A simulation based optimization approach for scheduling of a semiconductor manufacturing system

As an important and challenging problem, the scheduling of semiconductor manufacturing is a hot topic in both engineering and academic field. Its purpose is to satisfy production constraints on time, cost and quality while optimizing some performance indexes like cycle-time, movement, WIP and etc. However, due to complexities of semiconductor manufacturing system, conventional technologies and/or methods are hard to solve this kind of scheduling problem. A new scheduling approach based on simulation based optimization (SBO) is proposed in this paper. For the issue of the high computational cost including both CPU time and memory space which could hinder the application of SBO scheduling in practice, a distributed/parallel architecture is discussed. With genetic algorithm as an optimization algorithm, the proposed SBO based scheduling approach for semiconductor manufacturing system is tested on its feasibility and effectiveness.