• 论文 • 上一篇    下一篇

 基于拟合优度检验的非参数EWMA 控制图

李阳,丁冬   

  1. 西安工程大学管理学院, 西安 710048
  • 出版日期:2020-05-25 发布日期:2020-08-21

李阳,丁冬.  基于拟合优度检验的非参数EWMA 控制图[J]. 系统科学与数学, 2020, 40(5): 917-926.

LI Yang, DING Dong. Goodness-of-Fit Test-Based Nonparametric EWMA Control Chart[J]. Journal of Systems Science and Mathematical Sciences, 2020, 40(5): 917-926.

Goodness-of-Fit Test-Based Nonparametric EWMA Control Chart

LI Yang, DING Dong   

  1. School of Management, Xi’an Polytechnic University, Xi’an 710048
  • Online:2020-05-25 Published:2020-08-21

文章提出了一种基于拟合优度检验的非参数控制图, 以实现对连续型数据的监控. 所提出的方法不仅适用于单值观测的情况, 也可用于分组样本. 不同于传统的控制图要求数据服从正态分布, 文章的方法不限制数据的分布, 可用于正态以及非正态的任意分布; 并且能够监控数据分布的变化, 例如分布中的位置参数、尺度参数、以及形状参数等. 仿真结果表明, 文章提出的控制图计算迅速、使用方便, 在各种分布下都表现稳健, 对分布变化的监控非常有效.

This article proposes a new powerful nonparametric method for the monitoring of continuous data. The proposed method, based on the integration of a goodness-of-fit test and the exponentially weighted moving average (EWMA) control scheme, can apply to individual observations and group observations. Conventional control charts usually require the normal assumption, so that they cannot perform well when the normal assumption is violated. To tackle this problem, we propose a nonparametric method that can deal with any distribution, normal or abnormal. The proposed method can detect any changes of the distribution, for instance changes in location parameter, scale parameter, and shape parameter. Simulation results demonstrate that the proposed chart is easy to implement, robust under various distributions, and powerful in detecting shifts.

()
[1] 张军舰. 含估计参数的加权经验过程[J]. 系统科学与数学, 2009, 29(5): 608-616.
阅读次数
全文


摘要