Monitoring multi-stage sequential manufacturing processes: a Bayesian approach

Abstract

We have developed a process monitoring system, in a Bayesian framework, which is designed to be used for monitoring VLSI and other multi-stage manufacturing processes. For a single-step process, the Bayesian monitor is at least as good as the Shewhart-CUSUM charts for detecting changes in the distribution of the in-lines collected from the step. For a multi-stage process, however, the Bayesian monitor can significantly reduce the detection time by using in-line correlation information from earlier stages.