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
机构地区:[1]西安理工大学印刷包装与数字媒体学院,陕西西安710048
出 处:《西安理工大学学报》2017年第2期240-246,共7页Journal of Xi'an University of Technology
基 金:国家自然科学基金资助项目(51305340;51275406);陕西省自然科学基础研究计划资助项目(2017JQ5012)
摘 要:针对印刷机定位故障隐蔽性强、诊断难度大等特点,本文提出基于主元分析的定位故障建模与诊断方法。首先,采集计算印刷机连续样张的轴向与周向机械误差数值,通过主元分析将原始数据投影到主元空间和残差空间,并完成故障模型的建立。其次,计算SPE控制限并以此判断印刷机定位状态是否发生异常。最后,利用主元载荷图解释各个主元构成,根据主元得分图获取不同故障模式下各个变量的分布特征,以实现故障机理的分析与解释。通过实验证明了所提出方法在故障识别和分析中的有效性,为印刷机定位故障诊断提供了新的技术方法和研究思路。Location faults in offset press always have very strong confidentiality, so it is very difficult to diagnose. A fault modeling and diagnosis method based on the principal component analysis (PCA) was proposed, which consists mainly of three steps First, the feeding deviations of an offset press during printing continuous sheets are obtained in both circumferential and axial directions, and then they are projected into principal component space and residual space, thereby establishing a fault model Second, PSE control limit is calculated to judge whether the locating status is normal or not Finally, the composition of each principal component is determined according to the PCA load diagram, and the distribution feature of each variable under different fault modes is obtained based on the PCA score plot so as to reveal the fault mechanism. The effectiveness of this method in the recognition and analysis of fault was confirmed by experiments. The work can provide a new insight into the diagnosis of location fault in offset press.
分 类 号:TH17[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]
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:3.137.142.253