Monitoring of Process Parameters Under Measurement Errors

Exact measurement is a rare phenomenon in any of the situations where human involvement is evident. By and large error does appear in measuring or observing the characteristic(s) of concern. The conventional control charting design structures generally ignore such effect(s). This study aims at highlighting the practical situations with measurement errors and examining the effect of measurement errors in Phase I on the run length performance of some conventional Shewhart control charts namely the (X) over bar chart, the R chart, and the S-2 chart in the monitoring phase. The focus of the study is to see whether and how these measurement errors deteriorate the diagnostic ability of the said charts in terms run length characteristics. We have provided some remedial adjustment in the control structures of these charts in terms of control limits coefficients and also suggested some other solutions to the problem. Finally we have provided a couple of illustrative examples for practical considerations.