An Adaptive Moving Average (A-MA) Control Chart with Variable Sampling Intervals (VSI)

摘要: This paper proposes an adaptive moving average (A-MA) control chart with variable sampling intervals (VSI) for detecting shifts in the process mean. The basic idea of VSI A-MA is to adjust as well accumulate previous samples selectively order increase sensitivity. employs a threshold limit determine whether or not rate samples. If standardized statistic falls outside limit, next sample taken higher and accumulated calculate statistic. within lower only used get produces 'out-of-control' signal either when any L-consecutive statistics fall limit. length L introduced prevent small mean from being undetected long period. A Markov chain model employed investigate process. Formulae related steady state time-to (ATS) in-control out-of-control are derived closed forms. statistical design procedure proposed. Comparative studies show that proposed uniformly superior Cumulative sum (CUSUM) Exponentially Weighted Moving Average (EWMA) chart, comparable size (VSS) EWMA respect ATS performance.