Dynamic fuzzy-neural fluctuation smoothing rule for jobs scheduling in a wafer fabrication factory

Abstract

The present paper proposes a dynamic fuzzy-neural fluctuation smoothing rule to improve the performance of scheduling jobs in a wafer fabrication factory. The rule is modified from the well-known fluctuation smoothing rules with some innovative treatments. First, two non-linear forms of the fluctuation smoothing rule are obtained. To consider two performance measures (the average cycle time and cycle time variation) simultaneously, the two non-linear fluctuation smoothing rules are merged into a bi-criteria rule. Second, to tailor the content of the bi-criteria rule for a specific wafer fabrication factory, a dynamic factor is designed which facilitates the gradual transition between rules. Third, the remaining cycle time of a job to be scheduled is estimated by applying the fuzzy c-means (FCM)-back-propagation network (BPN) approach to improve the estimation accuracy. To evaluate the effectiveness of the proposed methodology, production simulation is also applied in this study. According to experimental results, the proposed methodology outperforms some existing approaches in reducing the average cycle time and cycle time variation at the same time. Moreover, experimental results also reveal that with the dynamic rule it is possible to improve one performance measure without raising the expense of another performance measure.