的问题，提出了一种基于深度学习的输送带跑偏状态智能监测方法。将输送带边缘识别问题看作特定场景下的直线检测问题，提出以目标检测网络预测框的对角线表征输送带边缘直线的检测策略，以预测框的右上−左下对角线表征输送带左边缘，以左上−右下对角线表征输送带右边缘；通过YOLOv5模型对输送带边缘进行检测，并设计了跑偏量计算方法和跑偏状态判定规则。实验结果表明，利用目标检测网络预测框的对角线特征可稳定高效地实现输送带边缘识别和跑偏量量化，简化了图像数据处理流程和数据标注，具有较强的泛化能力和快速迁移学习能力；结合直线检测策略的YOLOv5模型对料流边界、支柱等其他直线的抗干扰能力强，在CUMT−BELT数据集上的检测精度达99%以上，检测速度最快达148帧/s，实时性好。
Abstract:Existing methods for monitoring conveyor belt misalignment face challenges in terms of practicality, robustness, and the difficulty of dataset creation. This paper proposed an intelligent monitoring method for conveyor belt misalignment based on deep learning. First, the conveyor belt edge recognition problem was treated as a line detection issue in a specific scenario. A strategy was proposed to detect the straight lines of the conveyor belt edges using the diagonal features of the bounding box predicted by the object detection network. Specifically, the top-right to bottom-left diagonal of the predicted bounding box was used to represent the left edge of the conveyor belt, and the top-left to bottom-right diagonal was used to represent the right edge. The YOLOv5 model was employed to detect the conveyor belt edges, and a misalignment calculation method and misalignment state determination rules were developed. Experimental results demonstrated that the diagonal features of the predicted bounding box could stably and efficiently achieve conveyor belt edge recognition and misalignment quantification, thereby simplifying image data processing and annotation tasks. The method exhibited strong generalization ability and rapid transfer learning capability. The YOLOv5 model, combined with the line detection strategy, showed excellent anti-interference performance for detecting material flow boundaries, support pillars, and other straight lines. On the CUMT-BELT dataset, the detection accuracy exceeded 99%, with a maximum detection speed of 148 frames per second, ensuring excellent real-time performance.
-
Keywords:
- belt conveyor /
- misalignment monitoring /
- line detection /
- conveyor belt edge recognition /
- deep learning /
- YOLOv5
-
-
![]()
图 2 对角线特征与输送带边缘直线耦合表征策略
Figure 2. Diagonal features and conveyor belt edge straight lines representation strategy
![]()
图 6 YOLOv5s对输送带边缘的检测效果
Figure 6. Detection performance of YOLOv5s on conveyor belt edges
![]()
图 7 DHT算法对输送带边缘的检测效果
Figure 7. Detection performance of DHT algorithm on conveyor belt edges
![]()
图 8 输送带跑偏数值计算和状态判定结果
Figure 8. Misalignment calculation and state determination results for conveyor belt
![]()
图 9 相机对中安装过程及检测结果
Figure 9. Camera alignment installation process and detection results
-
[1] 陈云,吴敬兵,叶涛. 基于目标检测的输送带损伤检测方法[J]. 自动化与仪表,2020,37(6):64-69. CHEN Yun,WU Jingbing,YE Tao. Conveyor belt damage detection method based on object detection[J]. Automation & Instrumentation,2020,37(6):64-69.
[2] 周坪,马国庆,周公博,等. 智能化带式输送机健康监测技术研究综述[J]. 仪器仪表学报,2023,44(12):1-21. ZHOU Ping,MA Guoqing,ZHOU Gongbo,et al. Health monitoring technology for the intelligent belt conveyor:a review[J]. Chinese Journal of Scientific Instrument,2023,44(12):1-21.
[3] 袁敦鹏. 基于三维点云的带式输送机跑偏及堆煤监测技术研究[D]. 徐州:中国矿业大学,2022. YUAN Dunpeng. Study on the belt conveyor deviation and coal stacking monitoring based on three-dimensional point cloud[D]. Xuzhou:China University of Mine and Technology,2022.
[4] 谭恒,张红娟,靳宝全,等. 基于机器视觉的煤矿带式输送机跑偏检测方法[J]. 煤炭技术,2021,40(5):152-156. TAN Heng,ZHANG Hongjuan,JIN Baoquan,et al. Method for detecting deviation of coal mine belt conveyor based on machine vision[J]. Coal Technology,2021,40(5):152-156.
[5] 王平. 基于数字图像处理的输送带跑偏状态实时监测技术[J]. 煤矿机械,2021,42(2):168-170. WANG Ping. Real-time monitoring technology of conveyor belt deviation state based on digital image processing[J]. Coal Mine Machinery,2021,42(2):168-170.
[6] 王星,白尚旺,潘理虎,等. 基于计算机视觉的带式输送机跑偏监测[J]. 煤矿安全,2017,48(5):130-133. WANG Xing,BAI Shangwang,PAN Lihu,et al. Deviation monitoring of belt conveyor based on computer vision[J]. Safety in Coal Mines,2017,48(5):130-133.
