LiDAR-based edge extraction method for underground belt conveyors
-
摘要: 带式输送机是煤矿井下非结构化胶带巷中巡检机器人的巡检对象之一，且其边缘提取可使机器人获取自身相对检测目标的空间位姿，为执行巡检任务提供环境信息支持。目前井下大多采用基于视觉的边缘提取技术，难以有效克服照度低、粉尘大、水雾浓等问题。针对该问题，采用防爆16线激光雷达作为巡检机器人传感器获取巷道点云，以降低环境对提取结果的影响。对获取的原始稀疏点云进行统计离群值移除和直通滤波预处理，以去除噪声和无用点云，采用随机样本一致算法分割带式输送机点云平面，基于投影−四叉树方法提取带式输送机边缘点云。rviz+Gazebo联合仿真结果表明：在机器人不同运动工况下，带式输送机边缘提取的准确率不低于96.33%；雷达遮蔽率低于30%时准确率不低于79.23%。实验室测试结果表明：带式输送机表面水层分布比例为100%且厚度饱和条件下，边缘提取准确率不低于88%，整体优于基于经纬的极值检索法、基于KDTree/OcTree的曲率阈值法、基于KDTree/OcTree的临近点夹角阈值法，且平均计算耗时仅为36 ms，满足井下实时巡检需求。Abstract: The belt conveyor is one of the inspection targets of the inspection robot in the unstructured belt roadway of underground coal mines. Extracting its edges allows the robot to obtain its spatial pose relative to the inspection target, providing environmental information to support the execution of inspection tasks. Currently, most underground edge extraction techniques are vision-based, which struggle to overcome challenges such as low illumination, heavy dust, and dense fog. To address this issue, an explosion-proof 16-line LiDAR was used as the sensor for the inspection robot to acquire the roadway point cloud, reducing the environmental impact on the extraction results. The raw sparse point cloud was preprocessed using statistical outlier removal and passthrough filtering to eliminate noise and irrelevant points. The belt conveyor's point cloud plane was segmented using the Random Sample Consensus (RANSAC) algorithm, and the edge point cloud of the belt conveyor was extracted using a projection-quad tree method. The combined rviz and Gazebo simulation results showed that, under different operating conditions of the robot, the accuracy of belt conveyor edge extraction was no less than 96.33%. When the LiDAR shielding rate was below 30%, the accuracy was no less than 79.23%. Laboratory tests showed that, even when the surface of the belt conveyor had a 100% water distribution and saturated thickness, the edge extraction accuracy was no less than 88%. Overall, this method outperforms the latitude and longitude extremum search method, the curvature threshold method based on KDTree/OcTree, and the adjacent point angle threshold method based on KDTree/OcTree, with an average computation time of only 36 ms, meeting the real-time inspection needs of underground environments.
-
Key words:
- unstructured roadway /
- belt roadway /
- inspection robot /
- belt conveyor /
- LiDAR /
- sparse point; edge extraction cloud
-
图 2 不同布置方式下激光雷达获取的巷道点云
Figure 2. Roadway point cloud obtained by LiDAR under different layout
图 5 不同SOR滤波参数下巷道点云规模
Figure 5. Tunnel point cloud size under different filtering parameters of SOR（statistical outlier removal） algorithm
图 9 带式输送机边缘提取结果可视化
Figure 9. Visualization of edge extraction results of belt conveyor
图 10 机器人不同运动工况下边缘提取结果可视化
Figure 10. Visualization of edge extraction results of belt conveyor under different robot motion conditions
图 11 不同雷达遮敝率下带式输送机边缘提取结果可视化
Figure 11. Visualization of edge extraction results of belt conveyor under different radar occlusion rates
图 12 带式输送机边缘提取测试环境
Figure 12. Experimental environment of edge extraction algorithm for belt conveyor
图 13 不同偏航角度下带式输送机边缘提取可视化结果
Figure 13. Visualization of edge extraction results of belt conveyor under different yaw angles
表 1 柠条塔煤矿胶带巷常见物体（要素）点云特征退化分析
Table 1. Feature degradation of point cloud of common objects （elements） in belt conveyor roadway in Ningtiaota Coal Mine
