| 189 | 0 | 72 |
| 下载次数 | 被引频次 | 阅读次数 |
针对GDX6包装机人工装载商标纸效率低、成本高等问题，设计了基于3D视觉的GDX6包装机商标纸智能装载系统。该系统采用3D视觉相机采集商标叠图像，利用YOLOv5s-seg实例分割模型对商标叠进行检测，检测的商标叠平面坐标与场景点云信息进行匹配，获得分割点云信息，最终得到商标叠的位姿结果。根据位姿结果，协作机器人输送商标叠至无损切割及分离装置进行无损切割和分离包裹纸，进一步通过放置料库将商标叠输送至包装机传送带上。结果表明：该系统能够对商标叠实现快速的实例分割和位姿估计，性能可代替人工完成正常生产过程中的各项要求，提高了包装机组自动化水平和生产效率。
Abstract：In response to the issues of low efficiency and high cost of manual loading of trademark paper in the GDX6 packaging machine, this paper designs an intelligent loading system for the trademark paper based on 3D vision. The system uses a 3D vision camera to capture trademark stack images. The YOLOv5s-seg instance segmentation model is used to detect the trademark stacks. The detected flat coordinates of the trademark stack are matched with the scene point cloud information to obtain the segmented point cloud data, ultimately determining the pose of the trademark stacks. According to the pose results, a collaborative robot delivers the trademark stacks to a non-destructive cutting and separation device to perform non-destructive cutting and separate the wrapper paper. Subsequently, the trademark stacks are transported to the packaging machine conveyor belt through a placing material storage. The results show that the system can quickly perform instance segmentation and pose estimation of the trademark stacks, achieving the requirements of normal production processes and replacing manual labor. This improves the automation level and production efficiency of the packaging machine unit.
[1]意大利G.D公司. GDX6操作说明书[G]. 2009.Italy G.D company. GDX6 operating instructions[G]. 2009.
[2]李丹，周延辉，周明，等.基于遗传算法的卷烟换牌排产与优化设计[J].烟草科技，2019, 52(05):94-99.LI Dan, ZHOU Yanhui, ZHOU Ming, et al. Cigarette replacement scheduling and optimization design based on genetic algorithm[J].Tobacco Science&Technology, 2019, 52(05):94-99.
[3]王青，王宇璐.工业机器人应用对制造业高质量发展的影响研究[J].工业技术经济，2023, 42(02):115-124.WANG Qing, WANG Yulu. Research on the impact of industrial robot applications on the high-quality development of manufacturing industry[J]. Industrial technology and economy, 2023, 42(02):115-124.
[4]孙立宁，许辉，王振华，等.工业机器人智能化应用关键共性技术综述[J].振动.测试与诊断，2021, 41(02):211-219+406.SUN Lining, XU Hui, WANG Zhenhua, et al. Summary of key common technologies for intelligent application of industrial robots[J].Vibration. Test and diagnosis, 2021, 41(02):211-219+406.
[5]黄文镇.机器人在卷烟工业企业成品生产物流中的应用[J].造纸装备及材料，2021(06):46-48.HUANG Wenzhen. Application of robots in finished product production logistics of cigarette industrial enterprises[J].Papermaking equipment and materials, 2021(06):46-48.
[6]杨剑锋，徐智勇，赵云斌，等.机器人自动上箱系统在卷烟装封箱机组的应用[J].烟草科技，2013(02):20-23.YANG Jianfeng, XU Zhiyong, ZHAO Yunbin, et al. Application of robot automatic loading system in cigarette packing machine[J].Tobacco Science&Technology, 2013(02):20-23.
[7]于德福，孟庆华，文银地.烟丝储运系统的升级改造[J].物流工程与管理，2022(08):46-49.YU Defu, MENG Qinghua, WEN Yindi. Upgrading of tobacco storage and transportation system[J]. Logistics Engineering and Management, 2022(08):46-49.
[8]张晓东，苏瑞芳，董唯光.基于自适应分块的工业机器人压缩感知视觉图像处理[J].自动化与仪表，2021, 36(08):38-42.ZHANG Xiaodong, SU Ruifang, DONG Weiguang. Compressed sensing visual image processing of industrial robots based on adaptive block[J]. Automation and instrumentation, 2021, 36(08):38-42.
