检测尺度参数的非参数控制图
Distribution-Free Control Charts for Detecting Process Scale
-
摘要: 本文基于Ansari-Bradley检验提出两种在过程分布未知时检测过程尺度参数的非参数控制图,即混合指数加权移动平均与累积加和(mixed exponentially weightedmoving average\,--\,cumulative sum, EWMA-CUSUM)控制图与混合累积加和与指数加权移动平均(mixed cumulative sum\,--\,exponential weighted moving average, CUSUM-EWMA)控制图.通过比较平均运行链长等多个指标来衡量控制图的性能表现,并考虑了阶段I及阶段II样本容量对阶段~II~检测性能的影响.最后用实例来说明本文提出的控制图的实际应用.Abstract: In this paper, we propose distribution-free mixed exponentially weighted moving average-cumulative sum (EWMA-CUSUM) and mixed cumulative sum -- exponentially weighted moving average (CUSUM-EWMA) control charts based on the Ansari-Bradley test for detecting process scale without any distributional assumption of the underlying quality process. The performances of the proposed charts are measured in terms of average run-length and some other performance indexes. The effect of sample size in phase I and phase II on phase II of the proposed charts is also investigated. The application of the new chart is illustrated by real data examples.