Stochastic flow modeling for control of manufacturing system quality

The importance of quality control and management has long been demonstrated, with quality being shown to be as important as manufacturing productivity. The goal of this paper is to propose an accurate stochastic model that can represent quality data for supervisory control of manufacturing lines. In this paper, we develop a new application of the stochastic-flow modeling (SFM) approach to model the quality behavior of a manufacturing system. This work extends the basic one-product, one-station SFM to that of a multi- product, multi-station manufacturing system. The quality SFM- based model provides aggregation by machine, product, and operational shift. Bernoulli-type rejects, persistent rejects, and quality-loop rejects are addressed in the modeling. Following a presentation of the application physical system, results are given for different examples where the effectiveness of the SFM model is shown.