The Proper Selection of Control Charts under Small Sustained Shifts in the Process Mean

• Main Authors: Lin, Ming Yi, 林明毅
• Other Authors: Pan J. N.
• Format: Others
• Language: zh-TW
• Published: 1998
• Online Access: http://ndltd.ncl.edu.tw/handle/23627282091394776890

碩士 === 國立成功大學 === 統計學系 === 86 === The Shewhart control charts are used by most factories but it can not effectively detect the small sustained shifts in the process mean, hence high-tech companies have started using the exponentially weighted moving average control chart (EWMA) and cumulative sum control chart (CUSUM) for monitoring the process and product quality. Prior research have shown that EWMA and CUSUM control charts have similar performance, but most quality engineers have the problem of identifying the appropriate conditions for each chart when monitoring process quality. In this research, we find that the effectiveness of either the EWMA or CUSUM control chart can be measured by using the relative increase of the Average Run Length to determine which chart is superior. Finally, a decision flow chart has been developed to show the procedure of proper selection of control charts under the small sustained shifts in the mean. Numerical examples have also been given to demonstrate the use of the above procedure for both indenpendent and correlated data.