Identifying cycle time factors and its relative impact on tools in semi-conductor fab using statistical inferences

Abstract

This paper discusses a methodology using multiple linear regression as a tool to statistically identify, understand, and infer the factors affecting the wait time component of the tool set in a semi-conductor fab. The regression model is based on least-square estimators. This model can recognize the significant factors affecting the wait times of lots in front of the tool set, and their effect and magnitude. Results from the analysis can be used to set priorities and focus on high magnitude factors. It can also be used to study the interactions between the factors on the wait times.