基于高质量过程的指数分布中位数控制图的统计设计  

Statistics design of exponential distributed median control chart based on the high-quality process

作　　者：曹程明 马义中[1] CAO Chengming;MA Yingzhong(School of Economics and Management,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学经济管理学院,江苏南京210094

出　　处：《计算机集成制造系统》2020年第3期641-647,共7页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(71471088)。

摘　　要：针对事件间隔时间服从指数分布的高质量过程的监控问题,给出参数已知和未知情况下的中位数控制图设计方法;应用条件错误警报概率、受控时控制图的平均运行链长均值AARL及其标准差SDARL分析了参数估计对所设计控制图性能的影响;在小样本情况下,采用Bootstrap方法对所设计控制图的控制限进行调整,结果表明调整后的控制限能够有效减少参数估计对控制图性能的影响。最后用实例说明了所设计控制图应用的有效性。To monitoring the time between events following exponential distribution of the high quality process,firstly,the design procedure of the median control chart was proposed to monitor time between events following exponential distribution for both the known and unknown parameter case.Then,the effects of parameter estimation on the chart performance were evaluated in terms of conditional false alarm rate,the AARL and the SDARL.Thirdly,the bootstrap method was proposed to adjust the control limits for the small sample problem.Results showed that the adjusted control limits could efficiently reduce the effects of parameter estimation on the chart performance.Finally,an illustrative example was given to verify the effectiveness of the proposed control chart.

关 键 词：事件间隔时间 中位数控制图 参数估计 平均运行链长 BOOTSTRAP方法 

分 类 号：O213.1[理学—概率论与数理统计]