[7] 董征,张旭辉,王泰华,等. 基于机器视觉的矿用带式输送机跑偏故障检测系统[J]. 智能矿山,2022,3(2):60-65. DONG Zheng,ZHANG Xuhui,WANG Taihua,et al. Fault detection system of mine belt conveyor deviation based on machine vision[J]. Journal of Intelligent Mine,2022,3(2):60-65.
[8] ZHANG Mengchao,SHI Hao,YU Yan,et al. A computer vision based conveyor deviation detection system[J]. Applied Sciences,2020,10(7). DOI:10.3390/ app10072402.
[9] 韩涛,黄友锐,张立志,等. 基于图像识别的带式输送机输煤量和跑偏检测方法[J]. 工矿自动化,2020,46(4):17-22. HAN Tao,HUANG Yourui,ZHANG Lizhi,et al. Detection method of coal quantity and deviation of belt conveyor based on image recognition[J]. Industry and Mine Automation,2020,46(4):17-22.
[10] ZENG Chan,ZHENG Junfeng,LI Jiangyun. Real-time conveyor belt deviation detection algorithm based on multi-scale feature fusion network[J]. Algorithms,2019,12(10). DOI: 10.3390/a12100205.
[11] 聂志勇,官锋,穆杞梓. 基于图像分割的皮带跑偏故障分级报警方法研究[J]. 中国设备工程,2023(24):271-274. DOI: 10.3969/j.issn.1671-0711.2023.24.110 NIE Zhiyong,GUAN Feng,MU Qizi. Research on grading alarm method of belt deviation fault based on image segmentation[J]. China Plant Engineering,2023(24):271-274. DOI: 10.3969/j.issn.1671-0711.2023.24.110
[12] 曾飞,陶玉衡,苏俊彬,等. 融合ResNet18和Deconvolution的输送带横向跑偏检测方法[J]. 现代制造工程,2023(8):121-126. ZENG Fei,TAO Yuheng,SU Junbin,et al. Detection method of conveyor belt lateral deviation by integrating ResNet18 and Deconvolution[J]. Modern Manufacturing Engineering,2023(8):121-126.
[13] LIU Yi,MIAO Changyun,LI Xianguo,et al. Research on deviation detection of belt conveyor based on inspection robot and deep learning[J]. Complexity,2021,2021(1). DOI: 10.1155/2021/3734560.
[14] WANG Jingbo,LIU Qing,DAI Mengting. Belt vision localization algorithm based on machine vision and belt conveyor deviation detection[C]. 34th Youth Academic Annual Conference of Chinese Association of Automation,Jinzhou,2019:269-273.
[15] AGGARWAL N,KARL W C. Line detection in images through regularized Hough transform[J]. IEEE Transactions on Image Processing,2006,15(3):582-591. DOI: 10.1109/TIP.2005.863021
[16] XU Yifan,XU Weijian,CHEUNG D,et al. Line segment detection using transformers without edges[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition,Nashville,2021:4257-4266.
[17] HUANG Siyu,QIN Fangbo,XIONG Pengfei,et al. TP-LSD:tri-points based line segment detector[EB/OL]. [2024-02-20]. https://arxiv.org/abs/2009.05505?context=cs.CV.
[18] ZHU Xingkui,LYU Shuchang,WANG Xu,et al. TPH-YOLOv5:improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]. IEEE/CVF International Conference on Computer Vision Workshops,Montreal,2021:2778-2788.
[19] LIU Wei,ANGUELOV D,ERHAN D,et al. SSD:single shot multibox detector[C]. European Conference on Computer Vision,Amsterdam,2016:21-37.
[20] CARION N,MASSA F,SYNNAEVE G,et al. End-to-end object detection with transformers[C]. European Conference on Computer Vision,Munich,2020:213-229.
[21] 程德强,陈杰,寇旗旗,等. 融合层次特征和注意力机制的轻量化矿井图像超分辨率重建方法[J]. 仪器仪表学报,2022,43(8):73-84. CHENG Deqiang,CHEN Jie,KOU Qiqi,et al. Lightweight super-resolution reconstruction method based on hierarchical features fusion and attention mechanism for mine image[J]. Chinese Journal of Scientific Instrument,2022,43(8):73-84.
-
期刊类型引用(6)
1. 李黎黎，李合菊. 基于大数据的采煤机运行状态监测与评估. 煤矿机械. 2025(03): 208-211 . 
百度学术
2. 侯京平. 薄煤层综采工作面智能化控制系统的设计及应用分析. 当代化工研究. 2024(22): 129-131 . 百度学术
3. 邵明育，赵兖锋，梁汝光. 基于RBF预测的采煤机电气运行数据获取系统设计. 电气技术与经济. 2024(12): 384-386+390 . 百度学术
4. 李翠平，陈永松. 大数据分析技术下给煤机运行中的异常分析与处理. 科学技术创新. 2023(13): 9-12 . 百度学术
5. 薛军. 基于循环神经网络的采煤机状态预测方法. 煤炭技术. 2023(09): 252-254 . 百度学术
6. 赵晓璐. 采煤机运行状态监控系统设计及应用分析. 西部探矿工程. 2023(12): 162-164 . 百度学术
其他类型引用(0)
下载:
计量
- 文章访问数: 94
- HTML全文浏览量: 25
- PDF下载量: 18
- 被引次数: 6
