Abstract

A control chart is used to monitor longitudinal measurements of a quality characteristic and detects undesirable causes of variability. In practice, measurement error may exist and deteriorate the detection capability of a control chart. This paper focuses on the effect of measurement errors on the performance of a joint monitoring scheme for mean and coefficient of variation (CV), which is a useful measure to monitor variability when the process mean fluctuates over time and process standard deviation is a linear function of process mean. Our results from the simulations and real data application demonstrated that measurement error affects the performance of the joint monitoring control chart and multiple measurements are recommended to avoid the adverse effects of measurement error.

摘要

控制图用于监控质量特性的纵向测量并检测不希望的可变性原因。在实践中，可能存在测量误差并降低控制图的检测能力。本文重点关注测量误差对均值和变异系数 (CV) 联合监测方案性能的影响，这是在过程均值随时间波动且过程标准差为线性函数时监测变异性的有用度量过程均值。我们的模拟和实际数据应用结果表明，测量误差会影响联合监控控制图的性能，建议进行多次测量以避免测量误差的不利影响。