This paper can be considered as an extension of the work of Tran et al (for monitoring compositional data using a multivariate exponentially weighted moving average MEWMA‐compositional data [CoDa] chart) by taking into account potential measurement errors that are known to highly affect production processes. A linearly covariate error model with a constant error variance is used to study the impact of measurement errors on the MEWMA‐CoDa control chart. In particular, the influence of the device parameters (σ_M,b), the number of independent observations m, and the the number of variables p are investigated in terms of the MEWMA optimal couples (r,H) as well as in terms of their corresponding ARLs. A comparison between the Hotelling‐CoDa T² and the proposed chart is made in order to show that the MEWMA‐CoDa chart is more efficient in detecting shifts in the presence of measurement errors. A real‐life example of muesli production, using multiple measurements for each composition, is used to estimate the parameters and also to demonstrate how the MEWMA‐CoDa can handle measurement errors to detect shifts in the process.

中文翻译：

---

存在测量错误时MEWMA‐CoDa控制图的性能

考虑到已知会严重影响生产的潜在测量误差，可以将本文视为Tran等人（用于使用多元指数加权移动平均MEWMA-成分数据[CoDa]图表监视成分数据）工作的扩展。流程。具有恒定误差方差的线性协变量误差模型用于研究测量误差对MEWMA-CoDa控制图的影响。特别地，所述设备参数的影响（σ_中号，b），独立观测值的数量中号和变量的数量p被在MEWMA最佳耦合的术语（调查- [R ，ħ）及其相应的ARL。将Hotelling-CoDa T ²与拟议的图表进行了比较，以显示MEWMA-CoDa图表在存在测量误差的情况下更有效地检测偏移。一个真实的牛奶什锦早餐生产示例，对每个成分进行多次测量，用于估计参数，并演示MEWMA-CoDa如何处理测量误差以检测过程中的变化。