A novel adaptive CUSUM system for efficient process mean monitoring: An application in piston ring manufacturing process

The adaptive versions of charting tools are well-established statistical monitoring techniques for detecting unknown changes in the process over a range of shifts. A re-weighted adaptive CUSUM mean (RACUSUM) charting scheme has been proposed in this study for monitoring the range of shifts. The proposed RACUSUM statistic estimates the unknown changes in the ongoing process using an EWMA statistic by plugging in an unbiased shift estimator and choosing a suitable smoothing constant according to the estimated shift to update the slack value of the CUSUM statistic. By employing Monte Carlo simulation using the zero- and steady-state processes, the proposal's run-length (RL) profiles have been calculated. The proposed RACUSUM chart shows more sensitive behavior under the shift delay process than in the case of zero-state. A comparative analysis between the proposal and competitors has been presented using average RL, extra quadratic loss (EQL), and the relative mean index (RMI) as metrics for 1-sided and 2-sided charting schemes. The robustness of the proposed 2-sided RACUSUM chart against non-normality has also been reported. The proposal's applicability has been demonstrated using two cases, one from the artificial and the other from a dataset of piston ring manufacturing industrial process.