常规控制图应用的基本假设是从过程得到的测量值彼此独立,但许多连续型的制造业生产过程(例如化学和制药)往往存在自相关,此时常规控制图容易虚发警报。基于数据的样本自相关函数,本文改进了常规控制图的控制界限,使之适用于自相关过程,并运用常规Xˉ—s控制图和本文修正的X控制图对一个实际案例进行了比较分析,结果表明本文修正的Xˉ控制图可正确地判断过程是否处于受控状态。
Traditional control chart is based on a fundamental assumption that the process data are independent. However, in continuous-type processes, such as chemical and pharmacy, and such processes in which data are autocollected, the process data are often highly auto-correlated. Under such conditions, traditional control chart are not adequate and can lead to false alarms. In this paper, based on the sample autocorrelation function of data, the control limits are modified, which are suitable for all stationary auto-correlated processes. A comparison of traditional and modified X control charts is presented to an actual case, and the results show that the modified control chart can correctly detect whether the process is in control.