Job scheduling (or dispatching) in a wafer fabrication factory is an extremely difficult task. For this reason, a modified dynamic-bottleneck-detection (MDBD) approach is proposed in this study. The MDBD approach is modified from the well-known DBD approach with some innovative treatments. First, for non-bottleneck and bottleneck machines, different scheduling approaches are applied. Second, the remaining cycle time of a job was estimated by applying an advanced data-mining approach to improve the estimation accuracy. Third, the content of the modified DBD approach can be tailored to the wafer fabrication factory. To evaluate the effectiveness of the proposed methodology, production simulation was also applied in this study. According to the experimental results, the proposed methodology outperformed some existing approaches in reducing the average cycle time and cycle time standard deviation.
|頁（從 - 到）||396-405|
|期刊||International Review on Computers and Software|
|出版狀態||Published - 1 七月 2010|