名称 退化程度 退化方向 非退化方向特征间距 定位范围 带式输送机 未退化 无 约1 m（支架、
托辊间距）全局 通风管道 未退化 无 3 m以上（法兰、
承插架间距）全局 线缆 弱退化 巷道轴向 1～5 cm（线缆直径） 无法应用 标志牌、路障 未退化 无 极稀疏（摆放间距） 局部路段定位 喷浆面 完全退化 墙壁面/顶
板面/路面无特征 无法应用 未喷浆面 强退化 墙壁面/顶
板面/路面无显著特征 较难应用 
下载: 导出CSV
表 2 机器人不同运动工况下带式输送机边缘提取仿真结果
Table 2. Edge extraction simulation results of edge extraction of belt conveyor under different robot motion conditions
偏航角度/（°） 不同移动速度下的准确率/% 1 m/s 2 m/s 3 m/s 4 m/s 5 m/s 0 98.13 98.09 97.84 97.68 97.18 7.5 98.01 97.97 97.65 97.32 96.94 15.0 97.91 97.76 97.20 96.81 96.78 30.0 97.71 97.53 96.89 96.56 96.47 60.0 97.45 97.05 96.61 96.36 96.33
下载: 导出CSV
表 3 不同雷达遮蔽率下带式输送机边缘提取仿真结果
Table 3. Simulation results of edge extraction of belt conveyor under different radar occlusion rates
遮蔽率/% 直线夹角/（°） 投影距离/m 0 0 0 5 4.37 0.02 15 7.02 0.04 30 12.89 0.11 50 37.63 0.33
下载: 导出CSV
表 4 不同偏航角度下带式输送机边缘提取测试结果
Table 4. Edge extraction experiment results of belt conveyor under different yaw angle
偏航角度/（°） 直线夹角/（°） 投影距离/m 准确率/% 0 14.57 0.12 77.25 7.5 15.05 0.14 76.93 15.0 16.12 0.14 74.11 30.0 15.92 0.15 75.36 60.0 16.11 0.15 74.97
下载: 导出CSV
表 5 不同水层分布比例下带式输送机边缘提取测试结果
Table 5. Edge extraction experiment results of belt conveyor under different distribution ratios of water layers
% 序号 不同水层分布比例下的准确率 0～24.9% 25.0%～49.9% 50.0%～74.9% 75.0%～99.9% 100% 1 97.95 97.51 97.64 97.29 97.25 2 95.51 95.23 96.85 95.44 94.23 3 91.02 94.17 92.43 90.50 91.59 4 92.28 89.90 91.08 89.82 90.06 5 89.19 89.11 89.12 89.01 89.23
下载: 导出CSV
表 6 不同边缘提取方法测试结果对比
Table 6. Comparison of test results for different edge extraction methods
方法 不同参数下的准确率/% 平均计算
耗时/ms5 m/s移动速度，
60°偏航角30%雷达
遮蔽率100%水层
分布比例极值检索法 97 55 87 51 曲率阈值法 89 80 86 143 临近点夹角阈值法 89 81 88 156 本文方法 96 79 88 36
下载: 导出CSV
-
[1] 王国法,孟令宇. 煤矿智能化及其技术装备发展[J]. 中国煤炭,2023,49(7):1-13.WANG Guofa,MENG Lingyu. Development of coal mine intelligence and its technical equipment[J]. China Coal,2023,49(7):1-13. [2] 任满翊. 无人化智能煤矿建设探索与实践[J]. 工矿自动化,2022,48(增刊1):27-29.REN Manyi. Exploration and practice of unmanned intelligent coal mine construction[J]. Journal of Mine Automation,2022,48(S1):27-29. [3] 董书宁,刘再斌,程建远,等. 煤炭智能开采地质保障技术及展望[J]. 煤田地质与勘探,2021,49(1):21-31.DONG Shuning,LIU Zaibin,CHENG Jianyuan,et al. Technologies and prospect of geological guarantee for intelligent coal mining[J]. Coal Geology & Exploration,2021,49(1):21-31. [4] 王田苗,陶永. 我国工业机器人技术现状与产业化发展战略[J]. 机械工程学报,2014,50(9):1-13. doi: 10.3901/JME.2014.09.001WANG Tianmiao,TAO Yong. Research status and industrialization development strategy of Chinese industrial robot[J]. Journal of Mechanical Engineering,2014,50(9):1-13. doi: 10.3901/JME.2014.09.001 [5] GUO Aijun, WANG Bin, ZHAO Minghui. Application research of belt conveyor monitoring based on laser technology[C]. The 7th Asia-Pacific Conference on Intelligent Robot Systems,Tianjin,2022:140-143. [6] LI Xianguo,SHEN Lifang,MING Zixu,et al. Laser-based on-line machine vision detection for longitudinal rip of conveyor belt[J]. Optik,2018,168:360-369. doi: 10.1016/j.ijleo.2018.04.053 [7] 张克亮. 基于MT−CNN的矿井带式输送机输煤量检测技术[J]. 中国矿业,2024,33(6):137-142.ZHANG Keliang. Coal conveying quantity detection of mine belt conveyor based on MT-CNN[J]. China Mining Magazine,2024,33(6):137-142. [8] 毕东月. 基于深度学习的输煤皮带故障视觉检测方法研究[J]. 中国安全生产科学技术,2021,17(8):84-90.BI Dongyue. Research on visual detection method for fault of coal conveyor belt based on deep learning[J]. Journal of Safety Science and Technology,2021,17(8):84-90. [9] 杨林顺,董志勇. 基于图像处理的输送带跑偏故障在线检测技术研究[J]. 