Abstract
Monitoring, control and improvement of measurement systems performance are an important aspect of process and quality engineering. Gauge and measurement systems capability studies are often used to estimate the inherent variability of error in the gauge. Control charts of measurement error and periodic calibration activities can be employed to keep these systems operating properly. We describe and illustrate the use of a time series model to further improve gauge performance. The model is used to represent non-independent structure in the time series of measurement bias errors. Adjustments to actual process measurements are then based on the estimates of bias error from the model. The technique is applied to a measurement system used in semiconductor manufacturing, resulting in a reduction in the magnitude of measurement error of approximately 40%.
Original language | English (US) |
---|---|
Pages (from-to) | 273-280 |
Number of pages | 8 |
Journal | Quality and Reliability Engineering International |
Volume | 14 |
Issue number | 4 |
DOIs | |
State | Published - Aug 1998 |
Keywords
- Autocorrelated errors
- Gauge bias
- Gauge error
- Semiconductor testing
- Time series models
ASJC Scopus subject areas
- Safety, Risk, Reliability and Quality
- Management Science and Operations Research