作者: L. Li , H. Xu
DOI: 10.1109/COASE.2013.6653974
关键词: Off line 、 Workflow 、 Semiconductor wafer fabrication 、 Scheduling (production processes) 、 Selection algorithm 、 Engineering 、 Real-time computing 、 Learning based 、 Weighting 、 Semiconductor device fabrication
摘要: Uncertainties in semiconductor manufacturing fabrication facilities (FABs) requires scheduling methods adaptive to real-time environments. This paper presents an off-line learning based dispatching rule (ADR) whose parameters are tuned dynamically with information relevant scheduling. First, we introduce the framework of ADR composed dynamic dispatching, machine, and simulation model. Secondly, discuss workflow detail. Thirdly, use immune cloning selection algorithm (ICSA) find relations between weighting status adapt these environment. Finally, a real fab model is used demonstrate proposed method. The results show that changing tracking production over time more robust than constant ones, improve movements WIP by about 2%.