Accurately predicting the order flowtime for a wafer fab is a critical task
. Previous investigations involving flowtime estimation of the regression a
pproach have extensively applied the macro flowtime estimation concept. The
'macro' flowtime estimation concept constructs only one aggregate model to
estimate the flowtime as a whole. In contrast, the 'micro' flowtime estima
tion approach constructs an individual regression model for each stage of o
peration to estimate its individual flowtime. The cumulative order estimate
d flowtime is then the sum of the individual estimated operation flowtime.
Each approach has its own merits and limitations. Therefore, in this study
we examine the feasibility of mixing the macro and micro flowtime estimatio
n models. Comparing the proposed model with a variety of macro and micro mo
dels reveals that the mixed macro and micro flowtime estimation model can a
chieve a balance between flowtime estimation error and model complexity.