| Summary: | 碩士 === 國立交通大學 === 工業工程與管理學系 === 85 === The control charts are the most useful tool of statistical
process control(SPC). Among various types of control charts, c-
chart is used in IC fabrication to monitor the defect counts on
wafers. As the surface area of wafer of IC increases, the
clustering phenomenon of the defects becomes more apparent.
Consequently, the clustered defects frequently cause many false
alarms when the conventional c-chart based on Poisson-based c-
chart is used. To reduce the number of false alarms caused by
clustered defects, Albin and Friedman suggested to construct the
defect control charts based on the Neyman type-A distribution.
One of the multivariate statistical techniques, cluster
analysis, can also be utilized to modify the conventional c-
chart. The purpose of this thesis is to design an economic
control chart by using the Duncan''s economical idea. Economic
models for defect control charts based upon Neyman type-A
distribution and cluster analysis are derived. The models can
assist the engineer or analyst to select a sample size, a
sampling frequency, and the control limits with minimum cost. A
numerical example is given to demonstrate the effectiveness of
the derived economic models. Sensitivity analysis of the models
are also discussed.
|
|---|
