A fuzzy-neural approach for optimizing the performance of job dispatching in a wafer fabrication factory

A fuzzy-neural approach is presented in this study to optimize the performance of job dispatching in a wafer fabrication factory. The traditional optimization methods in this field have a few problems. To tackle these problems, we performed several treatments. First, we applied a more effective fuzzy-neural approach to estimate the remaining cycle time of a job. Then we established a systematic procedure to determine the optimal values of the parameters in the two-factor tailored nonlinear fluctuation smoothing rule for the mean cycle time, in order to optimize the scheduling performance. To assess the effectiveness of the proposed methodology, we conducted a production simulation. According to the experimental results, the proposed methodology is better than the existing approaches in optimizing the average cycle time.