Production planning for semiconductor manufacturing under demand and yield uncertainty
•We propose a stochastic programming model for a complex semiconductor production planning problem under uncertainty.•We consider demand uncertainty in the market and production and process yield uncertainties from the production process and implement them in our model.•We use a hybrid push–pull pol...
Gespeichert in:
Veröffentlicht in: | Computers & industrial engineering 2024-10, Vol.196, p.110403, Article 110403 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | •We propose a stochastic programming model for a complex semiconductor production planning problem under uncertainty.•We consider demand uncertainty in the market and production and process yield uncertainties from the production process and implement them in our model.•We use a hybrid push–pull policy and implement in-house production and outsourcing into the model.•We apply the model on a test case problem and provide managerial insights for the problem.
In this paper, we study a complex semiconductor production planning problem under uncertainties due to product demand, and production and process yields. The studied semiconductor manufacturing processes consists of facilities for wafer fabrication, sort, assembly, test, and demand centers. We consider the fabrication and sort facilities as a single unit called the Front-End and the assembly and test facilities as another single unit called the Back-End. The production processes are considered to follow a push policy in the Front-End and a pull policy in the Back-End. We propose a multi-stage stochastic programming model for this problem and apply the model to a large data set. We perform various analyses to understand the effect of these uncertainties on the semiconductor manufacturing decisions and its profit and provide interesting managerial insights. Our experiments verify the usefulness of our proposed stochastic programming model. |
---|---|
ISSN: | 0360-8352 |
DOI: | 10.1016/j.cie.2024.110403 |