检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:王鑫[1,2] 向忠[1,2] WANG Xin;XIANG Zhong(School of Mechanical Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,China;Zhejiang Sci-Tech University Pingyang Research Institute Company,Wenzhou,Zhejiang 325400,China)
机构地区:[1]浙江理工大学机械工程学院,浙江杭州310018 [2]浙江理工大学平阳研究院有限公司,浙江温州325400
出 处:《轻工机械》2024年第3期92-99,107,共9页Light Industry Machinery
摘 要:为提高氧化锌电阻片的生产环节自动化水平,课题组设计了一种针对电阻片侧面绝缘涂层自动滚涂设备。设计了自动滚涂机构,由2个滚轴分别实现电阻片的滚涂和均匀刮抹;基于改进的YOLOv8模型的点位检测算法设计了基于视觉引导的拆垛机构,在YOLOv8中融入了动态稀疏注意力(bi-level routing attention, BRA)模块并将特征融合方式改为双向特征金字塔网络(bidirectional feature pyramid network, BiFPN)。与原有YOLOv8模型相比,改进的YOLOv8在识别精度上取得了显著的提升,平均均值精度(mean average precision, mAP)从92.8%提升至95.3%,从而在实际应用中降低了电阻片的漏检率和错检率,使漏检率相对减少了26.2%,错检率相对减少了33.3%。自动涂绝缘层设备为电阻片涂覆提供了高效的自动化解决方案。To enhance the automation rate of the production process of zinc oxide resistor chips,an automatic rolling coating device for applying insulating coatings on the side surfaces of the resistor chips was designed.An automatic rolling coating mechanism with two rollers was designed to realize rolling coating and uniform scraping of the resistor respectively.A de-stacking mechanism guided by vision was designed based on an improved YOLOv8-based point detection algorithm.The BRA module was integrated and the feature fusion method was changed to BiFPN in YOLOv8.Compared with the original YOLOv8 model,the improved YOLOv8 had achieved significant improvements in recognition accuracy,with the MAP increasing from 92.8%to 95.3%,which reduced the missed detection rate and false detection rate of resistor chips in practical applications,resulting in a relative reduction of 26.2%in the missed detection rate and 33.3%in the false detection rate.The automatic rolling coating equipment provides an efficient automated solution for coating resistors.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:13.59.84.174