[9]陈晓东，石江涛，贾仁耀. 3D机器视觉在智能机器人拆垛中的应用[J].电气应用，2019, 38(S1):31-35.CHEN Xiaodong, SHI Jiangtao, JIA Renyao. Application of 3D machine vision in intelligent robot unstacking[J]. Electrical application, 2019, 38(S1):31-35.
[10]崔旭东，谭欢，王平江，等.基于3D视觉的散乱堆放工件机器人抓取技术研究[J].制造技术与机床，2021,(02):36-41.CUI Xudong, TAN Huan, WANG Pingjiang, et al. Research on robotic grasping technology for scattered stacked workpieces based on 3D vision[J]. Manufacturing Technology and Machine Tools,2021,(02):36-41.
[11]赵云涛，唐千，王晓飞，等.融合3D视觉的机器人自主更换变压器熔断器系统[J].自动化与仪表，2020, 35(03):46-48+57.ZHAO Yuntao, TANG Qian, WANG Xiaofei, et al. Robot autonomous replacement of transformer fuse system with 3D vision[J]. Automation and Instrumentation, 2020, 35(03):46-48+57.
[12]王德明，颜熠，周光亮，等.基于实例分割网络与迭代优化方法的3D视觉分拣系统[J].机器人，2019, 41(05):637-648.WANG Deming, YAN Yi, ZHOU Guangliang, et al. 3D visual sorting system based on instance segmentation network and iterative optimization method[J]. Robot, 2019, 41(05):637-648.
[13]张浩，陈成军，潘勇.基于视觉的工业机器人装配演示示教研究[J].机床与液压，2023, 51(19):25-31.ZHANG Hao, CHEN Chengjun, PAN Yong. Research on visionbased industrial robot assembly demonstration teaching[J].Machine and Hydraulics, 2023, 51(19):25-31.
[14]杨平，王博，骆凯鑫.基于机器视觉的蜗壳智能识别拆垛系统[J].组合机床与自动化加工技术，2022,(11):38-43.YANG Ping, WANG Bo, LUO Kaixin. Intelligent recognition and unpacking system for snail shell based on machine vision[J].Combination Machine Tool and Automation Processing Technology, 2022,(11):38-43.
[15]李伟，杨超宇，孟祥瑞.融合启发式搜索的改进极快决策树算法在多规格货物智能混合装载中的应用[J].科学技术与工程，2020, 20(36):15074-15080.LI Wei, YANG Chaoyu, MENG Xiangrui. Application of improved ultra fast decision tree algorithm with heuristic search in intelligent hybrid loading of multi specification goods[J]. Science, Technology and Engineering, 2020, 20(36):15074-15080.
[16]刘宝临，邹汶材.基于视觉定位的机器人智能拆垛系统[J].计算机系统应用，2023, 32(07):138-144.LIU Baolin, ZOU Wencai. Robot intelligent palletizing system based on visual positioning[J]. Computer System Application, 2023,32(07):138-144.
[17]黄涛，李华，周桂，等.实例分割方法研究综述[J].计算机科学与探索，2023, 17(04):810-825.HUANG Tao, LI Hua, ZHOU Gui, et al. Review of instance partitioning methods[J]. Computer Science and Exploration, 2023,17(04):810-825.
[18] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified,real-time object detection[C]//Proceedings of the 2016IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE, 2016:799-788.
[19] HE K, GKIOXARI G, PIOTR DOLLAR, et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision. New York:IEEE Press, 2017:2961-2969.
基本信息:
DOI：10.16472/j.chinatobacco.2024.T0314
中图分类号:TS43;TP391.41;TP18
引用信息:
[1]张志彬,蒋景强,陈瑾龙等.基于3D视觉的GDX6包装机商标纸智能装载系统[J].中国烟草学报,2025,31(04):22-33.DOI:10.16472/j.chinatobacco.2024.T0314.
基金信息:
福建中烟工业有限责任公司技术改进类重点科技项目“高速包装机商标纸智能装载系统自主研发与应用”(FJZYKJJH2023ZD036)