High-dimensional process monitoring when a few Phase I samples are available

In this article, we investigate Phase II monitoring of high-dimensional processes when the available number of samples collected in Phase I is limited in comparison to the number of variables. We propose a unified procedure for Phase I and II by employing a self-starting control chart. Results show that the proposed control chart scheme effectively detects various kinds of shifts in the process mean vector. Finally, we illustrate the applicability of our proposed method via a manufacturing application.