监控平方变异系数的MEWMA-γ^(2)控制图  

MEWMA-γ^(2) Control Chart for Monitoring Squared Coefficient of Variation

作　　者：李宁 朱永忠[1] LI Ning;ZHU Yong-zhong(College of Science,Hohai University,Nanjing,Jiangsu 211100,China)

机构地区：[1]河海大学理学院,江苏南京211100

出　　处：《计算技术与自动化》2023年第3期130-135,共6页Computing Technology and Automation

基　　金：国家自然科学基金面上资助项目(11771120)。

摘　　要：变异系数已广泛应用于不同领域来衡量资料中各观测值的变异程度。为了监控各种制造或服务过程的质量特性,记忆型控制图已成为一种重要的实时监控方案。提出了一种改进的指数加权移动平均变异系数(记为MEWMA-γ^(2))控制图,通过蒙特卡罗模拟研究了其在不同参数下的平均运行长度,并与其他EWMA控制图进行了比较分析。结果表明,所给控制图具有良好的监测能力。最后,利用机械零件烧结过程的实际数据,说明了该方法在应用中的优良性。The coefficient of variation has been widely used in different fields to measure the degree of variation of each observation in data.To monitor the quality characteristics of various manufacturing or service processes,the memory control chart has become a vital real-time monitoring scheme.This paper presents a modified exponentially weighted moving average(denoted as MEWMA-γ^(2))control chart for the coefficient of variation,studies its average run length under different parameters by Monte Carlo simulation,and compares it with other EWMA control charts.The results show that the proposed control chart has good performance.At the end of this paper,the advantages of this method in application is illustrated by the datasets of the sintering process of mechanical parts.

关 键 词：变异系数 MEWMA-γ^(2) 平均运行长度 

分 类 号：O212[理学—概率论与数理统计]