Incorporating Future Release Plan in Predicting Wafer Lot Output Time with a Hybrid ANN

Output time prediction is a critical task to a wafer fab (fabrication plant). However, traditional wafer lot output time prediction methods are based on the historical data of the fab. The influence of the future release plan has been neglected. In addition, a lot that will be released in the future might appear in front of another lot that currently exists in the fab. For these reasons, to further improve the accuracy of wafer lot output time prediction, the future release plan of the fab has to be considered, and a hybrid ANN (SOM+FBPN) incorporating the future release plan of the fab is proposed in this study. Production simulation is also applied to generate test examples. According to experimental results, the prediction accuracy of the proposed methodology was significantly better than those of three approaches, FBPN, evolving fuzzy rules (EFR), and the hybrid ANN without considering the future release plan in most cases by achieving a 20%~49% (and an average of 35%) reduction in the root-mean-squared-error (RMSE) over the comparison basis – the FBPN. Key-Words: Output time prediction; Future release plan; Fuzzy back propagation network; Self-organization map; Wafer fab