Real-time rule-based scheduling system for integrated delivery in a semiconductor manufacturing using evolutionary algorithm-based simulation approach

Abstract

In a wafer fabrication facility, automated material handling system (AMHS) to dispatch the material flow is a critical and challenging task. This paper investigates the integrated delivery of automated material handling system (AMHS) and processing tools for a large-scale complex wafer fabrication facility. Although the dispatching rules are one of the most frequently used approach for effective semiconductor manufacturing schedule, it is necessary to adapt new techniques due to time-consuming nature of dispatching rules when the number of variables and iterations increases. There are very few studies on enhancing the rule-based scheduling system. To address this issue, we proposed an evolutionary algorithmic approach for enhancing the rule-based scheduling system. We explored the best possible genetic algorithm parameters from famous approach called Taguchi, and then, statistical analysis, i.e., regression analysis, has been conducted to find out the significance of the parameters. Later, with hierarchical rule-based scheduling approach, the combined sequential dispatching rules are formed to achieve better efficiency and effectiveness of the scheduling.