CUSUM Procedures for Monitoring Process Mean and Variability

Cumulative sum (CUSUM) control schemes are widely used in industry for process and measurement control. Most CUSUM applications have been in monitoring shifts in the mean level of a process or in the process variability separately. In this article, we proposes a CUSUM chart based on the likelihood ratio test for the change point problem for normal process when controlling process mean and variability simultaneously. A Markov chain model is developed to analyze the performance of the new chart. Some numerical results and comparisons have been given. It has been shown that the new chart has an average run length performance that is superior to other procedures.