基于符号秩统计量的非参数阶段累积和控制图  

Non-parametric Step Cumulative Sum Control Chart Based on Signed-rank

作　　者：徐薪苡 朱永忠[1] 杨亦浏 XU Xinyi;ZHU Yongzhong;YANG Yiliu(School of mathematics,Hohai University,Nanjing,Jiangsu 211100,China)

机构地区：[1]河海大学数学学院,江苏南京211100

出　　处：《计算技术与自动化》2025年第1期88-95,共8页Computing Technology and Automation

摘　　要：控制图是现代工业生产中常用的质量控制方法,传统控制图通常在数据服从正态分布的情况下进行研究。然而,在实际生产过程中,数据的正态分布假设并不总是成立,且有时分布的情况未知。针对这一状况,可以采用非参数控制图对生产过程进行监控。本文提出了一种基于Wilcoxon符号秩统计量的非参数阶段累积和控制图,通过对非参数累积和控制图的结构进行调整,使得所提出的控制图在监测不同范围的位置偏移时更加灵敏。通过模拟分析了该控制图的受控与失控表现,并与其他非参数控制图进行了比较.结果表明,本文提出的方法具有良好的监控效果。Control charts are commonly used quality control methods in modern industrial production,and traditional control charts are typically studied under the assumption that data follows a normal distribution.However,in actual production processes,the assumption of normal distribution for data does not always hold,and at times,the distribution is unknown.In response to this situation,non-parametric control charts can be employed to monitor the production process.This paper proposes a non-parametric step cumulative sum control chart based on the Wilcoxon signed-rank statistic.By adjusting the structure of the non-parametric cumulative sum control chart,it enhances sensitivity in detecting positional shifts across different ranges.The in-control and out-of-control performance of the proposed control chart is analyzed through Monte Carlo simulation methods and compared with other non-parametric control charts.The results indicate that the proposed control chart exhibits excellent monitoring performance.

关 键 词：非参数控制图 统计过程控制 Wilcoxon符号秩 平均运行链长 

分 类 号：O212[理学—概率论与数理统计]