Mixing macro and micro flowtime estimation model: wafer fab example

Abstract

Accurately predicting the order flowtime for a wafer fab is a critical task. Previous investigations involving flowtime estimation of the regression approach 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 estimation approach constructs an individual regression model for each stage of operation to estimate its individual flowtime. The cumulative order estimated 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 estimation models. Comparing the proposed model with a variety of macro and micro models reveals that the mixed macro and micro flowtime estimation model can achieve a balance between flowtime estimation error and model complexity.