检测尺度参数的非参数控制图

Distribution-Free Control Charts for Detecting ProcessScale

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 weighted moving averagecumulative 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.

In this paper,we propose distribution-free mixed exponentially weighted moving averagecumulative 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.