煤炭工程,2020,52(10):116-120.YANG Linshun,DONG Zhiyong. On-line detection of conveyor belt deviation fault based on image processing[J]. Coal Engineering,2020,52(10):116-120. [10] 王锴,曾祥进,黎新,等. 输送带跑偏检测方法研究[J]. 工矿自动化,2023,49(3):23-30,52.WANG Kai,ZENG Xiangjin,LI Xin,et al. Research on conveyor belt deviation detection method[J]. Journal of Mine Automation,2023,49(3):23-30,52. [11] 薛旭升,杨星云,齐广浩,等. 煤矿带式输送机分拣机器人异物识别与定位系统设计[J]. 工矿自动化,2022,48(12):33-41.XUE Xusheng,YANG Xingyun,QI Guanghao,et al. Design of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor[J]. Journal of Mine Automation,2022,48(12):33-41. [12] YU L,LI J,WANG T,et al. T2I-Net:time series classification via deep sequence-to-image transformation networks[C]. 2022 IEEE International Conference on Networking,Sensing and Control,Shanghai,2022:1-5. [13] 李猛钢,胡而已,朱华. 煤矿移动机器人LiDAR/IMU紧耦合SLAM方法[J]. 工矿自动化,2022,48(12):68-78.LI Menggang,HU Eryi,ZHU Hua. LiDAR/IMU tightly-coupled SLAM method for coal mine mobile robot[J]. Journal of Mine Automation,2022,48(12):68-78. [14] 何怡静,杨维. 基于视觉与激光融合的井下灾后救援无人机自主位姿估计[J]. 工矿自动化,2024,50(4):94-102.HE Yijing,YANG Wei. Autonomous pose estimation of underground disaster rescue drones based on visual and laser fusion[J]. Journal of Mine Automation,2024,50(4):94-102. [15] LIN Jiarong,ZHANG Fu. Loam livox:a fast,robust,high-precision LiDAR odometry and mapping package for LiDARs of small FoV[C]. IEEE International Conference on Robotics and Automation,Paris,2020:3126-3131. [16] 荣耀,曹琼,安晓宇,等. 综采工作面三维激光扫描建模关键技术研究[J]. 工矿自动化,2022,48(10):82-87.RONG Yao,CAO Qiong,AN Xiaoyu,et al. Research on key technologies of 3D laser scanning modeling in fully mechanized working face[J]. Journal of Mine Automation,2022,48(10):82-87. [17] TRYBALA P,BLACHOWSKI J,Błażej R,et al. Damage detection based on 3D point cloud data processing from laser scanning of conveyor belt surface[J]. Remote Sensing,2021,13(1). DOI: 10.3390/rs13010055. [18] 陈建华,马宝,王蒙. 基于二次特征提取的煤矿巷道表面点云数据精简方法[J]. 工矿自动化,2023,49(12):114-120.CHEN Jianhua,MA Bao,WANG Meng. A method for simplifying surface point cloud data of coal mine roadways based on secondary feature extraction[J]. Journal of Mine Automation,2023,49(12):114-120. [19] 于淼,张晞,龚子任,等. 基于LiDAR的煤矿井下自动驾驶边界检测与跟踪方法研究[J]. 煤炭工程,2023,55(6):145-151.YU Miao,ZHANG Xi,GONG Ziren,et al. LiDAR-based boundary detection and tracking method for autonomous vehicles in underground coal mines[J]. Coal Engineering,2023,55(6):145-151. [20] HUANG Qiang, PAN Changchun, LIU Haichun. A multi-sensor fusion algorithm for monitoring the health condition of conveyor belt in process industry[C]. The 3rd International Conference on Industrial Artificial Intelligence,Shenyang,2021:1-6. [21] WEN Liang, LIANG Bing, ZHANG Liya, et al. Research on coal volume detection and energy-saving optimization intelligent control method of belt conveyor based on laser and binocular visual fusion[J]. IEEE Access,2024,12:75238-75248. doi: 10.1109/ACCESS.2023.3261335 [22] 孙朋朋,赵祥模,蒋渊德,等. 降雨条件对车载激光雷达性能影响的试验研究[J]. 中国公路学报,2022,35(11):318-328.SUN Pengpeng,ZHAO Xiangmo,JIANG Yuande,et al. Experimental study of influence of rain on performance of automotive LiDAR[J]. China Journal of Highway and Transport,2022,35(11):318-328. [23] 郭鹏飞,张希,黄永晖,等. 面向降雨环境的激光雷达衰减模型研究[J]. 汽车技术,2023(1):1-8.GUO Pengfei,ZHANG Xi,HUANG Yonghui,et al. Research on LiDAR attenuation model for raining environment[J]. Automobile Technology,2023(1):1-8. -
点击查看大图
计量
- 文章访问数: 70
- HTML全文浏览量: 25
- PDF下载量: 2
- 被引次数: 0
