This paper presents a fuzzy-neural system to further improve the performance of scheduling jobs in a wafer fabrication factory. The fuzzy-neural system is modified from the well-known FSVCT rule with three innovative treatments. First, the remaining cycle time of a job is estimated by applying Chen et al's fuzzy-neural approach to improve the estimation accuracy. Second, the components of the FSVCT rule are normalized, and then the division operator is applied instead of the traditional subtraction operator to enhance the responsiveness of the rule. Third, the content of the fuzzy-neural system can be tailored for the wafer fabrication factory and be scheduled with two adjustment factors. To evaluate the effectiveness of the proposed methodology, production simulation was applied to generate some test data. According to the experimental results, the proposed methodology outperformed nine existing approaches in reducing the cycle time average and standard deviation. In addition, the fuzzy-neural system is shown to be a Pareto optimal solution for scheduling jobs in a semiconductor manufacturing factory.
|Number of pages||14|
|Journal||International Journal of Innovative Computing, Information and Control|
|State||Published - 1 Feb 2010|
- Wafer fabrication